Skip to content

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 IDgpt-6-astra
Input
Chat messages
Output
Text
Endpoint
POST /v1/chat/completions

Best for

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

  • messages
  • response_format
  • max_completion_tokens
  • stream
  • prompt_cache_key

Additional parameters

  • reasoning_effort
  • safety_identifier
  • service_tier
  • store
  • stream_options
  • user

Pricing

Billable unit and optionsRate (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