OpenAI
GPT-6.2 Astra Law
Astra for Law pairs GPT-6.2 Astra with a legal search index covering US precedential case law. It can find relevant authorities and compare their reasoning.
Model interface
API model ID
gpt-6.2-astra-law- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Best for
- Find US cases addressing a specific legal question
- Compare conflicting holdings for a research memo
Technical details
Read the model documentation- API model ID
gpt-6.2-astra-law- Provider
- OpenAI
- Modality
- Text
- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Request parameters
audioresponse_formatmax_completion_tokensstreamtemperaturetools
Additional parameters
extra_headersfrequency_penaltyfunction_callfunctionslogit_biaslogprobsmax_retriesmax_tokensmodalitiesnparallel_tool_callspredictionpresence_penaltyprompt_cache_keyprompt_cache_retentionsafety_identifierseedservice_tierstopstorestream_optionstool_choicetop_logprobstop_puserweb_search_options
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per 1M input tokens | |
| Base rate | $9.60 |
| prompts over 272,000 tokens | $19.20 |
| Per 1M output tokens | |
| Base rate | $48.00 |
| prompts over 272,000 tokens | $72.00 |
| Per 1M cached input tokens | |
| Base rate | $0.48 |
| prompts over 272,000 tokens | $0.96 |
| Per 1M cache-write tokens | |
| Base rate | $12.00 |
| prompts over 272,000 tokens | $24.00 |
| 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