Claude 3.5 Sonnet vs Claude Sonnet 4.6
Claude 3.5 Sonnet (2024) and Claude Sonnet 4.6 (2026) are frontier-tier reasoning models from Anthropic. Claude 3.5 Sonnet ships a 200k-token context window, while Claude Sonnet 4.6 ships a 1m-token context window. On MMLU PRO, Claude Sonnet 4.6 leads by 10.1 pts. On pricing, both list $3/1M input and $15/1M output tokens on the cheapest tracked route. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Pick Claude Sonnet 4.6 for general evaluation; token pricing is tied, so keep Claude 3.5 Sonnet only for already-validated prompts or route constraints.
Decision scorecard
Local evidence first| Signal | Claude 3.5 Sonnet | Claude Sonnet 4.6 |
|---|---|---|
| Best for | reasoning-heavy apps, multimodal apps, and tool-calling agents | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 200k | 1m |
| Cheapest output | $15/1M tokens | $15/1M tokens |
| Provider routes | 6 tracked | 6 tracked |
| Shared benchmarks | 8 shared | MMLU PRO leader |
Decision tradeoffs
- Local decision data tags Claude 3.5 Sonnet for Coding, RAG, and Agents.
- Claude Sonnet 4.6 holds a shared-benchmark lead on MMLU PRO, ahead by 10.1 points.
- Claude Sonnet 4.6 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Claude Sonnet 4.6 uniquely exposes Tool use, Computer use, and Parallel agents in local model data.
- Local decision data tags Claude Sonnet 4.6 for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Claude 3.5 Sonnet
$6,150
Cheapest tracked route/tier: GCP Vertex AI
Claude Sonnet 4.6
$6,150
Cheapest tracked route/tier: OpenRouter
Estimated monthly gap: $0.00. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter, Anthropic, and AWS Bedrock; start route-level A/B tests there.
- Cheapest tracked output pricing is tied, so migration risk shifts to quality, latency, and provider packaging.
- Claude Sonnet 4.6 adds Tool use, Computer use, and Parallel agents in local capability data.
- Use this scaffold for teams deciding whether Sonnet 4.6 should replace an established Claude 3.5 Sonnet integration.
- Focus on coding-agent reliability, long-context behavior, and output-token price deltas.
- Mention that migration should be tested with existing system prompts because Claude family upgrades can change refusal and formatting behavior.
- Provider overlap exists on GCP Vertex AI, AWS Bedrock, and Anthropic; start route-level A/B tests there.
- Cheapest tracked output pricing is tied, so migration risk shifts to quality, latency, and provider packaging.
- Check replacement coverage for Tool use, Computer use, and Parallel agents before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2024-06-20 | 2026-02-17 |
| Context window | 200k | 1m |
| Parameters | 70B | — |
| Architecture | Decoder Only | Decoder Only |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Commercial use | Commercial use: conditional | Commercial use: conditional |
| Knowledge cutoff | 2024-04 | 2025-08 |
Pricing and availability
| Pricing attribute | Claude 3.5 Sonnet | Claude Sonnet 4.6 |
|---|---|---|
| Input price | $3/1M tokens | $3/1M tokens |
| Output price | $15/1M tokens | $15/1M tokens |
| Providers |
Capabilities
| Capability | Claude 3.5 Sonnet | Claude Sonnet 4.6 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | Yes | Yes |
| Function calling | Yes | Yes |
| Tool use | No | Yes |
| Structured outputs | Yes | Yes |
| Code execution | Yes | Yes |
| IDE integration | No | No |
| Computer use | No | Yes |
| Parallel agents | No | Yes |
Benchmarks
| Benchmark | Claude 3.5 Sonnet | Claude Sonnet 4.6 |
|---|---|---|
| MMLU PRO | 77.2 | 87.3 |
| SWE-bench Verified | 49.0 | 79.6 |
| LiveCodeBench | 48.7 | 80.0 |
| Massive Multi-discipline Multimodal Understanding | 68.3 | 83.6 |
| HumanEval | 92.0 | 98.0 |
| Chatbot Arena | 1340.0 | 1459.0 |
| MMMU Pro | 63.7 | 75.6 |
| Massive Multitask Language Understanding | 88.7 | 89.3 |
Deep dive
On shared benchmark coverage, MMLU PRO has Claude 3.5 Sonnet at 77.2 and Claude Sonnet 4.6 at 87.3, with Claude Sonnet 4.6 ahead by 10.1 points; SWE-bench Verified has Claude 3.5 Sonnet at 49 and Claude Sonnet 4.6 at 79.6, with Claude Sonnet 4.6 ahead by 30.6 points; LiveCodeBench has Claude 3.5 Sonnet at 48.7 and Claude Sonnet 4.6 at 80, with Claude Sonnet 4.6 ahead by 31.3 points. The largest visible gap is 31.3 points on LiveCodeBench, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint differs most on tool use: Claude Sonnet 4.6. Both models share vision, multimodal input, reasoning mode, and function calling, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
For cost, Claude 3.5 Sonnet lists $3/1M input and $15/1M output tokens on the cheapest tracked provider, while Claude Sonnet 4.6 lists $3/1M input and $15/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend is tied on the cheapest tracked routes. Availability is 6 providers versus 6, so concentration risk also matters.
Choose Claude 3.5 Sonnet when coding workflow support are central to the workload. Choose Claude Sonnet 4.6 when coding workflow support and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Claude 3.5 Sonnet or Claude Sonnet 4.6?
Claude Sonnet 4.6 supports 1m tokens, while Claude 3.5 Sonnet supports 200k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, Claude 3.5 Sonnet or Claude Sonnet 4.6?
Neither is cheaper on tracked token pricing. Both list $3/1M input and $15/1M output tokens on the cheapest tracked route. Provider discounts, batch pricing, or route-specific tiers can still change the final bill.
Is Claude 3.5 Sonnet or Claude Sonnet 4.6 open source?
Claude 3.5 Sonnet is listed under Proprietary. Claude Sonnet 4.6 is listed under Proprietary. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Claude 3.5 Sonnet or Claude Sonnet 4.6?
Both Claude 3.5 Sonnet and Claude Sonnet 4.6 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Which is better for multimodal input, Claude 3.5 Sonnet or Claude Sonnet 4.6?
Both Claude 3.5 Sonnet and Claude Sonnet 4.6 expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Where can I run Claude 3.5 Sonnet and Claude Sonnet 4.6?
Claude 3.5 Sonnet is available on GCP Vertex AI, AWS Bedrock, Anthropic, OpenRouter, and Microsoft Foundry. Claude Sonnet 4.6 is available on OpenRouter, Anthropic, AWS Bedrock, GCP Vertex AI, and Microsoft Foundry. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.