Command R (08-2024) is Cohere’s August 2024 edition of its scalable text model for conversation, long-context work and grounded answers. The exact model has 32 billion parameters, accepts text and produces text. It uses a 128K context, with a 4,000-token maximum output in the maker’s published service profile. Its identity remains separate from the earlier Command R, the larger R+ update and later Command A models.
The maker describes an autoregressive transformer with grouped-query attention, followed by supervised fine-tuning and preference training. The model is trained on 23 languages and evaluated on ten principal languages. Specify the answer language, keep required names intact and provide the source wording when a translation or cross-language comparison needs to retain a precise distinction.
The August update improves decisions about when to use tools, system-instruction following, structured data manipulation and robustness to changes such as whitespace. It also supports retrieval workflows without citations and is trained to decline questions that cannot be answered from the available information. Give the model explicit criteria for an answer and describe the treatment of missing data rather than asking it to fill every field regardless of evidence.
Command R is trained to generate answers from supplied document snippets and attach grounding spans to the source information. The producer recommends its dedicated prompt template because this behaviour was trained with that representation. Use short chunks, typically 100–400 words, with descriptive keys and text or semi-structured content. Preserve the identifiers needed to interpret the source references.
The exact card distinguishes accurate and fast citation modes. Accurate mode first identifies relevant documents and sources to cite, develops the answer and then adds grounding spans. Fast mode generates the answer with those spans directly, reducing generated tokens while trading some grounding accuracy. Choose the producer workflow according to the need for source fidelity and the task’s response budget.
For a practical comparison, supply named requirements and a proposal, then ask for each mismatch with the source passage that establishes it. For summarisation, define the audience and the facts that must remain. A useful result ties each claim to the actual snippets rather than treating a source marker as evidence that external retrieval occurred.
The card’s native tool workflow has two model stages: selection of functions and arguments, followed by answer generation after the application executes those calls and returns their results. The model can select a subset of tools and can invoke a supplied tool more than once. Its documented directly_answer option expresses a choice to answer without another external operation.
Give functions specific names, purposes and parameter definitions. A product-information tool can return the relevant record, after which the answer should explain the value needed by the user. The application performs the lookup and checks the arguments; the generated list of actions does not independently execute them. This edition also supports a separately trained multi-step workflow that iterates through actions, observations and reflection before the final answer; its dedicated template differs from the single-step format.
Keep the question, retrieved passages and observations within the applicable context, leaving room for the final answer. The useful deliverable is a concise textual result with its source connections, and an explicit account of any information that remains unavailable in the provided evidence.
", "aboutText": "Command R (08-2024) is Cohere’s August 2024 edition of its scalable text model for conversation, long-context work and grounded answers. The exact model has 32 billion parameters, accepts text and produces text. It uses a 128K context, with a 4,000-token maximum output in the maker’s published service profile. Its identity remains separate from the earlier Command R, the larger R+ update and later Command A models.\n\n### Model details and the August update\n\nThe maker describes an autoregressive transformer with grouped-query attention, followed by supervised fine-tuning and preference training. The model is trained on 23 languages and evaluated on ten principal languages. Specify the answer language, keep required names intact and provide the source wording when a translation or cross-language comparison needs to retain a precise distinction.\n\nThe August update improves decisions about when to use tools, system-instruction following, structured data manipulation and robustness to changes such as whitespace. It also supports retrieval workflows without citations and is trained to decline questions that cannot be answered from the available information. Give the model explicit criteria for an answer and describe the treatment of missing data rather than asking it to fill every field regardless of evidence.\n\n### Grounded generation\n\nCommand R is trained to generate answers from supplied document snippets and attach grounding spans to the source information. The producer recommends its dedicated prompt template because this behaviour was trained with that representation. Use short chunks, typically 100–400 words, with descriptive keys and text or semi-structured content. Preserve the identifiers needed to interpret the source references.\n\nThe exact card distinguishes accurate and fast citation modes. Accurate mode first identifies relevant documents and sources to cite, develops the answer and then adds grounding spans. Fast mode generates the answer with those spans directly, reducing generated tokens while trading some grounding accuracy. Choose the producer workflow according to the need for source fidelity and the task’s response budget.\n\nFor a practical comparison, supply named requirements and a proposal, then ask for each mismatch with the source passage that establishes it. For summarisation, define the audience and the facts that must remain. A useful result ties each claim to the actual snippets rather than treating a source marker as evidence that external retrieval occurred.\n\n### Single-step and multi-step tool use\n\nThe card’s native tool workflow has two model stages: selection of functions and arguments, followed by answer generation after the application executes those calls and returns their results. The model can select a subset of tools and can invoke a supplied tool more than once. Its documented directly_answer option expresses a choice to answer without another external operation.\n\nGive functions specific names, purposes and parameter definitions. A product-information tool can return the relevant record, after which the answer should explain the value needed by the user. The application performs the lookup and checks the arguments; the generated list of actions does not independently execute them. This edition also supports a separately trained multi-step workflow that iterates through actions, observations and reflection before the final answer; its dedicated template differs from the single-step format.\n\nKeep the question, retrieved passages and observations within the applicable context, leaving room for the final answer. The useful deliverable is a concise textual result with its source connections, and an explicit account of any information that remains unavailable in the provided evidence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Ground a cancellation answer\n\nAnswer the customer from these excerpts only. [POLICY] Monthly plans may be canceled before renewal; service continues to the paid-through date. [ORDER] Plan renews 1 November; paid-through date is 31 October. Question: If I cancel on 20 October, when does access end? Give a concise answer with source labels and identify anything these excerpts do not establish.A short answer with POLICY and ORDER references plus a clearly marked evidence gap, if any.Check each asserted date against ORDER and avoid inventing a refund entitlement.cohere/command-r-08-2024Command R (08-2024) is Cohere’s 32B text model for conversational and document-grounded answers. Its 128K context, source-span citations and single-step function calling support multilingual knowledge assistants, extraction and questions answered from supplied evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Command R (08-2024) is Cohere’s August 2024 edition of its scalable text model for conversation, long-context work and grounded answers. The exact model has 32 billion parameters, accepts text and produces text. It uses a 128K context, with a 4,000-token maximum output in the maker’s published service profile. Its identity remains separate from the earlier Command R, the larger R+ update and later Command A models.
The maker describes an autoregressive transformer with grouped-query attention, followed by supervised fine-tuning and preference training. The model is trained on 23 languages and evaluated on ten principal languages. Specify the answer language, keep required names intact and provide the source wording when a translation or cross-language comparison needs to retain a precise distinction.
The August update improves decisions about when to use tools, system-instruction following, structured data manipulation and robustness to changes such as whitespace. It also supports retrieval workflows without citations and is trained to decline questions that cannot be answered from the available information. Give the model explicit criteria for an answer and describe the treatment of missing data rather than asking it to fill every field regardless of evidence.
Command R is trained to generate answers from supplied document snippets and attach grounding spans to the source information. The producer recommends its dedicated prompt template because this behaviour was trained with that representation. Use short chunks, typically 100–400 words, with descriptive keys and text or semi-structured content. Preserve the identifiers needed to interpret the source references.
The exact card distinguishes accurate and fast citation modes. Accurate mode first identifies relevant documents and sources to cite, develops the answer and then adds grounding spans. Fast mode generates the answer with those spans directly, reducing generated tokens while trading some grounding accuracy. Choose the producer workflow according to the need for source fidelity and the task’s response budget.
For a practical comparison, supply named requirements and a proposal, then ask for each mismatch with the source passage that establishes it. For summarisation, define the audience and the facts that must remain. A useful result ties each claim to the actual snippets rather than treating a source marker as evidence that external retrieval occurred.
The card’s native tool workflow has two model stages: selection of functions and arguments, followed by answer generation after the application executes those calls and returns their results. The model can select a subset of tools and can invoke a supplied tool more than once. Its documented directly_answer option expresses a choice to answer without another external operation.
Give functions specific names, purposes and parameter definitions. A product-information tool can return the relevant record, after which the answer should explain the value needed by the user. The application performs the lookup and checks the arguments; the generated list of actions does not independently execute them. This edition also supports a separately trained multi-step workflow that iterates through actions, observations and reflection before the final answer; its dedicated template differs from the single-step format.
Keep the question, retrieved passages and observations within the applicable context, leaving room for the final answer. The useful deliverable is a concise textual result with its source connections, and an explicit account of any information that remains unavailable in the provided evidence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits cohere/command-r-08-2024 | 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 $0.0003 / 1K tokens Output · Output tokens $0.0012 / 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 $0.0003 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "cohere/command-r-08-2024", "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='cohere/command-r-08-2024',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='cohere/command-r-08-2024',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 cohere/command-r-08-2024
Use the method paths shown above.
cohere/command-r-08-2024Command R (08-2024) is Cohere’s 32B text model for conversational and document-grounded answers. Its 128K context, source-span citations and single-step function calling support multilingual knowledge assistants, extraction and questions answered from supplied evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Command R (08-2024) is Cohere’s August 2024 edition of its scalable text model for conversation, long-context work and grounded answers. The exact model has 32 billion parameters, accepts text and produces text. It uses a 128K context, with a 4,000-token maximum output in the maker’s published service profile. Its identity remains separate from the earlier Command R, the larger R+ update and later Command A models.
The maker describes an autoregressive transformer with grouped-query attention, followed by supervised fine-tuning and preference training. The model is trained on 23 languages and evaluated on ten principal languages. Specify the answer language, keep required names intact and provide the source wording when a translation or cross-language comparison needs to retain a precise distinction.
The August update improves decisions about when to use tools, system-instruction following, structured data manipulation and robustness to changes such as whitespace. It also supports retrieval workflows without citations and is trained to decline questions that cannot be answered from the available information. Give the model explicit criteria for an answer and describe the treatment of missing data rather than asking it to fill every field regardless of evidence.
Command R is trained to generate answers from supplied document snippets and attach grounding spans to the source information. The producer recommends its dedicated prompt template because this behaviour was trained with that representation. Use short chunks, typically 100–400 words, with descriptive keys and text or semi-structured content. Preserve the identifiers needed to interpret the source references.
The exact card distinguishes accurate and fast citation modes. Accurate mode first identifies relevant documents and sources to cite, develops the answer and then adds grounding spans. Fast mode generates the answer with those spans directly, reducing generated tokens while trading some grounding accuracy. Choose the producer workflow according to the need for source fidelity and the task’s response budget.
For a practical comparison, supply named requirements and a proposal, then ask for each mismatch with the source passage that establishes it. For summarisation, define the audience and the facts that must remain. A useful result ties each claim to the actual snippets rather than treating a source marker as evidence that external retrieval occurred.
The card’s native tool workflow has two model stages: selection of functions and arguments, followed by answer generation after the application executes those calls and returns their results. The model can select a subset of tools and can invoke a supplied tool more than once. Its documented directly_answer option expresses a choice to answer without another external operation.
Give functions specific names, purposes and parameter definitions. A product-information tool can return the relevant record, after which the answer should explain the value needed by the user. The application performs the lookup and checks the arguments; the generated list of actions does not independently execute them. This edition also supports a separately trained multi-step workflow that iterates through actions, observations and reflection before the final answer; its dedicated template differs from the single-step format.
Keep the question, retrieved passages and observations within the applicable context, leaving room for the final answer. The useful deliverable is a concise textual result with its source connections, and an explicit account of any information that remains unavailable in the provided evidence.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits cohere/command-r-08-2024 | 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 $0.0003 / 1K tokens Output · Output tokens $0.0012 / 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 $0.0003 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "cohere/command-r-08-2024",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'cohere/command-r-08-2024', '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': 'cohere/command-r-08-2024', '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 cohere/command-r-08-2024
Use the method paths shown above.
Technical example in English
Ground a cancellation answer\n\nAnswer the customer from these excerpts only. [POLICY] Monthly plans may be canceled before renewal; service continues to the paid-through date. [ORDER] Plan renews 1 November; paid-through date is 31 October. Question: If I cancel on 20 October, when does access end? Give a concise answer with source labels and identify anything these excerpts do not establish.A short answer with POLICY and ORDER references plus a clearly marked evidence gap, if any.Check each asserted date against ORDER and avoid inventing a refund entitlement.