Claude Sonnet 4.6
Claude Sonnet 4.6 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 1m context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Claude 4.6
- Released
- 2026-02-17
- Context
- 1m
- Max output
- 64,000
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-08
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Training
- Fine-tuned
Cheapest of 6 routes · Anthropic · cache read $0.300
About
Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence. Proprietary decoder-only model with 1M-token context, 64K max output, multimodal vision, extended thinking, and function calling. Available via Anthropic API, AWS Bedrock, GCP Vertex AI, and OpenRouter at $3/1M input and $15/1M output tokens.
Claude Sonnet 4.6 is a proprietary model in the Claude 4.6 family. The structured metadata tracks a 1m-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenRouter, Anthropic, AWS Bedrock, and 3 more, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 79.6, Terminal-Bench 2.0 59.1, and SWE-bench Multilingual 75.9.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D3 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ D3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 6Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| Anthropic | $3.00 | $15.00 | $1.50 / $7.50 | read $0.300 / 5m $3.75 / 1h $6.00 | Serverless |
| AWS Bedrock | $3.00 | $15.00 | - | - | Serverless |
| GCP Vertex AI | $3.00 | $15.00 | - | - | Serverless |
| Microsoft Foundry | $3.00 | $15.00 | - | read $0.300 / 5m $3.75 / 1h $6.00 | Serverless |
Available via routers & gateways(16)
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(18)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 79.6 | SWE-bench Verified | https://www.nxcode.io/resources/news/claude-sonnet-4-6-complete-guide-benchmarks-pricing-2026 |
| Terminal-Bench 2.0 | 59.1 | Terminal-Bench 2.0 | https://www.datacamp.com/blog/claude-sonnet-4-6 |
| SWE-bench Multilingual | 75.9 | SWE-bench Multilingual | https://www.nxcode.io/resources/news/claude-sonnet-4-6-complete-guide-benchmarks-pricing-2026 |
| Google-Proof Q&A | 89.9 | diamond | https://www-cdn.anthropic.com/78073f739564e986ff3e28522761a7a0b4484f84.pdf |
| MMLU PRO | 87.3 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| τ-bench | 87.5 | τ-bench | https://taubench.com/ |
| MultiChallenge | 57.1 | MultiChallenge | https://labs.scale.com/leaderboard/multichallenge |
| Chatbot Arena | 1459.0 | — | https://arena.ai/leaderboard |
| MMMU Pro | 75.6 | official Anthropic system card, adaptive thinking, max effort, with image cropping tool | https://www.anthropic.com/news/claude-sonnet-4-6 |
| SWE-rebench | 60.7 | pass@1 (best of 5 runs) | https://swe-rebench.com/leaderboard |
| AIME 2025 | 94.0 | AIME 2025 (accuracy) | https://automatio.ai/models/claude-sonnet-4-6 |
| ARC-AGI-2 | 58.3 | llm-stats shows 0 (accuracy%) | https://llm-stats.com/benchmarks/arc-agi-v2 |
| Humanity's Last Exam | 33.2 | HLE without tools (accuracy) | https://automatio.ai/models/claude-sonnet-4-6 |
| HumanEval | 98.0 | HumanEval (pass@1) | https://automatio.ai/models/claude-sonnet-4-6 |
| LiveCodeBench | 80.0 | LiveCodeBench score (accuracy) | https://automatio.ai/models/claude-sonnet-4-6 |
| MCP-Atlas | 61.3 | llm-stats shows 0 (accuracy%) | https://llm-stats.com/benchmarks/mcp-atlas |
| Massive Multitask Language Understanding | 89.3 | MMLU (accuracy) | https://automatio.ai/models/claude-sonnet-4-6 |
| Massive Multi-discipline Multimodal Understanding | 83.6 | MMMU (accuracy) | https://automatio.ai/models/claude-sonnet-4-6 |
Migration checks
Rankings & picks(10)
Comparison and alternatives
Browse all comparisons →Show all 79 popular comparisonssorted by 7-day search impressions
Cheapest of 6 routes · Anthropic · cache read $0.300