Reasoning

Models that advertise reasoning can expose the model’s thinking trace as reasoning_content on the assistant message. LLMBase also includes a compatibility alias named reasoning when returned by the selected model.

Use reasoning_effort for portable effort control when the selected model lists that parameter in supported_parameters.

Effort control

{
  "model": "<model-id-from-/v1/models>",
  "messages": [
    { "role": "user", "content": "Compare these two migration plans." }
  ],
  "reasoning_effort": "high"
}

Effort values are model-dependent, so check metadata before requiring a value in production. When present, supported_reasoning_efforts lists the model-native values; use one of those values instead of carrying assumptions from another model family.

For compatibility with OpenAI-compatible agents, medium is also accepted when the selected model publishes high but does not provide a native medium tier. LLMBase uses high for that request. Models with native medium support keep the native value unchanged.

Thinking flags

Some model families also expose thinking through chat template flags. The portable flags below are supported through extra_body.chat_template_kwargs when advertised by the selected model:

{
  "model": "<model-id-from-/v1/models>",
  "messages": [
    { "role": "user", "content": "Solve 17 * 23 and show the final answer." }
  ],
  "extra_body": {
    "chat_template_kwargs": {
      "enable_thinking": true,
      "thinking": true,
      "preserve_thinking": true
    }
  }
}

Response shape

Typical non-streaming responses include the final answer in content and the reasoning trace separately:

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "17 * 23 = 391.",
        "reasoning_content": "Compute 17 * 20 = 340 and 17 * 3 = 51, then add them.",
        "reasoning": "Compute 17 * 20 = 340 and 17 * 3 = 51, then add them."
      }
    }
  ]
}

Reasoning support is model-dependent. If your request depends on reasoning, choose a model whose metadata includes supported_features: ["reasoning"] and supported_parameters containing reasoning_effort. If the model includes supported_reasoning_efforts, prefer one of those values.