VENICE ATLAS · MODEL DOSSIER · CLAUDE SONNET 4.6

Model overview

Claude Sonnet 4.6

Name: Claude Sonnet 4.6
Brand: venice.ai
Price: 3.0000 USD
Availability: InStock

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.

claude-sonnet-4-6 · venice.ai

Text · Venice catalog$3.00 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$3.00 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks17Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Biology#2631.44 rating Chemistry#3031.44 rating Communication#327.28 rating Finance#1229.95 rating Frontend Development#1326.83 rating Language#1926.86 rating Math#3334.61 rating Physics#3031.44 rating Search#2715.06 rating Spatial Reasoning#2520.50 rating

Agents2 results

Finance Agentfinance-agent · agents

63.3%

ReportedOct 2026

Finance Agent v2finance-agent-v2 · agents

51.0%

ReportedOct 2026

Coding1 result

DeepSWE 1.1deepswe-1.1 · code

30.0%

ReportedOct 2026

Communication2 results

Tau2 Retailtau2-retail · communication

91.7%

ReportedOct 2026

Tau2 Telecomtau2-telecom · communication

97.9%

ReportedOct 2026

Language1 result

MMMLUmmmlu · language

89.3%

ReportedOct 2026

Legal1 result

Legal Agent Benchmarklegal-agent-benchmark · legal

5.40%

ReportedOct 2026

Math1 result

LiveBenchlivebench · math

75.5%

ReportedOct 2026

Multimodal1 result

OSWorldosworld · multimodal

72.5%

ReportedOct 2026

Reasoning7 results

ARC-AGI v2arc-agi-v2 · reasoning

58.3%

ReportedOct 2026

BrowseCompbrowsecomp · reasoning

74.7%

ReportedOct 2026

GPQAgpqa · reasoning

89.9%

ReportedOct 2026

Humanity's Last Examhumanity's-last-exam · reasoning

49.0%

ReportedOct 2026

MCP Atlasmcp-atlas · reasoning

61.3%

ReportedOct 2026

SWE-Bench Verifiedswe-bench-verified · reasoning

79.6%

ReportedOct 2026

Terminal-Bench 2.0terminal-bench-2 · reasoning

59.1%

ReportedOct 2026

Vision1 result

MMMU-Prommmu-pro · vision

75.6%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $3.00
Output price per 1M tokens: $15.00
Cache read price per 1M tokens: $0.30
Cache write price per 1M tokens: $3.75
Blended price per 1M tokens (50/50): $9.00

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionWeb search

Endpoint metadata

Privacy: anonymized
Quantization: not-available
Maximum completion tokens: 64K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

All capabilities

Max Images: 10
Quantization: not-available
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: high
Reasoning Effort Options: low, medium, high, max
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from anthropic

claude-sonnet-5-5Claude Sonnet 5.5$2.00 input per 1M tokens ↗claude-haiku-5-5Claude Haiku 5.5$0.10 input per 1M tokens ↗claude-opus-5-5Claude Opus 5.5$4.00 input per 1M tokens ↗