anthropic
Anthropic: Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
Specifications
- Model ID
- anthropic/claude-sonnet-4.6
- Canonical ID
- anthropic/claude-4.6-sonnet-20260217
- Creator
- anthropic
- Added to OpenRouter
- 17.02.2026
- Context length
- 1,000,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $3 / out $15
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default medium · efforts: max, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | AA — next 20% of the cohort | — |
| Agents | AA — next 20% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default medium · efforts: max, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 63 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 31.8 | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · agenticgamedevwin rate 51.1% · rank 17 | 1,119Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 61.8% · rank 17 | 1,182Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 64.3% · rank 16 | 1,191Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 60.6% · rank 7 | 1,226Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 63.6% · rank 18 | 1,206Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 57% · rank 29 | 1,172Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 57.5% · rank 45 | 1,217Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 60.1% · rank 21 | 1,231Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 59.4% · rank 29 | 1,267Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 58.3% · rank 22 | 1,276Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 58.8% · rank 40 | 1,249Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 58.7% · rank 32 | 1,188Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 58.3% · rank 36 | 1,264Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 60% · rank 24 | 1,279Elo | AA — next 20% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Claude Platform on AWS | 1,000,000 | $3 | $15 | — | — | 100% |
| Azure | 1,000,000 | $3 | $15 | — | — | — |
| Anthropic | 1,000,000 | $3 | $15 | — | — | 73.33% |
| Amazon Bedrock | 1,000,000 | $3 | $15 | — | — | 100% |
| 1,000,000 | $3 | $15 | — | — | 100% | |
| Amazon Bedrock | 1,000,000 | $3.3 | $16.5 | — | — | — |
| Amazon Bedrock | 1,000,000 | $3.3 | $16.5 | — | — | 100% |
| 1,000,000 | $3.3 | $16.5 | — | — | — | |
| 1,000,000 | $3.3 | $16.5 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
- Four Amazon Bedrock request settings that change inference costsAn AWS walkthrough shows how cache duration, service tier, reasoning effort, and maxTokens change token counts and rates on Amazon Bedrock, with tests on Claude and Nova models.
- AWS shows composable multi-agent systems built on the A2A protocolAn AWS reference architecture connects a LangChain orchestrator with a Strands-based compliance agent across two accounts using the Agent-to-Agent protocol, bidirectional OAuth, and Agent Card discovery.