Command A is Cohere’s March 2025 text model for enterprise agents, retrieval-augmented answers and multilingual work. The exact edition has 111 billion parameters, accepts text and produces text. Its producer model context is 256K tokens, with an 8,000-token maximum output in the published service profile. It is separate from Command A Vision, Command A Reasoning and the later multimodal A+ edition.
The manufacturer describes an autoregressive transformer with local sliding-window attention and periodic global attention. Three local layers use a 4,096-token window with rotary position encoding; a fourth layer uses global attention without positional embeddings. Supervised fine-tuning and preference training shape helpful conversational and task-focused behaviour. The model is trained on 23 languages and supports cross-language tasks such as translation or answering a question about material written in another language.
Specify the answer language and preserve required terminology. For a multilingual knowledge assistant, give the source passages their own names and ask for an explanation that retains product names, code identifiers and quoted wording. A useful final answer identifies the source behind a conclusion rather than translating away a distinction that matters to the task.
Command A is conversational by default, often adding an introduction, follow-up questions and Markdown or mathematical formatting. For extraction, categorisation, summarisation or translation, use the producer’s system-instruction approach to ask for only the required answer and specify whether Markdown or code fences belong in the output. This avoids treating a friendly conversational preamble as part of a downstream data record.
The model card describes contextual and strict safety modes, with contextual mode as the producer default. These are documented behaviour settings of the maker profile, independent of the task’s requested format. Define the relevant task context and desired output clearly.
Command A is trained for the answer-generation step of retrieval-augmented generation. The input combines the conversation with supplied document snippets, typically around 100–400 words per chunk, represented with short descriptive keys and textual or semi-structured values. The maker also encourages comparing this specialised format with relevant documents placed directly in the user message.
For a policy or technical comparison, label each snippet and request a conclusion supported by the relevant passage. In its citation-enabled producer format, the output associates spans of the answer with supporting sources. Keep the retrieved document identifiers available so those references remain interpretable. A citation indicates which supplied material supports the generated span; the surrounding system provides the actual retrieval.
The maker trains Command A for conversational tool use with JSON-schema function descriptions. The model can generate a plan and selected calls, the application performs those calls, and their dictionary results return in the conversation with the matching tool-call identifier. The model then uses those observations to produce an answer, optionally with source spans tied to tool results.
Coding tasks include SQL generation, code explanation and translation or rewriting of code. Supply the schema or relevant implementation and the behaviour to preserve. The producer recommends low temperature, including greedy decoding where appropriate, for code-generation instructions. Review generated SQL or code before executing it and return real validation observations when revising the result.
The model card notes a practical context distinction: the model supports 256K, while the published Hugging Face configuration is set to 128K and can be adjusted. Retain the selected workflow’s actual context configuration and reserve room for the answer. A useful result is the requested text or code artifact with evidence that can be traced to the supplied sources and tool observations.
", "aboutText": "Command A is Cohere’s March 2025 text model for enterprise agents, retrieval-augmented answers and multilingual work. The exact edition has 111 billion parameters, accepts text and produces text. Its producer model context is 256K tokens, with an 8,000-token maximum output in the published service profile. It is separate from Command A Vision, Command A Reasoning and the later multimodal A+ edition.\n\n### Model details and language\n\nThe manufacturer describes an autoregressive transformer with local sliding-window attention and periodic global attention. Three local layers use a 4,096-token window with rotary position encoding; a fourth layer uses global attention without positional embeddings. Supervised fine-tuning and preference training shape helpful conversational and task-focused behaviour. The model is trained on 23 languages and supports cross-language tasks such as translation or answering a question about material written in another language.\n\nSpecify the answer language and preserve required terminology. For a multilingual knowledge assistant, give the source passages their own names and ask for an explanation that retains product names, code identifiers and quoted wording. A useful final answer identifies the source behind a conclusion rather than translating away a distinction that matters to the task.\n\n### Conversation and task-focused output\n\nCommand A is conversational by default, often adding an introduction, follow-up questions and Markdown or mathematical formatting. For extraction, categorisation, summarisation or translation, use the producer’s system-instruction approach to ask for only the required answer and specify whether Markdown or code fences belong in the output. This avoids treating a friendly conversational preamble as part of a downstream data record.\n\nThe model card describes contextual and strict safety modes, with contextual mode as the producer default. These are documented behaviour settings of the maker profile, independent of the task’s requested format. Define the relevant task context and desired output clearly.\n\n### Grounded generation\n\nCommand A is trained for the answer-generation step of retrieval-augmented generation. The input combines the conversation with supplied document snippets, typically around 100–400 words per chunk, represented with short descriptive keys and textual or semi-structured values. The maker also encourages comparing this specialised format with relevant documents placed directly in the user message.\n\nFor a policy or technical comparison, label each snippet and request a conclusion supported by the relevant passage. In its citation-enabled producer format, the output associates spans of the answer with supporting sources. Keep the retrieved document identifiers available so those references remain interpretable. A citation indicates which supplied material supports the generated span; the surrounding system provides the actual retrieval.\n\n### Tools and code\n\nThe maker trains Command A for conversational tool use with JSON-schema function descriptions. The model can generate a plan and selected calls, the application performs those calls, and their dictionary results return in the conversation with the matching tool-call identifier. The model then uses those observations to produce an answer, optionally with source spans tied to tool results.\n\nCoding tasks include SQL generation, code explanation and translation or rewriting of code. Supply the schema or relevant implementation and the behaviour to preserve. The producer recommends low temperature, including greedy decoding where appropriate, for code-generation instructions. Review generated SQL or code before executing it and return real validation observations when revising the result.\n\nThe model card notes a practical context distinction: the model supports 256K, while the published Hugging Face configuration is set to 128K and can be adjusted. Retain the selected workflow’s actual context configuration and reserve room for the answer. A useful result is the requested text or code artifact with evidence that can be traced to the supplied sources and tool observations.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
A multilingual answer grounded in snippets\n\nAnswer in English using only these snippets. FR-1: 'Les retours sont acceptés sous 30 jours pour les articles non utilisés.' EN-2: 'Return shipping is paid by the customer unless the item is defective.' A customer asks whether an unused item can be returned after 20 days and who pays postage. Cite snippet IDs.A short English answer with FR-1 and EN-2 attached to the conclusions they support.The answer preserves the unused-item condition and defective-item exception without inventing a refund timeline.cohere/command-aCommand A is Cohere’s 111B text model for multilingual enterprise agents, document-grounded answers and tool-guided work. It combines a 256K context with source citations, code assistance and 23-language training, producing text from written instructions and supplied evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Command A is Cohere’s March 2025 text model for enterprise agents, retrieval-augmented answers and multilingual work. The exact edition has 111 billion parameters, accepts text and produces text. Its producer model context is 256K tokens, with an 8,000-token maximum output in the published service profile. It is separate from Command A Vision, Command A Reasoning and the later multimodal A+ edition.
The manufacturer describes an autoregressive transformer with local sliding-window attention and periodic global attention. Three local layers use a 4,096-token window with rotary position encoding; a fourth layer uses global attention without positional embeddings. Supervised fine-tuning and preference training shape helpful conversational and task-focused behaviour. The model is trained on 23 languages and supports cross-language tasks such as translation or answering a question about material written in another language.
Specify the answer language and preserve required terminology. For a multilingual knowledge assistant, give the source passages their own names and ask for an explanation that retains product names, code identifiers and quoted wording. A useful final answer identifies the source behind a conclusion rather than translating away a distinction that matters to the task.
Command A is conversational by default, often adding an introduction, follow-up questions and Markdown or mathematical formatting. For extraction, categorisation, summarisation or translation, use the producer’s system-instruction approach to ask for only the required answer and specify whether Markdown or code fences belong in the output. This avoids treating a friendly conversational preamble as part of a downstream data record.
The model card describes contextual and strict safety modes, with contextual mode as the producer default. These are documented behaviour settings of the maker profile, independent of the task’s requested format. Define the relevant task context and desired output clearly.
Command A is trained for the answer-generation step of retrieval-augmented generation. The input combines the conversation with supplied document snippets, typically around 100–400 words per chunk, represented with short descriptive keys and textual or semi-structured values. The maker also encourages comparing this specialised format with relevant documents placed directly in the user message.
For a policy or technical comparison, label each snippet and request a conclusion supported by the relevant passage. In its citation-enabled producer format, the output associates spans of the answer with supporting sources. Keep the retrieved document identifiers available so those references remain interpretable. A citation indicates which supplied material supports the generated span; the surrounding system provides the actual retrieval.
The maker trains Command A for conversational tool use with JSON-schema function descriptions. The model can generate a plan and selected calls, the application performs those calls, and their dictionary results return in the conversation with the matching tool-call identifier. The model then uses those observations to produce an answer, optionally with source spans tied to tool results.
Coding tasks include SQL generation, code explanation and translation or rewriting of code. Supply the schema or relevant implementation and the behaviour to preserve. The producer recommends low temperature, including greedy decoding where appropriate, for code-generation instructions. Review generated SQL or code before executing it and return real validation observations when revising the result.
The model card notes a practical context distinction: the model supports 256K, while the published Hugging Face configuration is set to 128K and can be adjusted. Retain the selected workflow’s actual context configuration and reserve room for the answer. A useful result is the requested text or code artifact with evidence that can be traced to the supplied sources and tool observations.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits cohere/command-a | 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 $0.005 / 1K tokens Output · Output tokens $0.02 / 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 $0.005 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "cohere/command-a", "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-a',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-a',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-a
Use the method paths shown above.
cohere/command-aCommand A is Cohere’s 111B text model for multilingual enterprise agents, document-grounded answers and tool-guided work. It combines a 256K context with source citations, code assistance and 23-language training, producing text from written instructions and supplied evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Command A is Cohere’s March 2025 text model for enterprise agents, retrieval-augmented answers and multilingual work. The exact edition has 111 billion parameters, accepts text and produces text. Its producer model context is 256K tokens, with an 8,000-token maximum output in the published service profile. It is separate from Command A Vision, Command A Reasoning and the later multimodal A+ edition.
The manufacturer describes an autoregressive transformer with local sliding-window attention and periodic global attention. Three local layers use a 4,096-token window with rotary position encoding; a fourth layer uses global attention without positional embeddings. Supervised fine-tuning and preference training shape helpful conversational and task-focused behaviour. The model is trained on 23 languages and supports cross-language tasks such as translation or answering a question about material written in another language.
Specify the answer language and preserve required terminology. For a multilingual knowledge assistant, give the source passages their own names and ask for an explanation that retains product names, code identifiers and quoted wording. A useful final answer identifies the source behind a conclusion rather than translating away a distinction that matters to the task.
Command A is conversational by default, often adding an introduction, follow-up questions and Markdown or mathematical formatting. For extraction, categorisation, summarisation or translation, use the producer’s system-instruction approach to ask for only the required answer and specify whether Markdown or code fences belong in the output. This avoids treating a friendly conversational preamble as part of a downstream data record.
The model card describes contextual and strict safety modes, with contextual mode as the producer default. These are documented behaviour settings of the maker profile, independent of the task’s requested format. Define the relevant task context and desired output clearly.
Command A is trained for the answer-generation step of retrieval-augmented generation. The input combines the conversation with supplied document snippets, typically around 100–400 words per chunk, represented with short descriptive keys and textual or semi-structured values. The maker also encourages comparing this specialised format with relevant documents placed directly in the user message.
For a policy or technical comparison, label each snippet and request a conclusion supported by the relevant passage. In its citation-enabled producer format, the output associates spans of the answer with supporting sources. Keep the retrieved document identifiers available so those references remain interpretable. A citation indicates which supplied material supports the generated span; the surrounding system provides the actual retrieval.
The maker trains Command A for conversational tool use with JSON-schema function descriptions. The model can generate a plan and selected calls, the application performs those calls, and their dictionary results return in the conversation with the matching tool-call identifier. The model then uses those observations to produce an answer, optionally with source spans tied to tool results.
Coding tasks include SQL generation, code explanation and translation or rewriting of code. Supply the schema or relevant implementation and the behaviour to preserve. The producer recommends low temperature, including greedy decoding where appropriate, for code-generation instructions. Review generated SQL or code before executing it and return real validation observations when revising the result.
The model card notes a practical context distinction: the model supports 256K, while the published Hugging Face configuration is set to 128K and can be adjusted. Retain the selected workflow’s actual context configuration and reserve room for the answer. A useful result is the requested text or code artifact with evidence that can be traced to the supplied sources and tool observations.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits cohere/command-a | 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 $0.005 / 1K tokens Output · Output tokens $0.02 / 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 $0.005 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "cohere/command-a",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-a', '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-a', '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-a
Use the method paths shown above.
Technical example in English
A multilingual answer grounded in snippets\n\nAnswer in English using only these snippets. FR-1: 'Les retours sont acceptés sous 30 jours pour les articles non utilisés.' EN-2: 'Return shipping is paid by the customer unless the item is defective.' A customer asks whether an unused item can be returned after 20 days and who pays postage. Cite snippet IDs.A short English answer with FR-1 and EN-2 attached to the conclusions they support.The answer preserves the unused-item condition and defective-item exception without inventing a refund timeline.