Build

Request parameters

Set output limits, sampling controls and tool calls for your API requests.

Find what you need

Tools and plugins — use built-in tools, call your own functions, or adjust prompts and JSON responses.
Common fields — choose a model, set answer length and adjust sampling.
Thinking and reasoning, structured output, and streaming — follow a focused guide.
Field names by endpoint — compare Chat Completions, Responses and Messages.

Set your key

Create an API key, save its recovery link, and add credits. Replace the placeholder below and run it in your terminal before running the examples on this page.

Set your key

export MINIROUTER_KEY='paste-your-api-key-here'

Examples use paid models. For free requests, follow the Auto Free guide.

Send a request with parameters

Run this in the same terminal. Change the prompt, temperature or output limit to suit your request.

Send a request with parameters

curl https://api.minirouter.sh/v1/chat/completions \
  -H "Authorization: Bearer $MINIROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/qwen3.5-flash",
  "reasoning": {
    "effort": "none"
  },
  "messages": [
    {
      "role": "system",
      "content": "Give short, practical answers."
    },
    {
      "role": "user",
      "content": "Give three names for a gardening app."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.7
}'

Read the answer in choices[0].message.content. A finish_reason of length means the output limit was reached; increase it for a longer answer.

Common Chat Completions fields

Field	How to use it
`model`	Required. Copy an exact model ID or listed alias from the catalog.
`messages`	Required, non-empty conversation array. Use `system` for instructions, `user` for prompts and `assistant` for earlier answers. Send the history needed for each request.
`max_tokens`	Positive integer limiting generated output. Keep it within the model limit.
`max_completion_tokens`	Alternative output-limit field used by some models. Send this or `max_tokens`, never both.
`temperature`	Controls sampling randomness. Lower values generally make answers more focused. Accepted ranges depend on the model.
`top_p`	Nucleus sampling. Tune this or temperature first, rather than changing both together.
`stop`	A string or list of stop sequences. Output ends when a supported model reaches one.
`frequency_penalty`, `presence_penalty`	Adjust repetition on models that support these controls.
`stream`	Set to `true` for server-sent events. See streaming.
`stream_options`	Chat Completions accepts `{"include_usage":true}` for streaming usage.
`usage`	`{"include":true}` is accepted as an alias for `stream_options.include_usage`. Non-streaming responses always include usage.
`reasoning`, `reasoning_effort`	Thinking controls. Choose one form; see reasoning.
`tools`, `tool_choice`	Add built-in server tools or your own functions. See tools and plugins.
`parallel_tool_calls`	Boolean controlling parallel calls on models that support them.
`max_tool_calls`	Caps built-in server tool executions, from 1 to 30 (default 5). Requires a server tool. See limits and cost.
`plugins`	`context-compression` fits an over-long prompt to the model; `response-healing` repairs malformed JSON output. See plugins.
`seed`	Integer sampling seed where supported. It does not guarantee identical answers.
`n`	Only `1` is supported.
`logprobs`, `top_logprobs`	Request token probabilities where supported. `top_logprobs` accepts an integer from 0 to 20.
`models`	Ordered text-model fallback list. See fallback models.

Optional parameters vary by model and provider. Check supported_parameters on the public catalog, plus reasoning_options for thinking controls. If a field is rejected, read the field path in the error and remove or adjust it. For schema-constrained JSON, use the structured-output guide.

Field names by endpoint

Setting	Chat Completions	Responses	Messages
Endpoint	`/v1/chat/completions`	`/v1/responses`	`/v1/messages`
Input	`messages`	`input`	`messages`
System instructions	A system message	`instructions`	`system`
Output limit	`max_tokens` or `max_completion_tokens`	`max_output_tokens`	`max_tokens` (required)
Thinking	`reasoning` or `reasoning_effort`	`reasoning`	`thinking` and `output_config.effort`
Schema output	`response_format` on models listing `structured_outputs`	Ignored	`output_config.format` on the models listed in the structured-output guide

Where schema output is not enforced it is dropped and the response carries x-minirouter-structured-output: ignored; provider.require_parameters: true returns 400 instead.

Use the request shape for your endpoint. Moving the same JSON body between endpoints without changing its fields will return an error.

Call a tool

Your app runs the function. Send a function definition in tools, read choices[0].message.tool_calls, run the function, and return its result to the model. Follow the function-calling example.

Let MiniRouter run a tool

MiniRouter runs the built-in tool. Add minirouter:datetime, minirouter:web_search or minirouter:web_fetch to tools. MiniRouter calls the tool, sends the result back to the model, and returns the answer in the same request. Start with the datetime example. Server tools use Chat Completions and a model that supports tool calling.

Fit a long prompt

The context-compression plugin removes older content when a prompt is too long for a named model. Read how compression works before using it with conversation history you need to preserve.

Repair JSON output

The response-healing plugin can repair malformed JSON in non-streaming responses. See JSON repair and its limits.

Handle an error

A 400 invalid_request names the field to change. Reduce oversized schemas, remove unsupported controls, and check that you used the right endpoint. A 402 insufficient_credits means the available balance cannot cover the request; reduce the output limit or add credits. See the error reference.