Claude Sonnet 4.6: Pricing, Context, and Benchmarks
Claude Sonnet 4.6 is Anthropic's Claude 4 model released on 2026-03-12. It runs on a 200K-token context window, priced at $3.00/M input and $15.00/M output. The workhorse Claude — what most production teams default to. 200K context, strong coding, fast streaming.
Specifications
| Provider | Anthropic |
|---|---|
| Family | Claude 4 |
| Released | 2026-03-12 |
| Status | active |
| Context window | 200K tokens |
| Max output | 64K tokens |
| Modalities | text image |
| Capabilities | function calling json mode vision streaming tool use |
| Tokenizer | claude-3 |
| API endpoint | https://api.anthropic.com/v1/messages |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
Benchmark scores
| Benchmark | Category | Score | Measured | Source |
|---|---|---|---|---|
| HumanEval | coding | 92.0 | 2026-03-12 | ↗ |
| Aider Polyglot | coding | 74.0 | 2026-03-12 | ↗ |
| SWE-bench Verified | coding | 72.5 | 2026-03-12 | ↗ |
Scores reflect single measurements on the date shown. Reproducibility varies; consult the linked source for methodology. Use the comparison tool for side-by-side analysis.
What this model is good for
Based on benchmark scores and capability fit, Claude Sonnet 4.6 ranks well for:
- Code Generation — rank #2. The default. Strong coding plus best price/performance in the Claude line.
- Agentic Workflows — rank #2. Default agent loop model for most teams. Cheaper Opus alternative.
- Document Q&A / RAG — rank #2. Best general-purpose model for RAG when citations are added via prompting.
- Long Context Summarization — rank #4. 200K context limits very long documents but quality at that size is best in class.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0180 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.002100 | $2.10 | $2,100 |
| Standard chat | 1K / 500 | $0.010500 | $10.50 | $10,500 |
| RAG with retrieval | 4K / 500 | $0.019500 | $19.50 | $19,500 |
| Long doc summary | 20K / 1K | $0.075000 | $75.00 | $75,000 |
| Long context (100K input) | 100K / 2K | $0.322500 | $322.50 | $322,500 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other Anthropic models
Common comparisons
- Claude Sonnet 4.6 vs Grok 3 Side-by-side specs, pricing, and benchmarks
- Claude Sonnet 4.6 vs GPT-4o Side-by-side specs, pricing, and benchmarks
- Claude Sonnet 4.6 vs Llama 3.1 405B Side-by-side specs, pricing, and benchmarks
- Claude Sonnet 4.6 vs Command R+ Side-by-side specs, pricing, and benchmarks
API setup
curl https://api.anthropic.com/v1/messages \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-4-6", "messages": [{"role": "user", "content": "Hello"}]}'See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.