OpenAI
GPT-6 Astra
GPT-6 Astra applies adjustable reasoning to technical problems that combine text and images, including mathematical arguments and engineering designs.
Model interface
API model ID
gpt-6-astra- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Best for
- Check the steps in a mathematical proof
- Compare an engineering drawing with its written specification
Technical details
Read the model documentation- 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
messagesresponse_formatmax_completion_tokensstreamprompt_cache_key
Additional parameters
reasoning_effortsafety_identifierservice_tierstorestream_optionsuser
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per 1M input tokens | |
| Base rate | $12.00 |
| prompts over 272,000 tokens | $24.00 |
| priority (service_tier: priority) | $24.00 |
| prompts over 272,000 tokens, priority (service_tier: priority) | $48.00 |
| flex (service_tier: flex) | $6.00 |
| prompts over 272,000 tokens, flex (service_tier: flex) | $12.00 |
| Per 1M output tokens | |
| Base rate | $60.00 |
| prompts over 272,000 tokens | $90.00 |
| priority (service_tier: priority) | $120.00 |
| prompts over 272,000 tokens, priority (service_tier: priority) | $180.00 |
| flex (service_tier: flex) | $30.00 |
| prompts over 272,000 tokens, flex (service_tier: flex) | $45.00 |
| Per 1M cached input tokens | |
| Base rate | $1.20 |
| prompts over 272,000 tokens | $2.40 |
| priority (service_tier: priority) | $2.40 |
| prompts over 272,000 tokens, priority (service_tier: priority) | $4.80 |
| flex (service_tier: flex) | $0.60 |
| prompts over 272,000 tokens, flex (service_tier: flex) | $1.20 |
| Per 1M cache-write tokens | |
| Base rate | $15.00 |
| prompts over 272,000 tokens | $30.00 |
| priority (service_tier: priority) | $30.00 |
| prompts over 272,000 tokens, priority (service_tier: priority) | $60.00 |
| flex (service_tier: flex) | $7.50 |
| prompts over 272,000 tokens, flex (service_tier: flex) | $15.00 |
| Per 1K responses that search the web | $12.00 |
Billing notes
- A prompt over 272,000 tokens bills the whole request at the long-context rates.
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue