Thinking

Reasoning tokens are billed as output tokens, so controlling them controls cost and latency. Use your protocol's own reasoning fields with any model: a reasoning_effort sent on Chat Completions takes effect on Claude and Gemini models too.

Controls per protocolCopy Anchor Link

On a model's native protocol, these fields reach the model as you sent them and follow the vendor's documentation: reasoning_effort on GPT, thinking on Claude through Messages, thinkingConfig on Gemini through the Gemini endpoint, and vendor fields such as DeepSeek's thinking or Qwen's enable_thinking on Chat Completions.

On Chat Completions, reasoning_effort takes precedence over the reasoning object, which takes precedence over include_reasoning. Effort levels are none, minimal, low, medium, high, and xhigh.

ClaudeCopy Anchor Link

On Chat Completions, Responses, or Gemini, Claude models take these settings:

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-4-5",
    "max_tokens": 1500,
    "messages": [{"role": "user", "content": "What is 17 * 23? Reply with the number only."}],
    "thinking": {"type": "enabled", "budget_tokens": 1024}
  }'

{
  "choices": [
    {
      "finish_reason": "stop",
      "native_finish_reason": "end_turn",
      "message": {
        "role": "assistant",
        "content": "391",
        "reasoning": "17 * 23 = ?\n\nLet me calculate this:\n17 * 23 = 17 * 20 + 17 * 3\n= 340 + 51\n= 391",
        "reasoning_details": [{ "type": "reasoning.text", "text": "17 * 23 = ?\n\n…", "signature": "EuoCCrgB…", "index": 0 }]
      }
    }
  ],
  "usage": { "prompt_tokens": 51, "completion_tokens": 60, "total_tokens": 111, "completion_tokens_details": { "reasoning_tokens": 54 } }
}

Newer Claude models think adaptively. Use the setting each model takes:

Other settings reach the model as you sent them; if the model doesn't take one, its own error comes back to you, and a rejected request is not charged.

GeminiCopy Anchor Link

On Chat Completions, Responses, or Messages, Gemini models take these settings:

Measured on google/gemini-3.1-flash-lite with the same prompt as above:

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.1-flash-lite",
    "messages": [{"role": "user", "content": "What is 17 * 23? Reply with the number only."}],
    "reasoning_effort": "none"
  }'

Other modelsCopy Anchor Link

For GPT, DeepSeek, Qwen, and other models whose native protocol is Chat Completions, an effort level from any protocol becomes reasoning_effort. On GPT reasoning models, leave temperature and top_p at their defaults while reasoning is on.

Reasoning in the responseCopy Anchor Link

Reasoning tokens are reported in usage on every protocol:

The visible reasoning comes back as reasoning and reasoning_details on Chat Completions, reasoning output items on Responses, thinking blocks on Messages, and parts with "thought": true on Gemini.