Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.
- Input / output price
- $2.00 / $10.00 per 1M
- Context
- 1M tokens
- Released
- Jun 30, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 routes from 4 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Anthropic anthropic/claude-sonnet-5 | $2.00/M | $10.00/M |
Bedrock bedrock/global.anthropic.claude-sonnet-5 | $2.00/M | $10.00/M |
Perplexity perplexity/claude-sonnet-5 | $2.00/M | $10.00/M |
Bedrock bedrock/us.anthropic.claude-sonnet-5 | $2.20/M | $11.00/M |
OpenRouterRetired openrouter/claude-sonnet-5 | $2.00/M | $10.00/M |
Is a provider down? Claude status, AWS Bedrock status, Perplexity status, OpenRouter status
Pricing
Averaged across 5 routes from 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $2.04 per 1M
- Average output
- $10.20 per 1M
- Average cache read
- $0.20 per 1M
- Average cache write
- $2.56 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better128tokens/sacross providers
Time to first token
Lower is better0.9sacross providers
Response latency
Lower is better6.5sacross providers
Benchmarks
The Respan Index plus 32 published scores from 13 sources, each linked to where it was published.
48.0/ 100
Respan Index#48 of 176
- 48Claude Sonnet 548.0
- 47GPT-5.6 Luna48.4
- 49Hy4 preview47.2
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedAnthropic | 85.2% | Anthropic | Jun 30, 2026 |
| LiveBench CodingLiveBench | 80.7% | LiveBench | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 69% | Håvard Tveit Ihle | Nov 17, 2026 |
| MirrorCodeEpoch AI | 63.3% | Epoch AI | Nov 11, 2026 |
| SWE-rebench 2026-05-15 to 2026-07-01Nebius | 56.8% | Nebius | Oct 5, 2026 |
| DeepSWE v1.1Datacurve | 53.8% | Datacurve | Oct 5, 2026 |
| GSO Opt@1GSO | 36.3% | GSO | Jul 12, 2026 |
| Terminal-Bench 4.0Vals AI | 10.6% | Vals AI | Oct 13, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Toolathlon-VerifiedHKUST | 71.6% | HKUST | Jul 1, 2026 |
| LiveBench Agentic CodingLiveBench | 59.4% | LiveBench | Oct 5, 2026 |
| APEX-AgentsMercor | 54.5% | Mercor | Oct 5, 2026 |
| Vending-Bench 2Andon Labs | 6377.7 · #25 of 68 | Andon Labs | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 90.5% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 88.7% | LiveBench | Oct 5, 2026 |
| LiveBench Data AnalysisLiveBench | 71.7% | LiveBench | Oct 5, 2026 |
| SimpleBenchSimpleBench | 60.6% | SimpleBench | Jul 9, 2026 |
| Humanity's Last Exam (with tools)Anthropic | 57.4% | Anthropic | Jun 30, 2026 |
| Chess PuzzlesEpoch AI | 45% | Epoch AI | Oct 28, 2026 |
| Humanity's Last Exam (no tools)Anthropic | 43.2% | Anthropic | Jun 30, 2026 |
| Mystery Game PuzzlesEpoch AI | 35% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 94.7% | Epoch AI | Oct 5, 2026 |
| LiveBench MathematicsLiveBench | 92.9% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 65.6% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 29.3% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 75% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 63.9% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 33.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1539 Elo · #52 of 124 | LMArena | Nov 19, 2026 |
| LMArena EloLMArena | 1461 Elo · #52 of 191 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1261 Elo · #38 of 91 | LMArena | Nov 19, 2026 |
| LMArena AgentLMArena | 0.01 · #29 of 68 | LMArena | Nov 18, 2026 |
How Claude compares: Claude vs Gemini, Claude vs Grok, Claude vs GPT
Compare Claude Sonnet 5: Claude Sonnet 5 vs Claude Sonnet 4.6, Claude Sonnet 5 vs Claude Sonnet 5.5, Claude Sonnet 5 vs Gemini 3.8 Flash, Claude Sonnet 5 vs Gemini 4 Argon, Claude Sonnet 5 vs Claude Fable 5.2, Claude Sonnet 5 vs Claude Opus 5.5
Apps
Use Claude Sonnet 5 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Claude Sonnet 5 FAQ
Short answers, built from the data on this page.
Claude Sonnet 5 is a model from Anthropic, released on Jun 30, 2026. Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.
On the Respan gateway, Claude Sonnet 5 costs from $2.00 per 1M input tokens and $10.00 per 1M output tokens on Anthropic, Bedrock, Perplexity, and 1 more, after gateway discounts. Averaged across its 5 routes from 4 providers, it costs $2.04 per 1M input tokens and $10.20 per 1M output tokens.
Claude Sonnet 5 is available through 5 routes from 4 providers: Anthropic, Bedrock, Perplexity, and OpenRouter.
Claude Sonnet 5 accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "anthropic/claude-sonnet-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Claude Sonnet 5 scores 48.0 out of 100 on the Respan Index v1.1, ranking #48 of 176 models. By category: Coding 32.9, Agents 62.2, Reasoning 50.6, Knowledge & language 34.1, and Human preference 54.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Claude Sonnet 5 has 32 published benchmark scores, including SWE-bench Verified 85.2%, Toolathlon-Verified 71.6%, and GPQA Diamond 90.5%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.