GeniusRelay
Sign upConsole

Anthropic: Claude Sonnet 4.5 Thinking

claude-sonnet-4.5:thinking

CompareAPIGet an API keyGet an API key

Claude Sonnet 4.5 Thinking costs $3.90 per million input tokens and $19.50 per million output tokens, supports 200K context, and is available through the OpenAI-compatible API.

Adds extended, step‑by‑step reasoning for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows, complex problem solving, and scenarios that benefit from explicit thinking traces.

Modalities

Text + Image → Text

Input / output price

$3.90 / $19.50 per 1M

Context

200K · max output 64K

Capabilities

ReasoningVisionTool calling

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$3.90
Output$19.50
Cached input$0.390

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0273
Per day
$13.65
Per month (30 days)
$409.50

Claude Sonnet 4.5 Thinking: input $3.9/M · output $19.5/M · cached input $0.39/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-4.5:thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to claude-sonnet-4.5:thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5:thinking",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Claude Sonnet 4.5 Thinking billed?
Input is $3.90 and output is $19.50 per million tokens; cached input is $0.390. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
200K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Claude Sonnet 4.5 Thinking API pricing · GeniusRelay