Reka Flash 3 is Reka AI’s 21-billion-parameter general-purpose reasoning model. The released edition works with text for conversation, coding, instruction following and function-oriented tasks. The producer describes a 32K context window. It remains a distinct release from Flash 3.1 and from Reka’s multimodal Edge model.
Its training begins with pretraining from scratch on public and synthetic data. Instruction tuning follows, then reinforcement learning using both model-based and rule-based rewards. This training aims at broad reasoning improvements rather than turning the model into a specialist only for mathematics or code. The published model is a foundation for domain-specific adaptation as well as a conversational reasoning engine.
Flash 3 produces a reasoning stage before its answer. Reka’s format marks that stage with reasoning tags, and the producer describes budget forcing: closing the reasoning stage after a chosen amount of generation prompts the model to continue with its answer. This is a decoding technique for the published model, not a named low, medium or high effort mode. In multi-turn conversations, Reka recommends removing earlier reasoning traces to leave more room for the next task.
The producer’s prompt format separates human and assistant turns with a separator marker and uses an explicit end-of-text token as another stopping condition. A system instruction is prepended to the first user turn in the native format, and the published chat template handles that formatting for supported local tools. Prepare the conversation with clear turn boundaries so that the latest user request remains distinct from earlier model output.
For code review, give the relevant function, its intended behavior and an observed failure, then ask for a proposed correction and a way to check it. For a reasoning task, provide the premises and specify whether the useful result is a derivation, a concise explanation or a decision between alternatives. A follow-up can add a failing case and ask the model to revise the answer using that evidence. In a function-based application, keep any proposed arguments separate from the actual result returned by the application’s tool.
English is the main target language of this edition. Reka notes that the model can understand other languages to a degree, but may reason in English and lose quality in non-English output. For knowledge-intensive assignments, the producer recommends supplementing the model with web search; provide the retrieved material as evidence for the requested answer. The card also states that the released model has not received extensive persona or alignment training. These characteristics matter when choosing the language, supplying factual context and setting the assistant’s role.
", "aboutText": "Reka Flash 3 is Reka AI’s 21-billion-parameter general-purpose reasoning model. The released edition works with text for conversation, coding, instruction following and function-oriented tasks. The producer describes a 32K context window. It remains a distinct release from Flash 3.1 and from Reka’s multimodal Edge model.\n\nIts training begins with pretraining from scratch on public and synthetic data. Instruction tuning follows, then reinforcement learning using both model-based and rule-based rewards. This training aims at broad reasoning improvements rather than turning the model into a specialist only for mathematics or code. The published model is a foundation for domain-specific adaptation as well as a conversational reasoning engine.\n\nFlash 3 produces a reasoning stage before its answer. Reka’s format marks that stage with reasoning tags, and the producer describes budget forcing: closing the reasoning stage after a chosen amount of generation prompts the model to continue with its answer. This is a decoding technique for the published model, not a named low, medium or high effort mode. In multi-turn conversations, Reka recommends removing earlier reasoning traces to leave more room for the next task.\n\nThe producer’s prompt format separates human and assistant turns with a separator marker and uses an explicit end-of-text token as another stopping condition. A system instruction is prepended to the first user turn in the native format, and the published chat template handles that formatting for supported local tools. Prepare the conversation with clear turn boundaries so that the latest user request remains distinct from earlier model output.\n\nFor code review, give the relevant function, its intended behavior and an observed failure, then ask for a proposed correction and a way to check it. For a reasoning task, provide the premises and specify whether the useful result is a derivation, a concise explanation or a decision between alternatives. A follow-up can add a failing case and ask the model to revise the answer using that evidence. In a function-based application, keep any proposed arguments separate from the actual result returned by the application’s tool.\n\nEnglish is the main target language of this edition. Reka notes that the model can understand other languages to a degree, but may reason in English and lose quality in non-English output. For knowledge-intensive assignments, the producer recommends supplementing the model with web search; provide the retrieved material as evidence for the requested answer. The card also states that the released model has not received extensive persona or alignment training. These characteristics matter when choosing the language, supplying factual context and setting the assistant’s role.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Fix an incorrect empty-string check\n\nReview this JavaScript function: function fallback(value) { return value || 'untitled'; }. Required behaviour: use 'untitled' only for null or undefined; preserve 0, false and the empty string. Propose the smallest correction and give one test for each of those five input cases. Explain the distinction briefly without adding a library.A corrected fallback expression and five tests covering null, undefined, zero, false and empty string.Valid falsy values survive while only the two absent-value cases receive the fallback.rekaai/reka-flash-3Reka Flash 3 is a 21B text reasoning model for conversation, code and instruction-driven tasks, with a 32K context. It is primarily an English model and separates its reasoning stage from the answer, with producer-documented budget forcing.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Reka Flash 3 is Reka AI’s 21-billion-parameter general-purpose reasoning model. The released edition works with text for conversation, coding, instruction following and function-oriented tasks. The producer describes a 32K context window. It remains a distinct release from Flash 3.1 and from Reka’s multimodal Edge model.
Its training begins with pretraining from scratch on public and synthetic data. Instruction tuning follows, then reinforcement learning using both model-based and rule-based rewards. This training aims at broad reasoning improvements rather than turning the model into a specialist only for mathematics or code. The published model is a foundation for domain-specific adaptation as well as a conversational reasoning engine.
Flash 3 produces a reasoning stage before its answer. Reka’s format marks that stage with reasoning tags, and the producer describes budget forcing: closing the reasoning stage after a chosen amount of generation prompts the model to continue with its answer. This is a decoding technique for the published model, not a named low, medium or high effort mode. In multi-turn conversations, Reka recommends removing earlier reasoning traces to leave more room for the next task.
The producer’s prompt format separates human and assistant turns with a separator marker and uses an explicit end-of-text token as another stopping condition. A system instruction is prepended to the first user turn in the native format, and the published chat template handles that formatting for supported local tools. Prepare the conversation with clear turn boundaries so that the latest user request remains distinct from earlier model output.
For code review, give the relevant function, its intended behavior and an observed failure, then ask for a proposed correction and a way to check it. For a reasoning task, provide the premises and specify whether the useful result is a derivation, a concise explanation or a decision between alternatives. A follow-up can add a failing case and ask the model to revise the answer using that evidence. In a function-based application, keep any proposed arguments separate from the actual result returned by the application’s tool.
English is the main target language of this edition. Reka notes that the model can understand other languages to a degree, but may reason in English and lose quality in non-English output. For knowledge-intensive assignments, the producer recommends supplementing the model with web search; provide the retrieved material as evidence for the requested answer. The card also states that the released model has not received extensive persona or alignment training. These characteristics matter when choosing the language, supplying factual context and setting the assistant’s role.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits rekaai/reka-flash-3 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | 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— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "rekaai/reka-flash-3", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='rekaai/reka-flash-3',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n 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\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n 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\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='rekaai/reka-flash-3',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
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.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| 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. |
Ailoot Ultra rekaai/reka-flash-3
Use the method paths shown above.
rekaai/reka-flash-3Reka Flash 3 is a 21B text reasoning model for conversation, code and instruction-driven tasks, with a 32K context. It is primarily an English model and separates its reasoning stage from the answer, with producer-documented budget forcing.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Reka Flash 3 is Reka AI’s 21-billion-parameter general-purpose reasoning model. The released edition works with text for conversation, coding, instruction following and function-oriented tasks. The producer describes a 32K context window. It remains a distinct release from Flash 3.1 and from Reka’s multimodal Edge model.
Its training begins with pretraining from scratch on public and synthetic data. Instruction tuning follows, then reinforcement learning using both model-based and rule-based rewards. This training aims at broad reasoning improvements rather than turning the model into a specialist only for mathematics or code. The published model is a foundation for domain-specific adaptation as well as a conversational reasoning engine.
Flash 3 produces a reasoning stage before its answer. Reka’s format marks that stage with reasoning tags, and the producer describes budget forcing: closing the reasoning stage after a chosen amount of generation prompts the model to continue with its answer. This is a decoding technique for the published model, not a named low, medium or high effort mode. In multi-turn conversations, Reka recommends removing earlier reasoning traces to leave more room for the next task.
The producer’s prompt format separates human and assistant turns with a separator marker and uses an explicit end-of-text token as another stopping condition. A system instruction is prepended to the first user turn in the native format, and the published chat template handles that formatting for supported local tools. Prepare the conversation with clear turn boundaries so that the latest user request remains distinct from earlier model output.
For code review, give the relevant function, its intended behavior and an observed failure, then ask for a proposed correction and a way to check it. For a reasoning task, provide the premises and specify whether the useful result is a derivation, a concise explanation or a decision between alternatives. A follow-up can add a failing case and ask the model to revise the answer using that evidence. In a function-based application, keep any proposed arguments separate from the actual result returned by the application’s tool.
English is the main target language of this edition. Reka notes that the model can understand other languages to a degree, but may reason in English and lose quality in non-English output. For knowledge-intensive assignments, the producer recommends supplementing the model with web search; provide the retrieved material as evidence for the requested answer. The card also states that the released model has not received extensive persona or alignment training. These characteristics matter when choosing the language, supplying factual context and setting the assistant’s role.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits rekaai/reka-flash-3 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "rekaai/reka-flash-3",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'rekaai/reka-flash-3', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'rekaai/reka-flash-3', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| 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. |
Ailoot Ultra rekaai/reka-flash-3
Use the method paths shown above.
Technical example in English
Fix an incorrect empty-string check\n\nReview this JavaScript function: function fallback(value) { return value || 'untitled'; }. Required behaviour: use 'untitled' only for null or undefined; preserve 0, false and the empty string. Propose the smallest correction and give one test for each of those five input cases. Explain the distinction briefly without adding a library.A corrected fallback expression and five tests covering null, undefined, zero, false and empty string.Valid falsy values survive while only the two absent-value cases receive the fallback.