Source: https://ailoot.ai/models/nb/k3-256k/
Canonical: https://ailoot.ai/models/nb/k3-256k/
Language: nb

# MoonshotAI: Kimi K3 (256K)

[Markdown](https://ailoot.ai/models/nb/k3-256k/index.md) · [JSON](https://ailoot.ai/models/nb/k3-256k/facts.json)

## [k3-256k](https://ailoot.ai/models/nb/k3-256k/)

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

- [**Ailoot · Anthropic Messages** `POST /v1/messages` `k3-256k`](https://ailoot.ai/models/nb/k3-256k/#method-0)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `k3-256k`](https://ailoot.ai/models/nb/k3-256k/#method-1)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `k3-256k`](https://ailoot.ai/models/nb/k3-256k/#method-2)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `kimi-256k`](https://ailoot.ai/models/nb/k3-256k/#method-3)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `kimi-256k`](https://ailoot.ai/models/nb/k3-256k/#method-4)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `kimi-256k`](https://ailoot.ai/models/nb/k3-256k/#method-5)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `kimi-256k-latest`](https://ailoot.ai/models/nb/k3-256k/#method-6)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `kimi-256k-latest`](https://ailoot.ai/models/nb/k3-256k/#method-7)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `kimi-256k-latest`](https://ailoot.ai/models/nb/k3-256k/#method-8)

Om modellen

Denne beskrivelsen dekker modellens funksjoner. Tilgjengelige inndata, utdata og alternativer i Ailoot er oppført nedenfor for den valgte metoden.

#### K3 med fast vindusstørrelse

`k3-256k` er en Kimi K3-variant med en kontekst på **262 144 tokener**. Den beholder bruksretningen til K3: langvarige tekniske oppgaver, arbeid med kode og verktøy og analyse av visuelt materiale. Vindusstørrelsen er fast for denne varianten, så krav, prosjektmateriale og arbeidshistorikk må holdes innenfor samme samlede omfang.

#### Kode og visuelle tilbakemeldinger

Modellen er laget for trinnvis utvikling med lesing av repositoriet, endringer og bruk av kjøreresultater. Produsenten beskriver K3 i oppgaver med optimalisering av beregningskode, utvikling av kompilatorer og arbeid med store prosjekter. Visuelt materiale kan bidra til å knytte implementeringen til det som vises på skjermen.

Bildeinndata er bekreftet for `k3-256k`. Dette kortet tar imot tekst og bilder, og modellen returnerer tekst. Verktøy for terminalen, fillesing eller programkjøring må kobles til av programmet; resultatene kan brukes til å fortsette dialogen.

#### Undersøkende arbeid

K3 knytter analyse av litteratur og data til programmering. Gjennom verktøy kan den bidra til implementering av beregninger, kontroll av formler og utarbeiding av interaktivt analysemateriale. Dette er nyttig i oppgaver der en konklusjon må knyttes til en beregning og fremgangsmåten vises.

#### Resonnering og oppbygning

Nivåene `low`, `high` og `max` støttes; produsentens gjeldende konfigurasjon angir `high` som standardverdi for `k3-256k`. Ved verktøyarbeid bruker modellen historikken med tidligere svar og resonnering.

Arkitekturen i K3 har totalt **2,8 billioner parametere** og omtrent **104 milliarder aktive**. Kimi Delta Attention og Attention Residuals brukes for lang kontekst, og MoonViT-V2 for visuelle inndata. Dette kortet gjelder nettopp varianten med et vindu på 262 144 tokener.

#### Grensene for en lang økt

K3 er følsom for om resonneringshistorikken er fullstendig. Produsenten advarer om at ufullstendig overføring av denne historikken eller bytte til K3 midt i arbeidet med en annen modell kan gjøre svarene ustabile. I krevende oppgaver kan den også være for initiativrik: ved et uklart mål kan den velge en handling på egen hånd. Ved verktøyarbeid må tillatte handlinger og stoppvilkår derfor angis uttrykkelig.

Praktisk oppgave

### Praktisk oppgave

Teknisk eksempel på engelsk

```
Preserve evaluation order in a compiler rewrite

A compiler optimizer replaces f() * 0 with 0. In this language, function calls may log messages or raise errors, and left-to-right evaluation is observable. Explain why the rewrite is unsafe, give the condition under which it would be valid and propose two regression tests. Return a focused optimization rule rather than a whole compiler design.
```

#### Forventet resultat

```
A concise diagnosis, a guarded rewrite rule and two tests covering observable effects.
```

#### Kontroller resultatet

```
The rule does not discard a call unless its lack of observable effects is established.
```

**Ailoot · Anthropic Messages** `POST /v1/messages` `k3-256k`

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages)

Moonshot /`k3-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · Anthropic Messages** `POST /v1/messages`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser k3-256k | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser user, assistant | Standard— |
| Felt`messages[].content` | Type`string\|content_block[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`system` | Type`string\|content_block[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`max_tokens` | Type`integer` | KravPåkrevd | Verdier & grenser Minimum: 1 Grensen gjelder for: den eksakte øvre grensen for valgt modell/kort | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop_sequences` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].name` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: verktøy oppgitt | Standard— |
| Felt`tools[].description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].input_schema` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.budget_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`output_config.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`metadata` | Type`object` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`cache_control` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content eller type=text-blokk`

**Tekst + bilde**

`{type:image,source:{type:base64,media_type,data}} eller en kilde med type=url`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages, max\_tokens |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · Anthropic Messages

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="k3-256k",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "k3-256k",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='k3-256k',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · Anthropic Messages

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold alle innholdsblokker, resonneringssignaturer og faktiske ID-er for verktøybruk. Sett sammen alle SSE-blokkendringer; den første tekstblokken er ikke hele resultatet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`model` | Typestring |
| Felt`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Felt`stop_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `k3-256k`

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses)

Moonshot /`k3-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Responses** `POST /v1/responses`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser k3-256k | Standard— |
| Felt`input` | Type`string\|input_item[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].type` | Type`string` | KravValgfritt | Verdier & grenser message, reasoning, function\_call, function\_call\_output | Standard— |
| Felt`input[].content` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output; behold faktisk returnert call\_id | Standard— |
| Felt`input[].output` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output | Standard— |
| Felt`max_output_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.summary` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.verbosity` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`include` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`store` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`previous_response_id` | Type`string` | KravValgfritt | Verdier & grenser ID-krav: Bare en faktisk svar-ID fra en støttet videreføring Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_key` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`inputtekst eller input_text-del`

**Tekst + bilde**

`{type:input_image,image_url}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, input |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Responses

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="k3-256k", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "k3-256k", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="k3-256k", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Responses

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert outputelement og hver innholdsdel, faktisk call\_id for funksjonen, kryptert resonnering og bruksdata. Ved strømming beholder du fullstendig hendelses-/elementidentitet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`status` | Typestring |
| Felt`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Felt`output[].content[]` | Typecontent part |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `k3-256k`

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat)

Moonshot /`k3-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser k3-256k | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser Eksempler: system, user, assistant, tool, function Vilkår: Disse rollene representeres eksplisitt av kompatibilitetstyper i kildekoden; det eksakte rollesettet for modellen er fortsatt modellspesifikt. Avhenger av modellen | Standard— |
| Felt`messages[].content` | Type`string\|content_part[]\|null` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_calls` | Type`tool_call[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: role=tool; bruk faktisk returnert ID | Standard— |
| Felt`messages[].name` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].reasoning_content` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: Send den faktisk returnerte resonneringen tilbake der denne modellen bruker den | Standard— |
| Felt`messages[].reasoning_details` | Type`object\|array` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`max_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`max_completion_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`stream_options.include_usage` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop` | Type`string\|string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`function_tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].function.name` | Type`string` | KravPåkrevd | Verdier & grenser Gjelder når: funksjonsverktøy oppgitt | Standard— |
| Felt`tools[].function.description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].function.parameters` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`response_format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning_effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser Kompatibilitetsfelt | Standard— |
| Felt`functions` | Type`function[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`function_call` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content`

**Tekst + bilde**

`{type:image_url,image_url:{url,detail}}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Chat

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="k3-256k",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "k3-256k",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='k3-256k',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Chat

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert svaralternativ med innhold, verktøykall og resonnering. Sett sammen endringer i SSE etter svaralternativets/verktøyets indeks, og behold endelig avslutningsgrunn og bruksdata.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`choices[].index` | Typeinteger |
| Felt`choices[].message.content` | Typestring\|null |
| Felt`choices[].message.tool_calls` | Typetool\_call\[\] |
| Felt`choices[].message.reasoning_content` | Typestring |
| Felt`choices[].message.reasoning_details` | Typeobject\|array |
| Felt`choices[].finish_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `kimi-256k`

[`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages)

Moonshot /`kimi-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · Anthropic Messages** `POST /v1/messages`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser user, assistant | Standard— |
| Felt`messages[].content` | Type`string\|content_block[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`system` | Type`string\|content_block[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`max_tokens` | Type`integer` | KravPåkrevd | Verdier & grenser Minimum: 1 Grensen gjelder for: den eksakte øvre grensen for valgt modell/kort | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop_sequences` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].name` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: verktøy oppgitt | Standard— |
| Felt`tools[].description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].input_schema` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.budget_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`output_config.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`metadata` | Type`object` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`cache_control` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content eller type=text-blokk`

**Tekst + bilde**

`{type:image,source:{type:base64,media_type,data}} eller en kilde med type=url`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages, max\_tokens |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · Anthropic Messages

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="kimi-256k",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "kimi-256k",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='kimi-256k',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · Anthropic Messages

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold alle innholdsblokker, resonneringssignaturer og faktiske ID-er for verktøybruk. Sett sammen alle SSE-blokkendringer; den første tekstblokken er ikke hele resultatet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`model` | Typestring |
| Felt`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Felt`stop_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `kimi-256k`

[`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses)

Moonshot /`kimi-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Responses** `POST /v1/responses`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k | Standard— |
| Felt`input` | Type`string\|input_item[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].type` | Type`string` | KravValgfritt | Verdier & grenser message, reasoning, function\_call, function\_call\_output | Standard— |
| Felt`input[].content` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output; behold faktisk returnert call\_id | Standard— |
| Felt`input[].output` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output | Standard— |
| Felt`max_output_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.summary` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.verbosity` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`include` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`store` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`previous_response_id` | Type`string` | KravValgfritt | Verdier & grenser ID-krav: Bare en faktisk svar-ID fra en støttet videreføring Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_key` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`inputtekst eller input_text-del`

**Tekst + bilde**

`{type:input_image,image_url}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, input |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Responses

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="kimi-256k", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "kimi-256k", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="kimi-256k", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Responses

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert outputelement og hver innholdsdel, faktisk call\_id for funksjonen, kryptert resonnering og bruksdata. Ved strømming beholder du fullstendig hendelses-/elementidentitet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`status` | Typestring |
| Felt`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Felt`output[].content[]` | Typecontent part |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `kimi-256k`

[`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat)

Moonshot /`kimi-256k`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser Eksempler: system, user, assistant, tool, function Vilkår: Disse rollene representeres eksplisitt av kompatibilitetstyper i kildekoden; det eksakte rollesettet for modellen er fortsatt modellspesifikt. Avhenger av modellen | Standard— |
| Felt`messages[].content` | Type`string\|content_part[]\|null` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_calls` | Type`tool_call[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: role=tool; bruk faktisk returnert ID | Standard— |
| Felt`messages[].name` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].reasoning_content` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: Send den faktisk returnerte resonneringen tilbake der denne modellen bruker den | Standard— |
| Felt`messages[].reasoning_details` | Type`object\|array` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`max_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`max_completion_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`stream_options.include_usage` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop` | Type`string\|string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`function_tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].function.name` | Type`string` | KravPåkrevd | Verdier & grenser Gjelder når: funksjonsverktøy oppgitt | Standard— |
| Felt`tools[].function.description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].function.parameters` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`response_format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning_effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser Kompatibilitetsfelt | Standard— |
| Felt`functions` | Type`function[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`function_call` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content`

**Tekst + bilde**

`{type:image_url,image_url:{url,detail}}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Chat

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="kimi-256k",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "kimi-256k",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='kimi-256k',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Chat

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert svaralternativ med innhold, verktøykall og resonnering. Sett sammen endringer i SSE etter svaralternativets/verktøyets indeks, og behold endelig avslutningsgrunn og bruksdata.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`choices[].index` | Typeinteger |
| Felt`choices[].message.content` | Typestring\|null |
| Felt`choices[].message.tool_calls` | Typetool\_call\[\] |
| Felt`choices[].message.reasoning_content` | Typestring |
| Felt`choices[].message.reasoning_details` | Typeobject\|array |
| Felt`choices[].finish_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `kimi-256k-latest`

[`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

Moonshot /`kimi-256k-latest`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · Anthropic Messages** `POST /v1/messages`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k-latest | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser user, assistant | Standard— |
| Felt`messages[].content` | Type`string\|content_block[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`system` | Type`string\|content_block[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`max_tokens` | Type`integer` | KravPåkrevd | Verdier & grenser Minimum: 1 Grensen gjelder for: den eksakte øvre grensen for valgt modell/kort | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop_sequences` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].name` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: verktøy oppgitt | Standard— |
| Felt`tools[].description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].input_schema` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`thinking.budget_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`output_config.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`metadata` | Type`object` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`cache_control` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content eller type=text-blokk`

**Tekst + bilde**

`{type:image,source:{type:base64,media_type,data}} eller en kilde med type=url`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages, max\_tokens |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · Anthropic Messages

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="kimi-256k-latest",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "kimi-256k-latest",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='kimi-256k-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · Anthropic Messages

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold alle innholdsblokker, resonneringssignaturer og faktiske ID-er for verktøybruk. Sett sammen alle SSE-blokkendringer; den første tekstblokken er ikke hele resultatet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`model` | Typestring |
| Felt`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Felt`stop_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=messages), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=messages), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `kimi-256k-latest`

[`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

Moonshot /`kimi-256k-latest`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Responses** `POST /v1/responses`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k-latest | Standard— |
| Felt`input` | Type`string\|input_item[]` | KravPåkrevd | Verdier & grenser | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].type` | Type`string` | KravValgfritt | Verdier & grenser message, reasoning, function\_call, function\_call\_output | Standard— |
| Felt`input[].content` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`input[].call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output; behold faktisk returnert call\_id | Standard— |
| Felt`input[].output` | Type`string\|content_part[]` | KravValgfritt | Verdier & grenser Gjelder når: function\_call\_output | Standard— |
| Felt`max_output_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning.summary` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`text.verbosity` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`include` | Type`string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`store` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`previous_response_id` | Type`string` | KravValgfritt | Verdier & grenser ID-krav: Bare en faktisk svar-ID fra en støttet videreføring Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_key` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`inputtekst eller input_text-del`

**Tekst + bilde**

`{type:input_image,image_url}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, input |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Responses

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="kimi-256k-latest", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "kimi-256k-latest", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="kimi-256k-latest", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Responses

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert outputelement og hver innholdsdel, faktisk call\_id for funksjonen, kryptert resonnering og bruksdata. Ved strømming beholder du fullstendig hendelses-/elementidentitet.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`id` | Typestring |
| Felt`status` | Typestring |
| Felt`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Felt`output[].content[]` | Typecontent part |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=responses), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=responses), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=responses)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `kimi-256k-latest`

[`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

Moonshot /`kimi-256k-latest`

Modell-ID

- `k3-256k`
- `kimi-256k`
- `kimi-256k-latest`

### Start

En Kimi K3-variant med en kontekst på 262 144 tokener for utvikling og analyse av tekst og bilder.

Godkjente inndata

Tekst · Bilder

Resultater

Tekst

### Tilgjengelig i Ailoot · inndata & metoder

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Inndatatyper

`text`, `image`

Utdatatyper

`text`

Kontekst

262 144 tokens

Maksimale utdata

65 536 tokens

Utdataformat

json eller SSE

| Felt | Type | Krav | Verdier & grenser | Standard |
| --- | --- | --- | --- | --- |
| Felt`model` | Type`string` | KravPåkrevd | Verdier & grenser kimi-256k-latest | Standard— |
| Felt`messages` | Type`message[]` | KravPåkrevd | Verdier & grenser Minste antall elementer: 1 | Standard— |
| Felt`messages[].role` | Type`string` | KravPåkrevd | Verdier & grenser Eksempler: system, user, assistant, tool, function Vilkår: Disse rollene representeres eksplisitt av kompatibilitetstyper i kildekoden; det eksakte rollesettet for modellen er fortsatt modellspesifikt. Avhenger av modellen | Standard— |
| Felt`messages[].content` | Type`string\|content_part[]\|null` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_calls` | Type`tool_call[]` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].tool_call_id` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: role=tool; bruk faktisk returnert ID | Standard— |
| Felt`messages[].name` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`messages[].reasoning_content` | Type`string` | KravValgfritt | Verdier & grenser Gjelder når: Send den faktisk returnerte resonneringen tilbake der denne modellen bruker den | Standard— |
| Felt`messages[].reasoning_details` | Type`object\|array` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`max_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`max_completion_tokens` | Type`integer` | KravValgfritt | Verdier & grenser Minimum: 1 Avhenger av modellen | Standard— |
| Felt`stream` | Type`boolean` | KravValgfritt | Verdier & grenser | Standardfalse |
| Felt`stream_options.include_usage` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`temperature` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`top_p` | Type`number` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`stop` | Type`string\|string[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools` | Type`function_tool[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].type` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`tools[].function.name` | Type`string` | KravPåkrevd | Verdier & grenser Gjelder når: funksjonsverktøy oppgitt | Standard— |
| Felt`tools[].function.description` | Type`string` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tools[].function.parameters` | Type`JSON_schema` | KravValgfritt | Verdier & grenser | Standard— |
| Felt`tool_choice` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`parallel_tool_calls` | Type`boolean` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`response_format` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning_effort` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`reasoning` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`service_tier` | Type`string` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`instructions` | Type`string` | KravValgfritt | Verdier & grenser Kompatibilitetsfelt | Standard— |
| Felt`functions` | Type`function[]` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`function_call` | Type`string\|object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |
| Felt`prompt_cache_options` | Type`object` | KravValgfritt | Verdier & grenser Avhenger av modellen | Standard— |

Kombinasjoner av inngående materialer

**Tekst** · UTF8-tekst

`messages[].content`

**Tekst + bilde**

`{type:image_url,image_url:{url,detail}}`

Metodeparametere og livssyklus

| Parameter | Avtale |
| --- | --- |
| Parameter`material_types` | Avtaletext, image |
| Parameter`required` | Avtalemodel, messages |
| Parameter`optional_controls` | Avtalenull |
| Parameter`content_type` | Avtaleapplication/json |
| Parameter`text_file_material` | Avtalefaktisk UTF-8-innhold satt inn som tekst; fil-ID-er eller URL-adresser (URLs) trenger separat, eksakt støtte |

Livssyklus: `exact retained published method`

Metodestrukturer og ID-er er eksakte; leverandørens evne er adskilt fra godkjenning av forespørselen.

### Priser

#### Satser for Ailoot-metoder

Inndata

0,003 USD */ 1K*

Utdata

0,015 USD */ 1K*

Lesing fra hurtigbuffer

0,0003 USD */ 1K*

Skriving til hurtigbuffer

0,003 USD */ 1K*

Skriving til hurtigbuffer, 5 min

0,003 USD */ 1K tokens*

Ailoot reserverer et estimert beløp før en forespørsel. Etter resultatet gjøres det endelige beløpet opp basert på målt forbruk. Oppgjør for strømming bruker den endelige forbruksposten. [Slik fungerer reservasjon og oppgjør →](https://ailoot.ai/docs/nb/billing/reserve/)

### Eksempelforespørsler

#### Ailoot · OpenAI Chat

TeksteksempelInndata, bildePython SDKNode.js SDKPython-strømming

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="kimi-256k-latest",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "kimi-256k-latest",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='kimi-256k-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Motta og lagre resultater

#### Ailoot · OpenAI Chat

json eller SSE

##### Behold alle ferdige resultater

Behold alle fullstendige returnerte svar, filer og innholdsdeler.

Behold hvert svaralternativ med innhold, verktøykall og resonnering. Sett sammen endringer i SSE etter svaralternativets/verktøyets indeks, og behold endelig avslutningsgrunn og bruksdata.

##### Hvis det opprinnelige svaret må kontrolleres

Behold forespørsels-/svar-ID-er og headere. Ingen generell URL for henting av tekstjobber oppgis.

Svarfelter

| Felt | Type |
| --- | --- |
| Felt`choices[].index` | Typeinteger |
| Felt`choices[].message.content` | Typestring\|null |
| Felt`choices[].message.tool_calls` | Typetool\_call\[\] |
| Felt`choices[].message.reasoning_content` | Typestring |
| Felt`choices[].message.reasoning_details` | Typeobject\|array |
| Felt`choices[].finish_reason` | Typestring\|null |
| Felt`usage` | Typeobject |

Feil og neste trinn

| Svar | Vilkår | Neste trinn |
| --- | --- | --- |
| Svar400 · `invalid_request_error` | VilkårUgyldige påkrevde felter, materialrepresentasjon eller parameterverdi | Neste trinnKorriger de angitte feltene før en ny opprettelsesforespørsel. |

### Aliaser

#### Modellaliaser

**Ailoot** [`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

#### Aliaser for metodestier

Bruk metodestiene som vises ovenfor.

#### Tilknyttede anroper-ID-er

[`k3-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=k3-256k&fmt=chat), [`kimi-256k`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k&fmt=chat), [`kimi-256k-latest`](https://ailoot.ai/models/nb/#m=k3-256k&route=Core&caller=kimi-256k-latest&fmt=chat)

FAQ · MoonshotAI: Kimi K3 (256K)

Hvilke inndata og resultater er tilgjengelige?

`POST /v1/messages` · `k3-256k`: `text`, `image` → `text` `POST /v1/responses` · `k3-256k`: `text`, `image` → `text` `POST /v1/chat/completions` · `k3-256k`: `text`, `image` → `text` `POST /v1/messages` · `kimi-256k`: `text`, `image` → `text` `POST /v1/responses` · `kimi-256k`: `text`, `image` → `text` `POST /v1/chat/completions` · `kimi-256k`: `text`, `image` → `text` `POST /v1/messages` · `kimi-256k-latest`: `text`, `image` → `text` `POST /v1/responses` · `kimi-256k-latest`: `text`, `image` → `text` `POST /v1/chat/completions` · `kimi-256k-latest`: `text`, `image` → `text`

Hvilke felt bruker forespørselen?

`POST /v1/messages` · `k3-256k`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `k3-256k`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `k3-256k`: `model`, `messages`, `stream` `POST /v1/messages` · `kimi-256k`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `kimi-256k`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `kimi-256k`: `model`, `messages`, `stream` `POST /v1/messages` · `kimi-256k-latest`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `kimi-256k-latest`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `kimi-256k-latest`: `model`, `messages`, `stream`

Hvilke grenser gjelder?

`POST /v1/messages` · `k3-256k`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `k3-256k`: `ctx`: `262144`; `max_out`: `65536` `POST /v1/chat/completions` · `k3-256k`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1` `POST /v1/messages` · `kimi-256k`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `kimi-256k`: `ctx`: `262144`; `max_out`: `65536` `POST /v1/chat/completions` · `kimi-256k`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1` `POST /v1/messages` · `kimi-256k-latest`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `kimi-256k-latest`: `ctx`: `262144`; `max_out`: `65536` `POST /v1/chat/completions` · `kimi-256k-latest`: `ctx`: `262144`; `max_out`: `65536`; `messages.min_items`: `1`

Koble Ailoot til Claude Code, OpenCode, Hermes eller egen applikasjon.

## Selskapet og dets prosjektportefølje

Selskapet og dets prosjektportefølje: millioner av kunder; månedlig salg for milliarder.

## Kjøp tokener med rabatt.

Abonnementsrabatt for jevnlig bruk. Kampanjekoder gir opptil 50% på tokenkjøp.

Abonnement

Velg et rabattabonnement for faste forespørsler.

Kampanjekode opptil 50%

Oppgi kode ved kjøp. Prisen beregnes på nytt etter gjeldende kampanje.

Kostnader i historikken

Modell, tokener og beløp lagres for hver forespørsel.

[Velg abonnement](https://ailoot.ai/docs/nb/billing/subscriptions/) · [Se modellpriser](https://ailoot.ai/models/nb/)

## Koble API-et til produktet du selger.

SaaS, apper og boter etter Ailoots offentlige tilbud og lisensavtale. Be om forhandlerlisens for videresalg.

Kommersiell applikasjon

Bygg tekst-, bilde-, video- og lydgenerering inn i betalte funksjoner i tjenesten.

Forhandlerlisens

Send prosjektbeskrivelse og tilgangsopplegg. Be om skriftlige vilkår for bruk og videresalg.

Dokumenter på nettstedet

Offentlig tilbud, lisensavtale og retningslinjer for databehandling er tilgjengelige før tilkobling.

[Be om forhandlerlisens](mailto:support@ailoot.ai) · [Offentlig tilbud og lisensavtale](https://ailoot.ai/legal/offer?lang=nb)

## Ailoot · Selskapet og dets prosjektportefølje





Ailoot bygger på etablert driftserfaring, en stor kundebase, stabil tjeneste og løpende KPI-kontroll.





Selskapet og dets prosjektportefølje: millioner av kunder; månedlig salg for milliarder.





Ailoot bruker denne driftserfaringen til API-tilgang til AI-funksjoner i kundenes produkter, agenter, applikasjoner og automatiseringer.