API reference

Responses

An OpenAI-compatible, stateless Responses surface for text, images, tools and reasoning. Send the complete conversation history on every multi-turn request.

POST https://router.omnitools.ai/v1/responses

Authentication

Authenticate every request with a Team API key.

Authorization: Bearer $OTRouter_API_KEY

Content-Type must be application/json. Query parameters are not accepted.

Create a response

This minimal request returns one completed Response object.

curl https://router.omnitools.ai/v1/responses \
  -H "Authorization: Bearer $OTRouter_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-fable-5",
  "input": "Summarize why deterministic errors matter in one sentence.",
  "max_output_tokens": 160,
  "store": false
}'

Request parameters

Only the parameters below are accepted. Limits are validated before an upstream call begins.

Parameter	Requirement	Description
model	Required	Stable OTRouter model ID from the model catalog.
input	Required	A text string or an array of supported input items.
instructions	Optional	A leading developer instruction. Do not also place another system or developer instruction in input.
max_output_tokens	Optional	Positive integer. Router also enforces the selected model's output limit.
temperature	Optional	Number from 0 through 2.
top_p	Optional	Number from 0 through 1.
stream	Optional · default false	Returns typed server-sent events when true.
store	Required · false only	Must be explicitly set to false. OTRouter never stores Responses request or response bodies.
tools	Optional	Up to 128 functions after namespace expansion. Supports function, namespace and custom tools; web_search is accepted only with external_web_access: false.
tool_choice	Optional	auto, none, required, or a named function/custom tool. Namespace functions include namespace.
parallel_tool_calls	Optional · default true	Allows the model to request multiple functions in one turn.
reasoning	Optional	effort accepts none through max; summary accepts auto, concise or detailed; context accepts all_turns or current_turn.
include	Optional	Compatibility form: exactly ['reasoning.encrypted_content'].
prompt_cache_key	Optional	A validated non-empty compatibility key.
client_metadata	Optional	Up to 32 bounded string entries used as compatibility metadata.
service_tier	Optional	Validated compatibility value: auto, default, flex or priority.
stream_options	Optional	Accepts the compatibility boolean include_obfuscation.
text	Optional	Accepts verbosity: low, medium or high. text.format remains unsupported.

Input items and conversation history

Replay all prior message, function-call and function-output items on every multi-turn request. OTRouter does not store or reconstruct conversation history.

Message items

Roles are system, developer, user and assistant. Text parts use text, input_text or output_text; user input accepts input_image by URL or data URL. Images require a route with verified image support.

Function and custom items

function_call may include namespace. custom_tool_call carries string input; each output item reuses its call_id and may return input_text or input_image parts. id and status are accepted replay metadata.

Codex tools

A developer additional_tools item may declare custom and namespace tools. OTRouter preserves their public identities while translating them to upstream functions. Hosted web search is never executed.

Reasoning and integrity

Reasoning accepts summary_text entries and optional encrypted_content replay metadata. Call IDs stay unique and every pending call requires a matching output before conversation continues.

Automatic routing

The stable model ID is the only routing input. Internal route selection is automatic.

Routing is automatic and private. Router filters by the requested protocol and capabilities, then applies configured priority and internal cost. Fallback keeps the public model ID. Fixed-price models use their published model rates; supply-priced models use the applicable quote for the route actually used, so fallback may change the rate charged.

Streaming events

With stream: true, Content-Type is text/event-stream. Each event has a type and monotonically increasing sequence_number.

response.created and response.in_progress open the Response.
response.output_item.added and response.content_part.added open text or function output.
response.output_text.delta and response.function_call_arguments.delta carry incremental content.
response.output_text.done, response.function_call_arguments.done, response.content_part.done and response.output_item.done close output.
response.completed or response.incomplete is the terminal success state; response.failed is the terminal stream error.

Response object

The public model ID is preserved. The returned resp_* value identifies this request only; it cannot be retrieved, deleted or used for server-side continuation.

Minimal response

{
  "id": "resp_…",
  "object": "response",
  "created_at": 1783900800,
  "completed_at": 1783900801,
  "status": "completed",
  "error": null,
  "incomplete_details": null,
  "model": "claude-fable-5",
  "output": [
    {
      "id": "msg_…",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "…",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 24,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 36
  }
}

Unsupported parameters

The following recognized Responses fields are explicitly rejected. store is required and must be false.

backgroundconversationprevious_response_idmax_tool_callsmetadatapromptprompt_cache_retentionsafety_identifiertop_logprobstruncationuser

Any unlisted top-level field returns unknown_parameter. Text parts reject annotations and logprobs. Files, audio, computer use and hosted tool execution are unsupported; images are limited to user input and tool output and are capability-gated.

Errors

Responses and Chat Completions return message, type, param and code with x-request-id. Messages maps the HTTP status to the Anthropic error shape, omits code and also includes request-id.

HTTP	Router code	Description
400	invalid_parameter	The JSON shape, parameter value, protocol header or requested feature is invalid.
401	invalid_api_key	The API key is missing, malformed, expired, deleted or unknown.
402	insufficient_credits	The Team has no available Credits for a new request.
404	model_not_found	The requested model is unavailable.
413	payload_too_large	The JSON request body exceeds 8 MiB.
429	api_key_spend_limit_exceeded	The API key reached one of its rolling spend limits.
502	upstream_error / invalid_upstream_response	Model execution was rejected or returned an invalid response.
503	upstream_unavailable / route_unavailable	No eligible route completed the request before the routing deadline.

Keep x-request-id (or request-id for Messages) when contacting support or inspecting the request in Console.