Source: https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/ Canonical: https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/ Language: en # Riva Translate 4B Instruct v1.1 [Markdown](https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/index.md) · [JSON](https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/facts.json) ## [Riva Translate 4B Instruct v1.1](https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/) NVIDIA's Riva-Translate-4B-Instruct-v1.1 translates sentences and documents between English and 11 other languages and regional variants, including Russian. Supports translation examples in the prompt and context of up to 8K tokens. - [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/riva-translate-4b-instruct-v1.1`](https://ailoot.ai/models/en/nvidia-riva-translate-4b-instruct-v1-1/#method-0) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. Riva-Translate-4B-Instruct-v1.1 is a specialized NVIDIA model for written translation. It works with individual sentences and documents: accepting text and returning text in the selected language. This format is suited to translators, marketers and developers preparing multilingual material. #### Languages and regional variants The model provides 12 languages and variants: English, German, European and Latin American Spanish, French, Brazilian Portuguese, Russian, Simplified and Traditional Chinese, Japanese, Korean and Arabic. The desired variant can be specified separately for Spanish and Chinese, while Portuguese is represented by its Brazilian variant in this version. Translation directions center on English: from English to the listed languages and back. Russian text can be translated into English, and English into Russian. Regional variety is part of direction selection and is therefore best specified together with the language. #### How translation is specified The request separates translation direction from the material itself. The system message specifies the language pair, and the user message contains the source text. For example, `en-ru` specifies English-to-Russian translation and `ru-en` Russian-to-English. `en-es-es` is provided for European Spanish, `en-es-us` for Latin American Spanish and `en-pt-br` for Brazilian Portuguese. Several translation examples can be supplied within a request. The conversation template supports alternating user text and translated responses. This allows a source-and-translation pair to be demonstrated before the next material. NVIDIA recommends the translation template on which the model was fine-tuned: it explicitly specifies the source and target languages. #### Context and architecture The model contains around four billion parameters and uses a decoder Transformer architecture. The base model was obtained through compression and distillation, then underwent additional text training, training from examples and preference-based optimization. Context is up to 8K tokens. #### What affects the translation Quality depends on subject matter, task conditions, noise in the source text and available context. Responses may contain grammatical errors and semantic inaccuracies. Refining the prompt can help obtain a more suitable translation. Practical task ### Translate a collection notice into Russian Technical example in English ``` Translate a collection notice into Russian Translation direction: English to Russian, en-ru. Translate this notice: 'Your repaired kettle is ready for collection at the service desk. Please bring receipt R-204. We will keep it until Friday at 18:00.' Preserve the receipt identifier and the collection deadline. Return only the translated notice. ``` #### Expected result ``` A Russian translation preserving the service-desk location, R-204 and Friday 18:00 deadline. ``` #### Check the result ``` The translation must not turn the collection deadline into the repair completion time. ``` **Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/riva-translate-4b-instruct-v1.1` [`nvidia/riva-translate-4b-instruct-v1.1`](https://ailoot.ai/models/en/#m=nvidia%2Friva-translate-4b-instruct-v1.1&route=Core&caller=nvidia%2Friva-translate-4b-instruct-v1.1&fmt=chat) NVIDIA /`nvidia/riva-translate-4b-instruct-v1.1` ### Overview NVIDIA's Riva-Translate-4B-Instruct-v1.1 translates sentences and documents between English and 11 other languages and regional variants, including Russian. Supports translation examples in the prompt and context of up to 8K tokens. Accepted inputs Text Results Text ### Available in Ailoot · inputs & methods **Ailoot · OpenAI Chat** `POST /v1/chat/completions` Input types `text` Output types `text` Context 4,096 tokens Maximum output 1,024 tokens Output format json or SSE | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits nvidia/riva-translate-4b-instruct-v1.1 | Default— | | Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— | | Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— | | Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— | | Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— | | Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— | | Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse | | Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— | | Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— | | Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— | | Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | Input material combinations **Text** · UTF8 text `messages[].content` Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`material_types` | Contracttext | | Parameter`required` | Contractmodel, messages | | Parameter`optional_controls` | Contractnull | | Parameter`content_type` | Contractapplication/json | | Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support | Lifecycle: `exact retained published method` Method shapes and IDs are exact; supplier capability is separate from admission. ### Pricing #### Ailoot method rates Input $0.0001 */ 1K* Output $0.0002 */ 1K* Cache read $0.0001 */ 1K* Cache write $0.0001 */ 1K* Cache write, 5 min $0.0001 */ 1K tokens* Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot · OpenAI Chat Text examplePython SDKNode.js SDKPython stream ```bash set -eu : "${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": "nvidia/riva-translate-4b-instruct-v1.1", "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 ``` ```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="nvidia/riva-translate-4b-instruct-v1.1", 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: "nvidia/riva-translate-4b-instruct-v1.1", 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='nvidia/riva-translate-4b-instruct-v1.1',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") ``` ### Receive and save results #### Ailoot · OpenAI Chat json or SSE ##### Keep all completed results Keep every complete returned response, file and content part. Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage. ##### If the original response needs checking Keep request/response IDs and headers. No generic text job retrieval URL is supplied. Response fields | Field | Type | | --- | --- | | Field`choices[].index` | Typeinteger | | Field`choices[].message.content` | Typestring\|null | | Field`choices[].message.tool_calls` | Typetool\_call\[\] | | Field`choices[].message.reasoning_content` | Typestring | | Field`choices[].message.reasoning_details` | Typeobject\|array | | Field`choices[].finish_reason` | Typestring\|null | | Field`usage` | Typeobject | Errors and next steps | Response | Condition | Next step | | --- | --- | --- | | Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. | ### Aliases #### Model aliases **Ailoot** [`nvidia/riva-translate-4b-instruct-v1.1`](https://ailoot.ai/models/en/#m=nvidia%2Friva-translate-4b-instruct-v1.1&route=Core&caller=nvidia%2Friva-translate-4b-instruct-v1.1&fmt=chat) #### Method path aliases Use the method paths shown above. #### Related caller IDs [`nvidia/riva-translate-4b-instruct-v1.1`](https://ailoot.ai/models/en/#m=nvidia%2Friva-translate-4b-instruct-v1.1&route=Core&caller=nvidia%2Friva-translate-4b-instruct-v1.1&fmt=chat) FAQ · nvidia/riva-translate-4b-instruct-v1.1 What inputs and results are available? `POST /v1/chat/completions` · `nvidia/riva-translate-4b-instruct-v1.1`: `text` → `text` Which fields does the request use? `POST /v1/chat/completions` · `nvidia/riva-translate-4b-instruct-v1.1`: `model`, `messages`, `stream` What limits apply? `POST /v1/chat/completions` · `nvidia/riva-translate-4b-instruct-v1.1`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` Connect Ailoot to Claude Code, OpenCode, Hermes or your own app. ## The company and its project portfolio The company and its project portfolio: millions of customers; monthly sales in the billions. ## Buy tokens at a discount. Subscription discounts for regular use. Promo codes offer up to 50% off token purchases. Subscription Choose a discounted plan for your regular requests. Promo code: up to 50% off Enter your code at checkout. The price updates to reflect the current promotion. Spending in your history The model, tokens and amount are recorded for each request. [Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/) ## Connect the API to a product you sell. Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale. Commercial application Add text, image, video and audio generation to paid features in your service. Reseller licence Send a description of your project and how you provide access. Request written terms for use and resale. Documents on the website The service offer, licence agreement and data processing policy are available before you connect. [Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en) ## Ailoot · The company and its project portfolio Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control. The company and its project portfolio: millions of customers; monthly sales in the billions. Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.