# Claude Sonnet 5

Claude Sonnet 5 is a text generation model from Anthropic, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $2.00 per million input tokens. The advertised output rate is $10.00 per million output tokens.

- Model identifier: ` anthropic/claude-sonnet-5 `
- Creator: Anthropic
- Model type: Text generation
- Canonical model page: [Claude Sonnet 5](<https://impossibl.com/anthropic/claude-sonnet-5>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-06-30

## Capabilities and limits

- Context window: 1,000,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` anthropic/claude-sonnet-5 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $2.00 | per million input tokens |
| Output | $10.00 | per million output tokens |
| Cache read | $0.20 | per million cached input tokens |
| Cache write (default retention) | $2.50 | per million tokens |
| Cache write (one-hour retention) | $4.00 | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T10:50:14.034Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 38.36 |
| Omniscience Index | 16.45 |
| GPQA | 91.11% |
| Humanity’s Last Exam | 41.29% |
| SciCode | 54.28% |
| CritPt | 16.86% |
| Terminal-Bench v2.1 | 80.52% |
| Terminal-Bench v4.0 | 14.14% |
| AA-LCR | 82.00% |
| Multilingual LCR | 55.00% |
| Harvey LAB | 90.07% |
| GDPval Elo | 1500.86 |
| GDP.pdf All-pass | 13.20% |
| AutomationBench Partial | 36.51% |
| AnalystAgent | 46.25% |
| MMMU-Pro | 77.28% |
| Tau Banking | 37.32% |
| coding index (API) | 71.5 |
| agentic index (API) | 44.3 |
| intelligence index (API) | 38.4 |

### Claude Sonnet 5 (Adaptive Reasoning, High Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5-high>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 32.03 |
| Omniscience Index | -3.68 |
| Humanity’s Last Exam | 35.73% |
| SciCode | 54.28% |
| CritPt | 15.14% |
| Terminal-Bench v4.0 | 5.05% |
| AA-LCR | 76.67% |
| GDPval Elo | 1308.45 |
| GDP.pdf All-pass | 9.40% |
| AutomationBench Partial | 32.10% |
| intelligence index (API) | 32 |

### Claude Sonnet 5 (Adaptive Reasoning, Low Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5-low>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 24.74 |
| Omniscience Index | -8.23 |
| Humanity’s Last Exam | 21.92% |
| SciCode | 50.12% |
| CritPt | 4.57% |
| Terminal-Bench v4.0 | 2.53% |
| AA-LCR | 67.33% |
| GDPval Elo | 1145.04 |
| GDP.pdf All-pass | 9.40% |
| AutomationBench Partial | 19.90% |
| intelligence index (API) | 24.7 |

### Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5-medium>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 28.44 |
| Omniscience Index | -6.87 |
| Humanity’s Last Exam | 29.98% |
| SciCode | 51.62% |
| CritPt | 8.57% |
| Terminal-Bench v4.0 | 2.02% |
| AA-LCR | 73.67% |
| GDPval Elo | 1222.52 |
| GDP.pdf All-pass | 11.60% |
| AutomationBench Partial | 27.87% |
| intelligence index (API) | 28.4 |

### Claude Sonnet 5 (Non-reasoning, High Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 28.94 |
| Omniscience Index | -0.65 |
| GPQA | 80.00% |
| Humanity’s Last Exam | 19.05% |
| CritPt | 1.14% |
| Terminal-Bench v2.1 | 75.28% |
| AA-LCR | 70.00% |
| GDPval Elo | 1283.47 |
| MMMU-Pro | 71.91% |
| Tau Banking | 15.67% |
| coding index (API) | 66.4 |
| intelligence index (API) | 28.9 |

### Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-sonnet-5-xhigh>)

| Benchmark | Score |
| --- | --- |
| Omniscience Index | 3.18 |
| Humanity’s Last Exam | 39.02% |
| SciCode | 54.05% |
| Terminal-Bench v4.0 | 7.07% |
| AA-LCR | 76.67% |
| GDPval Elo | 1410.49 |
| GDP.pdf All-pass | 12.60% |
| AutomationBench Partial | 34.48% |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/anthropic/claude-sonnet-5/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Claude Sonnet 5?

Claude Sonnet 5 is a text-generation model from Anthropic, available through the Impossibl API.

### How much does Claude Sonnet 5 cost?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens through the Impossibl API. Cache reads cost $0.20 per million tokens; cache writes cost $2.50 per million tokens; cache writes with one-hour retention cost $4.00 per million tokens. All rates are in USD.

### What is the context length of Claude Sonnet 5?

Claude Sonnet 5 has a 1,000,000-token context window through the Impossibl API.

### What inputs and outputs does Claude Sonnet 5 support?

Claude Sonnet 5 accepts text and image as input. Claude Sonnet 5 returns text.

### How do I use Claude Sonnet 5 through an API?

Claude Sonnet 5 is available through the Impossibl API. Use anthropic/claude-sonnet-5 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Claude Sonnet 5 released?

Anthropic released Claude Sonnet 5 on June 30, 2026.

Sources: [Creator release announcement](<https://www.anthropic.com/news/claude-sonnet-5>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Claude Sonnet 5: model details and pricing](<https://impossibl.com/anthropic/claude-sonnet-5>)
- [Model directory](<https://impossibl.com/models>)