Claude Sonnet 4.6 vs Claude Sonnet 5
Claude Sonnet 4.6 (2026) and Claude Sonnet 5 (2026) are frontier-tier reasoning models from Anthropic. Both ship a 1M-token context window. On SWE-bench Verified, Claude Sonnet 5 leads by 5.6 pts. On pricing, Claude Sonnet 5 costs $2/1M input tokens versus $3/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Claude Sonnet 5 is ~50% cheaper at $2/1M; pay for Claude Sonnet 4.6 only for coding workflow support.
Decision scorecard
Local evidence first| Signal | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| 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 | 1M | 1M |
| Cheapest output | $15/1M tokens | $10/1M tokens |
| Provider routes | 6 tracked | 6 tracked |
| Shared benchmarks | 7 shared | SWE-bench Verified leader |
Decision tradeoffs
- Claude Sonnet 4.6 holds a shared-benchmark lead on CursorBench, ahead by 24.9 points.
- Claude Sonnet 4.6 uniquely exposes Computer use and Parallel agents in local model data.
- Local decision data tags Claude Sonnet 4.6 for Coding, RAG, and Agents.
- Claude Sonnet 5 holds a shared-benchmark lead on SWE-bench Verified, ahead by 5.6 points.
- Claude Sonnet 5 has the lower cheapest tracked output price at $10/1M tokens.
- Local decision data tags Claude Sonnet 5 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 Sonnet 4.6
$6,150
Cheapest tracked route/tier: OpenRouter
Claude Sonnet 5
$4,100
Cheapest tracked route/tier: Anthropic
Estimated monthly gap: $2,050. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on Anthropic, AWS Bedrock, and GCP Vertex AI; start route-level A/B tests there.
- Claude Sonnet 5 is $5/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Computer use and Parallel agents before moving production traffic.
- Provider overlap exists on OpenRouter, Anthropic, and AWS Bedrock; start route-level A/B tests there.
- Claude Sonnet 4.6 is $5/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Claude Sonnet 4.6 adds Computer use and Parallel agents in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-02-17 | 2026-06-30 |
| Context window | 1M | 1M |
| Parameters | — | — |
| Architecture | Decoder Only | Decoder Only |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Weights | Not released | Not released |
| Code | Unknown | Unknown |
| Commercial use | Restricted | Restricted |
| Knowledge cutoff | 2025-08 | 2026-01 |
Pricing and availability
| Pricing attribute | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Input price | $3/1M tokens | $2/1M tokens |
| Output price | $15/1M tokens | $10/1M tokens |
| Providers |
Capabilities
| Capability | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | Yes | Yes |
| JSON / Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | Yes | Yes |
| IDE integration | No | No |
| Computer use | Yes | No |
| Parallel agents | Yes | No |
Benchmarks
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| SWE-bench Verified | 79.6 | 85.2 |
| Humanity's Last Exam | 33.2 | 43.2 |
| CursorBench | 49.0 | 24.1 |
| LMArena Text Arena - Creative Writing | 1435.0 | 1416.0 |
| LMArena Vision Arena | 1275.0 | 1262.0 |
| Chatbot Arena | 1459.0 | 1462.0 |
| SWE-bench Multilingual | 75.9 | 78.3 |
Deep dive
On shared benchmark coverage, SWE-bench Verified has Claude Sonnet 4.6 at 79.6 and Claude Sonnet 5 at 85.2, with Claude Sonnet 5 ahead by 5.6 points; Humanity's Last Exam has Claude Sonnet 4.6 at 33.2 and Claude Sonnet 5 at 43.2, with Claude Sonnet 5 ahead by 10 points; CursorBench has Claude Sonnet 4.6 at 49 and Claude Sonnet 5 at 24.1, with Claude Sonnet 4.6 ahead by 24.9 points. The largest visible gap is 24.9 points on CursorBench, 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 is close: both models cover vision, multimodal input, reasoning mode, JSON / Tool use, and JSON / Tool use. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.
For cost, Claude Sonnet 4.6 lists $3/1M input and $15/1M output tokens on the cheapest listed provider, while Claude Sonnet 5 lists $2/1M input and $10/1M output tokens on the cheapest listed provider. A 70/30 input-output blend puts Claude Sonnet 5 lower by about $2.20 per million blended tokens. Availability is 6 providers versus 6, so concentration risk also matters.
Choose Claude Sonnet 4.6 when coding workflow support are central to the workload. Choose Claude Sonnet 5 when coding workflow support and lower input-token cost 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 Sonnet 4.6 or Claude Sonnet 5?
Claude Sonnet 4.6 supports 1M tokens, while Claude Sonnet 5 supports 1M 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 Sonnet 4.6 or Claude Sonnet 5?
Claude Sonnet 5 is cheaper on listed token pricing. Claude Sonnet 4.6 costs $3/1M input and $15/1M output tokens. Claude Sonnet 5 costs $2/1M input and $10/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Claude Sonnet 4.6 or Claude Sonnet 5 open source?
Claude Sonnet 4.6 is listed under Proprietary. Claude Sonnet 5 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 Sonnet 4.6 or Claude Sonnet 5?
Both Claude Sonnet 4.6 and Claude Sonnet 5 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 Sonnet 4.6 or Claude Sonnet 5?
Both Claude Sonnet 4.6 and Claude Sonnet 5 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 Sonnet 4.6 and Claude Sonnet 5?
Claude Sonnet 4.6 is available on OpenRouter, Anthropic, AWS Bedrock, GCP Vertex AI, and Microsoft Foundry. Claude Sonnet 5 is available on Anthropic, AWS Bedrock, GCP Vertex AI, OpenRouter, and Microsoft Foundry. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Popular comparisons for Claude Sonnet 4.6
Last reviewed: 2026-10-17. Data sourced from public model cards and provider documentation.