🎉 Get Free $5 on Signup！
Models
Enterprise
Subscribe
Resource
Activity
Documentation
Console

/anthropic/claude-opus-4-6-thinking

C

Anthropic: Claude Opus 4.6 (Thinking)

Claude Opus 4.6 Thinking: Launched in February 2026, this model defaults to an "Adaptive Thinking Mode." Engineered for extreme logical reasoning and agentic programming, it natively supports a massive 1 Million token context window, making it ideal for processing colossal codebases.

Modetext、image → text
Input price$5 per M tokens
Output price$25 per M tokens
Context length1M tokens
Listed at2026-02-05T00:00:00Z

Anthropic

Latency—
Throughput—
Upload rate—
Context length1M tokens
Max output128K tokens
Input price$5per 1M tokens
Output price$25per 1M tokens
Cache read$0.5per 1M tokens
Cache write$6.25per 1M tokens

Performance

Avg TPS—
Avg latency—
Avg success rate—
TPS—
TTFT—
Latency—
Success rate—

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1/messages \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-6-thinking",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
anthropic

Supported Parameters

ParameterTypeDefaultDescription
integer-Maximum number of output tokens. Claude Opus 4.6 supports up to 128K output tokens.
stringhighControls the model's reasoning effort. Higher effort can improve performance on complex tasks while increasing latency and token usage.
booleanfalseWhether to stream the response incrementally using server-sent events.
objectadaptiveEnables adaptive thinking. Claude dynamically decides when and how much to reason based on task complexity and the configured effort level.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary
C
Anthropic
Per token
Input price$5per 1M tokens
Completion price$25per 1M tokens
Cache read price$0.5per 1M tokens
Cache write price$6.25per 1M tokens