🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
C

Claude Opus 4.5

AnthropicModel IDclaude-opus-4-5
C

Claude Opus 4.5

AnthropicModel IDclaude-opus-4-5

Claude Opus 4.5 is an advanced Anthropic model designed for complex reasoning, professional software engineering, coding, agentic workflows, computer use, research, and demanding knowledge work. It supports text and image inputs, extended thinking, advanced tool use, a 200K-token context window, and up to 64K output tokens.

ModeText / Image → Text
Input price$5 / 1M tokens
Output price$25 / 1M tokens
Context length200K tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Anthropic
Input modality
Text / Image
Output modality
Text
Max output
64K tokens

Pricing

ProviderBilling typePrice summary
C
Anthropic-Custom
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
C
Anthropic-Balanced
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

Integration

Code Example

curl http://127.0.0.1:4179/v1/messages \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "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 4.5 supports up to 64K output tokens.
object-Enables extended thinking for complex reasoning tasks.
integer-Maximum token budget allocated to extended thinking. The minimum supported value is 1024 and it must normally be lower than max_tokens.
stringhighControls how much effort the model spends on the overall response. Supported levels include low, medium, and high.
booleanfalseWhether to stream the response incrementally using server-sent events.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.