FlagshipAnthropic
Claude Sonnet 4.6
Claude Sonnet 4.6 by Anthropic — compare inference API pricing across providers.
Context 1.0M
Tier Flagship
Knowledge Aug 2025
Modalities text, image
Input from
$1.50 / 1M tokens
across 3 providers
API Pricing
Cheapest on Anthropic — 43% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $1.50 | $7.50 | - | |
| $3.00 | $15.00 | $0.300 | |
| $3.00 | $15.00 | - | |
| $3.00 | $15.00 | - |
Prices updated daily. Last check: Jun 27, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
35.9 / 100
Output Speed
53.7 t/s
Latency (TTFT)
1.1s
Reasoning & Knowledge
- GPQA Diamond79.9%
- Humanity's Last Exam13.2%
Coding
- SciCode46.9%
Agentic & Tool Use
- Terminal-Bench Hard46.2%
- τ²-bench79.5%
Instruction & Long Context
- IFBench41.2%
- Long-Context Reasoning57.7%
Benchmarks measured Jun 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Anthropic
- Family
- Sonnet
- Tier
- Flagship
- Context Window
- 1.0M
- Knowledge Cutoff
- Aug 2025
- Modalities
- Text, Image
Capabilities
- Tool Calling
- No
- Open Source
- No
- Aliases
- claude-sonnet-4-6, claude-sonnet-4-6-20260217, Claude Sonnet 4.6