Skip to main content
AnthropicFeb 17, 2026

Claude Sonnet 4.6

claude-sonnet-4-6Anonymized

Claude Sonnet 4.6 is Anthropic’s best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.

$3.00/$15.00
per 1M in / out
1M
context window
64K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 31%78.8%
Blended pricecheaper than 17%$6.00
Context windowlarger than 42%1M
Max outputlarger than 35%64K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImage
OutText

Not supportedvideo input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
78.8%96th of 139 · 72 score higher for less, including GPT-6.2 Sol, GPT-6.2 Sol Pro and Gemini 4 Argon

Specs

Model ID
claude-sonnet-4-6
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
64,000 tokens
Reasoning
low · medium · high · max · default high
Precision
Set by the provider
Privacy
Anonymized
Weights
Closed
Added
Feb 17, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Claude Sonnet 4.6$3.00$15.0078.8%1M64K——
Gemini 3.1 Pro Preview$2.50$15.0081.0%1M32K——
GPT-5.4$2.50$15.0089.9%1M128K——
GPT-5.3 Codex$1.75$14.0085.0%400K128K——
GPT-5.2$1.75$14.0089.4%256K64K——

Other versions

  1. Claude Sonnet 4.6Feb 2026
  2. Claude Sonnet 5Jun 2026
  3. Claude Sonnet 5.5Sep 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$3.00per 1M tokens
Cached input$0.3090% off input
Output$15.00per 1M tokens

Estimate a workload

$0.0135per request
$135for 10,000 requests

Blended price against similar models

Claude Sonnet 4.6$6.00
GPT-5.4$5.63
GPT-5.2$4.81

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "high"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelclaude-sonnet-4-6Required
messagestext · image_urlContent parts the model reads
max_completion_tokensUp to 64,000Counts reasoning tokens
reasoning_effortlow | medium | high | maxDefault high
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations