Claude Sonnet 4.6
Language AvailableCompare models
ComparingClaude Sonnet 4.6with
Pick a model above to see the comparison.
anthropic/claude-sonnet-4-6 · by Anthropic · decoder-only-transformer
Pricing — 1 offering(s)
Input tokens
- $3.00 / 1M tokens (input) Current 2026-06-12 → present
Output tokens
- $15.00 / 1M tokens (output) Current 2026-06-12 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
Capability profile
reasoning strong
coding strong
tool use strong
instruction following strong
context window strong
multilingual strong
speed moderate
cost efficiency moderate
Coding benchmarks
View full leaderboard →| Benchmark | Score | Harness | Source |
|---|---|---|---|
| swe-bench-verified ↗ | 79.6% 2026-02 | agentless 2.0 | 🏢 vendor ↗ |
| swe-bench-pro | 58.1% 2026-06 | agentless | 🏢 vendor ↗ |
| terminal-bench-2-1 | 67.0% 2026-06 | terminus-2 | 🏢 vendor ↗ |
Operator guidance
The price/performance sweet spot of the Claude 4.x line prior to Sonnet 5's release. Step up to Opus 4.8 for the hardest tasks; drop to Haiku 4 for cost/latency-sensitive work.
Use cases
- The default workhorse: strong quality at a moderate price/latency
- Production coding agents, RAG, and tool use at scale
Limitations
- Not as strong as Opus 4.8 on the very hardest reasoning/agentic tasks
- Reasoning/tool-use/instruction-following/multilingual ratings are qualitative (vendor + community signal, inherited from the Sonnet 4 family's established profile); coding is now benchmark-cited directly
- Uses the PREVIOUS tokenizer, not the Opus-4.7+/Sonnet-5 one — Anthropic's pricing docs list Sonnet 4.6 and earlier as using the older tokenizer, so token counts for this model are NOT inflated ~30% the way Sonnet 5's are for the same text