# GPT-5.2

GPT-5.2 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 $1.75 per million input tokens. The advertised output rate is $14.00 per million output tokens.

- Model identifier: ` openai/gpt-5.2 `
- Creator: OpenAI
- Model type: Text generation
- Canonical model page: [GPT-5.2](<https://impossibl.com/openai/gpt-5.2>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2025-12-11

## 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-5.2 ` 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 An unpublished rate is unknown, not zero.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 | $1.75 | per million input tokens |
| Output | $14.00 | per million output tokens |
| Cache read | $0.175 | 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-5.2 (xhigh)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-2>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 30.45 |
| Omniscience Index | -0.88 |
| GPQA | 90.30% |
| Humanity’s Last Exam | 37.67% |
| CritPt | 11.55% |
| Terminal-Bench Hard | 46.97% |
| AA-LCR | 82.67% |
| IFBench | 75.44% |
| Tau2 | 84.80% |
| LiveCodeBench | 88.89% |
| AIME 2025 | 99.00% |
| intelligence index (API) | 30.4 |

### GPT-5.2 (medium)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-2-medium>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 26.50 |
| Omniscience Index | 0.27 |
| GPQA | 86.36% |
| Humanity’s Last Exam | 26.69% |
| CritPt | 7.86% |
| Terminal-Bench Hard | 43.18% |
| AA-LCR | 70.33% |
| MMMU-Pro | 74.57% |
| IFBench | 65.24% |
| Tau2 | 74.27% |
| LiveCodeBench | 89.42% |
| AIME 2025 | 96.67% |
| intelligence index (API) | 26.5 |

### GPT-5.2 (Non-reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-2-non-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 16.98 |
| Omniscience Index | -12.25 |
| GPQA | 71.21% |
| Humanity’s Last Exam | 8.02% |
| CritPt | 0.57% |
| Terminal-Bench Hard | 31.82% |
| AA-LCR | 45.67% |
| MMMU-Pro | 65.84% |
| IFBench | 47.41% |
| Tau2 | 46.49% |
| Tau Banking | 11.13% |
| LiveCodeBench | 66.88% |
| AIME 2025 | 51.00% |
| intelligence index (API) | 17 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/openai/gpt-5.2/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-5.2?

GPT-5.2 is a text-generation model from OpenAI, available through the Impossibl API.

### How much does GPT-5.2 cost?

GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens through the Impossibl API. Cache reads cost $0.175 per million tokens. All rates are in USD.

### What is the context length of GPT-5.2?

GPT-5.2 has a 400,000-token context window through the Impossibl API.

### What inputs and outputs does GPT-5.2 support?

GPT-5.2 accepts text and image as input. GPT-5.2 returns text.

### How do I use GPT-5.2 through an API?

GPT-5.2 is available through the Impossibl API. Use openai/gpt-5.2 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-5.2 released?

OpenAI released GPT-5.2 on December 11, 2025.

Sources: [Creator release announcement](<https://openai.com/index/introducing-gpt-5-2/>)

## 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-5.2: model details and pricing](<https://impossibl.com/openai/gpt-5.2>)
- [Model directory](<https://impossibl.com/models>)
