Available now
Anthropic

claude-opus-4-5-thinking

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

TextReasoningToolsFilesVision200KCacheComputerUse
Input$3.00/ 1M
Output$15.00/ 1M
Context200K
Endpointsopenai, anthropic

Capabilities

ReasoningToolsVisionFilesCacheStructuredComputer usePrefill

Modalities

Input
fileimagetext
Output
text

Quick stats

Context window200K
Max output64K
Modechat
TokenizerClaude
ModeratedYes
Reasoning levels
minimal

Performance

Loading performance data...

Supported parameters

ParameterAlwaysDefault
frequency_penalty(do not send)
include_reasoning
max_tokens
presence_penalty(do not send)
reasoning
repetition_penalty(do not send)
response_format
stop
structured_outputs
temperature(do not send)
tool_choice
tools
top_k(do not send)
top_p(do not send)
verbosity
§ 01

Pricing

Input price$3.00 · 1M tokens
Output price$15.00 · 1M tokens
Context window200K tokens
Compatible endpointsopenai, anthropic
VendorAnthropic
§ 02

Call claude-opus-4-5-thinking from your code

Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.

bash
curl https://api.unorouter.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5-thinking",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Sign in to auto-fill your API key

§ 03

Frequently asked questions

How much does claude-opus-4-5-thinking cost per 1M tokens?

Input is priced at $3.00 per 1M tokens, output at $15.00 per 1M tokens. Billing is per token, no rounding to batch sizes.

How do I access claude-opus-4-5-thinking via API?

Send requests to the UnoRouter /v1/chat/completions endpoint with model=claude-opus-4-5-thinking. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.

What is the context window of claude-opus-4-5-thinking?

claude-opus-4-5-thinking supports a context window of 200K tokens, shared between your prompt and the model's response.

§ 04

Similar models

Try claude-opus-4-5-thinking now

Create an API key and start making requests in under a minute.

View all models