# GPT-6 Astra

`gpt-6-astra` · OpenAI · text

GPT-6 Astra applies adjustable reasoning to technical problems that combine text and images, including mathematical arguments and engineering designs.

[Model page](https://sociaro.com/models/gpt-6-astra) · [JSON](https://sociaro.com/models/gpt-6-astra.json) · [Model pricing](https://sociaro.com/pricing?model=gpt-6-astra) · [Documentation](https://docs.sociaro.com/models/gpt-6-astra/)

## Use cases

- Check the steps in a mathematical proof
- Compare an engineering drawing with its written specification

## Technical details

- API model ID — gpt-6-astra
- Provider — OpenAI
- Modality — Text
- Input — Chat messages
- Output — Text
- Endpoint — POST /v1/chat/completions
- API constraints — Function calling and sampling parameters are not available on Chat Completions for this model.

## Request parameters

- `messages`
- `max_completion_tokens`
- `stream`
- `stream_options`
- `reasoning_effort`
- `response_format`
- `service_tier`
- `store`
- `safety_identifier`
- `prompt_cache_key`
- `user`

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 12 per 1M input tokens · active
- USD 24 per 1M input tokens · prompts over 272,000 tokens · active
- USD 24 per 1M input tokens · priority (service_tier: priority) · active
- USD 48 per 1M input tokens · prompts over 272,000 tokens, priority (service_tier: priority) · active
- USD 6 per 1M input tokens · flex (service_tier: flex) · active
- USD 12 per 1M input tokens · prompts over 272,000 tokens, flex (service_tier: flex) · active
- USD 60 per 1M output tokens · active
- USD 90 per 1M output tokens · prompts over 272,000 tokens · active
- USD 120 per 1M output tokens · priority (service_tier: priority) · active
- USD 180 per 1M output tokens · prompts over 272,000 tokens, priority (service_tier: priority) · active
- USD 30 per 1M output tokens · flex (service_tier: flex) · active
- USD 45 per 1M output tokens · prompts over 272,000 tokens, flex (service_tier: flex) · active
- USD 1.2 per 1M cached input tokens · active
- USD 2.4 per 1M cached input tokens · prompts over 272,000 tokens · active
- USD 2.4 per 1M cached input tokens · priority (service_tier: priority) · active
- USD 4.8 per 1M cached input tokens · prompts over 272,000 tokens, priority (service_tier: priority) · active
- USD 0.6 per 1M cached input tokens · flex (service_tier: flex) · active
- USD 1.2 per 1M cached input tokens · prompts over 272,000 tokens, flex (service_tier: flex) · active
- USD 15 per 1M cache-write tokens · active
- USD 30 per 1M cache-write tokens · prompts over 272,000 tokens · active
- USD 30 per 1M cache-write tokens · priority (service_tier: priority) · active
- USD 60 per 1M cache-write tokens · prompts over 272,000 tokens, priority (service_tier: priority) · active
- USD 7.5 per 1M cache-write tokens · flex (service_tier: flex) · active
- USD 15 per 1M cache-write tokens · prompts over 272,000 tokens, flex (service_tier: flex) · active
- USD 12 per 1K responses that search the web · active

- A prompt over 272,000 tokens bills the whole request at the long-context rates.
