# GPT-5

GPT-5 is a text generation model from OpenAI, available through the Impossibl API. Its published context window is 400,000 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $10.00 per million output tokens.

- Model identifier: ` openai/gpt-5 `
- Creator: OpenAI
- Model type: Text generation
- Canonical model page: [GPT-5](<https://impossibl.com/openai/gpt-5>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2025-08-07

## Capabilities and limits

- Context window: 400,000 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 ` openai/gpt-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 An unpublished rate is unknown, not zero.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 | $1.25 | per million input tokens |
| Output | $10.00 | per million output tokens |
| Cache read | $0.125 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-10T09:58:54.927Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### GPT-5 (high)

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

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 22.98 |
| Omniscience Index | -8.73 |
| GPQA | 85.35% |
| Humanity’s Last Exam | 28.50% |
| CritPt | 5.71% |
| Terminal-Bench v2.1 | 35.21% |
| Terminal-Bench Hard | 32.58% |
| AA-LCR | 78.20% |
| GDPval Elo | 1014.92 |
| MMMU-Pro | 74.22% |
| IFBench | 73.06% |
| Tau2 | 84.80% |
| Tau Banking | 22.06% |
| LiveCodeBench | 84.55% |
| AIME 2025 | 94.33% |
| coding index (API) | 37.8 |
| intelligence index (API) | 23 |

### GPT-5 (low)

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

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 20.79 |
| Omniscience Index | -10.78 |
| GPQA | 80.81% |
| Humanity’s Last Exam | 19.56% |
| CritPt | 1.14% |
| Terminal-Bench Hard | 26.52% |
| MMMU-Pro | 73.76% |
| IFBench | 66.60% |
| Tau2 | 84.21% |
| LiveCodeBench | 76.30% |
| AIME 2025 | 83.00% |
| intelligence index (API) | 20.8 |

### GPT-5 (medium)

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

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 22.87 |
| Omniscience Index | -10.87 |
| GPQA | 84.18% |
| Humanity’s Last Exam | 25.39% |
| CritPt | 0.00% |
| Terminal-Bench Hard | 37.88% |
| AA-LCR | 76.00% |
| MMMU-Pro | 74.34% |
| IFBench | 70.61% |
| Tau2 | 86.55% |
| LiveCodeBench | 70.26% |
| AIME 2025 | 91.67% |
| intelligence index (API) | 22.9 |

### GPT-5 (minimal)

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

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 11.45 |
| Omniscience Index | -33.80 |
| GPQA | 67.27% |
| Humanity’s Last Exam | 6.02% |
| CritPt | 0.00% |
| Terminal-Bench Hard | 18.18% |
| MMMU-Pro | 62.08% |
| IFBench | 45.58% |
| Tau2 | 66.96% |
| LiveCodeBench | 55.77% |
| AIME 2025 | 31.67% |
| intelligence index (API) | 11.4 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/openai/gpt-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 GPT-5?

GPT-5 is a text-generation model from OpenAI, available through the Impossibl API.

### How much does GPT-5 cost?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens through the Impossibl API. Cache reads cost $0.125 per million tokens. All rates are in USD.

### What is the context length of GPT-5?

GPT-5 has a 400,000-token context window through the Impossibl API.

### What inputs and outputs does GPT-5 support?

GPT-5 accepts text and image as input. GPT-5 returns text.

### How do I use GPT-5 through an API?

GPT-5 is available through the Impossibl API. Use openai/gpt-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 GPT-5 released?

OpenAI released GPT-5 on August 7, 2025.

Sources: [Creator release announcement](<https://openai.com/index/introducing-gpt-5-for-developers/>)

## 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>)
- [GPT-5: model details and pricing](<https://impossibl.com/openai/gpt-5>)
- [Model directory](<https://impossibl.com/models>)