Trinity-Large-Thinking is the reasoning-optimised release of Arcee AI’s Trinity Large family. It is built for agents that plan across several steps, call tools and maintain a coherent task over a long conversation, while retaining general text-generation capabilities. The model accepts text and generates text, including explicit reasoning and tool requests. Its training extends the Trinity-Large-Base model with instruction tuning and reinforcement learning on reasoning chains, tool-calling trajectories and multi-step agent tasks.
The model card describes a sparse mixture-of-experts architecture with approximately 398 billion total parameters and 13 billion active parameters per token. It lists 256 experts, one shared expert, four active experts and a 512K context window after extension from an 8,192-token pretraining context. These are producer model properties rather than a prediction of response speed. The Thinking checkpoint is distinct from the lightly post-trained, chat-ready Trinity-Large-Preview, which does not provide reasoning_content, and from the Base and TrueBase pretraining checkpoints.
Explicit thinking appears in <think>...</think> blocks before the final response. In the documented structured response, reasoning_content holds that reasoning separately from content and tool_calls. Keeping the full assistant turn is a substantive part of using this model: pass the reasoning back together with the answer and any tool calls before the next step. Its chat template restores the thinking blocks when constructing the next input. If history must be shortened, Arcee recommends removing older turns as a whole rather than stripping thinking from recent turns.
The manufacturer’s agent-loop pattern starts with the user task and tool definitions, receives reasoning, an answer or tool requests, executes the requested tools outside the model, and appends the assistant turn plus actual tool results before continuing. This continues until a final answer is returned without tool calls. For assistant turns that contain tool calls but no answer text, the guide requires content to be an empty string rather than null. The reasoning field must also match the serving interface: Arcee’s guide distinguishes reasoning_content from integrations that expect reasoning.
This makes the model useful for a support workflow that first looks up a record, applies the supplied policy and then requests the appropriate next action, or a coding agent that inspects files, proposes a change and interprets an execution result. Give it the actual goal, tool names, argument schemas, constraints and a completion condition. An illustrative brief could ask it to locate a defect, explain the evidence and propose a minimal patch, while keeping observed tool results separate from actions still planned. Tool calls are requests to an execution layer, not proof that the model has already changed a file or completed an external action.
The card recommends temperature 0.45–0.6, top_p 0.95 and top_k 50 for inference. These are recommended settings, not fixed output limits. The important failure mode in the manufacturer guide is malformed multi-step tool use when a preceding turn loses reasoning or carries an invalid message shape: tool-call markup may appear inside the reasoning field instead of the structured tool-call output. Preserve the complete turn, retain non-null answer content and treat the final artifact separately from the stored reasoning history. This edition is especially suited to workflows where continuity between observations, reasoning and subsequent actions matters.
", "aboutText": "Trinity-Large-Thinking is the reasoning-optimised release of Arcee AI’s Trinity Large family. It is built for agents that plan across several steps, call tools and maintain a coherent task over a long conversation, while retaining general text-generation capabilities. The model accepts text and generates text, including explicit reasoning and tool requests. Its training extends the Trinity-Large-Base model with instruction tuning and reinforcement learning on reasoning chains, tool-calling trajectories and multi-step agent tasks.\n\nThe model card describes a sparse mixture-of-experts architecture with approximately 398 billion total parameters and 13 billion active parameters per token. It lists 256 experts, one shared expert, four active experts and a 512K context window after extension from an 8,192-token pretraining context. These are producer model properties rather than a prediction of response speed. The Thinking checkpoint is distinct from the lightly post-trained, chat-ready Trinity-Large-Preview, which does not provide reasoning_content, and from the Base and TrueBase pretraining checkpoints.\n\nExplicit thinking appears inTechnical example in English
Apply a support policy to a record\n\nUse this supplied lookup result: order C17 arrived 12 days ago, packaging intact, customer requests a return. Policy: unopened items may be returned within 14 days; opened items need review. Decide the next support step and draft a request for the one missing fact. Do not claim any external action occurred.A policy-based decision, the missing fact and a customer-facing clarification message.Check that unopened status remains unknown and that no return is described as already created.arcee-ai/trinity-large-thinkingTrinity-Large-Thinking is Arcee AI’s reasoning model for multi-step agents and tool calling. It generates explicit thinking before its answer and requires that reasoning to be preserved across conversation turns and tool-driven workflows.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Trinity-Large-Thinking is the reasoning-optimised release of Arcee AI’s Trinity Large family. It is built for agents that plan across several steps, call tools and maintain a coherent task over a long conversation, while retaining general text-generation capabilities. The model accepts text and generates text, including explicit reasoning and tool requests. Its training extends the Trinity-Large-Base model with instruction tuning and reinforcement learning on reasoning chains, tool-calling trajectories and multi-step agent tasks.
The model card describes a sparse mixture-of-experts architecture with approximately 398 billion total parameters and 13 billion active parameters per token. It lists 256 experts, one shared expert, four active experts and a 512K context window after extension from an 8,192-token pretraining context. These are producer model properties rather than a prediction of response speed. The Thinking checkpoint is distinct from the lightly post-trained, chat-ready Trinity-Large-Preview, which does not provide reasoning_content, and from the Base and TrueBase pretraining checkpoints.
Explicit thinking appears in <think>...</think> blocks before the final response. In the documented structured response, reasoning_content holds that reasoning separately from content and tool_calls. Keeping the full assistant turn is a substantive part of using this model: pass the reasoning back together with the answer and any tool calls before the next step. Its chat template restores the thinking blocks when constructing the next input. If history must be shortened, Arcee recommends removing older turns as a whole rather than stripping thinking from recent turns.
The manufacturer’s agent-loop pattern starts with the user task and tool definitions, receives reasoning, an answer or tool requests, executes the requested tools outside the model, and appends the assistant turn plus actual tool results before continuing. This continues until a final answer is returned without tool calls. For assistant turns that contain tool calls but no answer text, the guide requires content to be an empty string rather than null. The reasoning field must also match the serving interface: Arcee’s guide distinguishes reasoning_content from integrations that expect reasoning.
This makes the model useful for a support workflow that first looks up a record, applies the supplied policy and then requests the appropriate next action, or a coding agent that inspects files, proposes a change and interprets an execution result. Give it the actual goal, tool names, argument schemas, constraints and a completion condition. An illustrative brief could ask it to locate a defect, explain the evidence and propose a minimal patch, while keeping observed tool results separate from actions still planned. Tool calls are requests to an execution layer, not proof that the model has already changed a file or completed an external action.
The card recommends temperature 0.45–0.6, top_p 0.95 and top_k 50 for inference. These are recommended settings, not fixed output limits. The important failure mode in the manufacturer guide is malformed multi-step tool use when a preceding turn loses reasoning or carries an invalid message shape: tool-call markup may appear inside the reasoning field instead of the structured tool-call output. Preserve the complete turn, retain non-null answer content and treat the final artifact separately from the stored reasoning history. This edition is especially suited to workflows where continuity between observations, reasoning and subsequent actions matters.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits arcee-ai/trinity-large-thinking | 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 $0.0005 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00012 / 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 $0.0005 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00012 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "arcee-ai/trinity-large-thinking", "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='arcee-ai/trinity-large-thinking',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='arcee-ai/trinity-large-thinking',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 arcee-ai/trinity-large-thinking
Use the method paths shown above.
arcee-ai/trinity-large-thinkingTrinity-Large-Thinking is Arcee AI’s reasoning model for multi-step agents and tool calling. It generates explicit thinking before its answer and requires that reasoning to be preserved across conversation turns and tool-driven workflows.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Trinity-Large-Thinking is the reasoning-optimised release of Arcee AI’s Trinity Large family. It is built for agents that plan across several steps, call tools and maintain a coherent task over a long conversation, while retaining general text-generation capabilities. The model accepts text and generates text, including explicit reasoning and tool requests. Its training extends the Trinity-Large-Base model with instruction tuning and reinforcement learning on reasoning chains, tool-calling trajectories and multi-step agent tasks.
The model card describes a sparse mixture-of-experts architecture with approximately 398 billion total parameters and 13 billion active parameters per token. It lists 256 experts, one shared expert, four active experts and a 512K context window after extension from an 8,192-token pretraining context. These are producer model properties rather than a prediction of response speed. The Thinking checkpoint is distinct from the lightly post-trained, chat-ready Trinity-Large-Preview, which does not provide reasoning_content, and from the Base and TrueBase pretraining checkpoints.
Explicit thinking appears in <think>...</think> blocks before the final response. In the documented structured response, reasoning_content holds that reasoning separately from content and tool_calls. Keeping the full assistant turn is a substantive part of using this model: pass the reasoning back together with the answer and any tool calls before the next step. Its chat template restores the thinking blocks when constructing the next input. If history must be shortened, Arcee recommends removing older turns as a whole rather than stripping thinking from recent turns.
The manufacturer’s agent-loop pattern starts with the user task and tool definitions, receives reasoning, an answer or tool requests, executes the requested tools outside the model, and appends the assistant turn plus actual tool results before continuing. This continues until a final answer is returned without tool calls. For assistant turns that contain tool calls but no answer text, the guide requires content to be an empty string rather than null. The reasoning field must also match the serving interface: Arcee’s guide distinguishes reasoning_content from integrations that expect reasoning.
This makes the model useful for a support workflow that first looks up a record, applies the supplied policy and then requests the appropriate next action, or a coding agent that inspects files, proposes a change and interprets an execution result. Give it the actual goal, tool names, argument schemas, constraints and a completion condition. An illustrative brief could ask it to locate a defect, explain the evidence and propose a minimal patch, while keeping observed tool results separate from actions still planned. Tool calls are requests to an execution layer, not proof that the model has already changed a file or completed an external action.
The card recommends temperature 0.45–0.6, top_p 0.95 and top_k 50 for inference. These are recommended settings, not fixed output limits. The important failure mode in the manufacturer guide is malformed multi-step tool use when a preceding turn loses reasoning or carries an invalid message shape: tool-call markup may appear inside the reasoning field instead of the structured tool-call output. Preserve the complete turn, retain non-null answer content and treat the final artifact separately from the stored reasoning history. This edition is especially suited to workflows where continuity between observations, reasoning and subsequent actions matters.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits arcee-ai/trinity-large-thinking | 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 $0.0005 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00012 / 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 $0.0005 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00012 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "arcee-ai/trinity-large-thinking",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'arcee-ai/trinity-large-thinking', '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': 'arcee-ai/trinity-large-thinking', '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 arcee-ai/trinity-large-thinking
Use the method paths shown above.
Technical example in English
Apply a support policy to a record\n\nUse this supplied lookup result: order C17 arrived 12 days ago, packaging intact, customer requests a return. Policy: unopened items may be returned within 14 days; opened items need review. Decide the next support step and draft a request for the one missing fact. Do not claim any external action occurred.A policy-based decision, the missing fact and a customer-facing clarification message.Check that unopened status remains unknown and that no return is described as already created.