Reasoning & thinking

Reasoning models perform internal thinking before producing an answer. They are significantly stronger at math, code, planning and logic problems than ordinary models, but with higher latency and cost.

Supported models

Vendor	Model / suffix	How to enable
OpenAI	`o3-mini-low/medium/high`, `o3`, `gpt-5.5-low/medium/high`	Built into the model ID / `reasoning_effort`
Anthropic	`claude-*-thinking`, base model + `thinking` param	Built into the model ID / `thinking` param
Google	`gemini-2.5-pro-thinking`, `-low/medium/high`	Built into the model ID / `thinking_budget`
DeepSeek	`deepseek-r1`	Use the model ID directly

OpenAI

Via model ID

resp = client.chat.completions.create(
    model="o3-mini-high",
    messages=[{"role": "user", "content": "Prove that √2 is irrational"}],
    max_completion_tokens=4096,
)
print(resp.usage.completion_tokens_details.reasoning_tokens)

Via parameter (Responses API)

resp = client.responses.create(
    model="o3-mini",
    input="Prove that √2 is irrational",
    reasoning={"effort": "high"},
    max_output_tokens=4096,
)

Notes:

Reasoning models do not support some parameters like temperature, top_p, presence_penalty.
Use max_completion_tokens (new) rather than max_tokens.
reasoning_tokens are invisible but billed — be sure to leave enough budget.

Claude

resp = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=4096,
    thinking={"type": "enabled", "budget_tokens": 8000},
    messages=[{"role": "user", "content": "Prove Fermat's little theorem"}],
)

for block in resp.content:
    if block.type == "thinking":
        print("[thinking]", block.thinking)
    elif block.type == "text":
        print("[answer]", block.text)

budget_tokens: the thinking budget ceiling, typically 1024-32000.
Thinking blocks are visible by default — unlike OpenAI, you can read the reasoning process.
Billing: thinking_tokens are billed additionally at the output price.

Gemini

resp = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents="Prove Goldbach's conjecture",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(thinking_budget=8000),
    ),
)
print(resp.usage_metadata.thoughts_token_count)

Or use a preset ID:

ID	Behavior
`gemini-2.5-pro-thinking`	Default medium thinking budget
`gemini-2.5-pro-thinking-128`	Force a 128-token thinking budget
`gemini-2.5-flash-nothinking`	Thinking off (cheaper)
`gemini-2.5-pro-high`	High reasoning effort

When to use a reasoning model

✅ Good for

Math proofs, complex logic problems
Code refactoring, bug localization
Multi-step planning, agent decisions
Long-document analysis, research reviews

❌ Not needed for

Ordinary Q&A, casual chat
Translation, summarization, rewriting
Simple classification, info extraction

Billing reminders

Reasoning tokens are not shown in content but are still billed at the output price.
The console log breaks out thinking / answer into two parts.
When setting max_completion_tokens / max_output_tokens, leave plenty of headroom (≥ 4096 recommended), or the answer may come back empty due to token exhaustion.

Streaming

Reasoning models can stream, but during the thinking phase there are no delta contents — the client sees a blank period first (possibly several seconds) before the answer starts arriving. Add a loading state in your UI. Claude / Gemini streaming can receive thinking-block deltas, enabling a “visible thinking process.”

Get started

First steps

Models & billing

Client integrations

Advanced

Help & support

Legal

Supported models

OpenAI

Via model ID

Via parameter (Responses API)

Claude

Gemini

When to use a reasoning model

✅ Good for

❌ Not needed for

Billing reminders

Streaming

​Supported models

​OpenAI

​Via model ID

​Via parameter (Responses API)

​Claude

​Gemini

​When to use a reasoning model

✅ Good for

❌ Not needed for

​Billing reminders

​Streaming

Supported models

OpenAI

Via model ID

Via parameter (Responses API)

Claude

Gemini

When to use a reasoning model

Billing reminders

Streaming