OpenAI releases GPT-6.2 Astra and GPT-6.2 Sol, with no temperature, top_p or effort none (November 17, 2026)
New gpt-6.2-astra ($8/$40 per 1M) and gpt-6.2-sol ($2/$10). Remove temperature and top_p, and use Responses for tool calls.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. Your keys stay in this tab. They are never sent to Wirestack or saved; we only count that the panel was used.
- OpenAI API keyOPENAI_API_KEYGet key
Click Create new secret key
What changed
On November 17, 2026 OpenAI released two models. gpt-6.2-astra is for demanding reasoning and coding. gpt-6.2-sol is for everyday coding and agent workflows.
Both take text and image input and return text. Both have a 1,050,000-token context window, with at most 922,000 input tokens and 128,000 output tokens. They work on v1/responses, v1/chat/completions and v1/batch. Chat Completions works, but tool calling needs the Responses API.
Standard prices per 1M tokens:
| Model | Input | Cached input | Cache write (30 min) | 12-hour cache write | Output |
|---|---|---|---|---|---|
gpt-6.2-astra | $8 | $0.40 | $10 | $20 | $40 |
gpt-6.2-sol | $2 | $0.10 | $2.50 | $5 | $10 |
gpt-6-astra costs $10 input, $1 cached input, $12.50 cache write and $50 output, so moving to gpt-6.2-astra lowers each of those rates by 20% or more. Above 272K input tokens, input and cache rates double and output costs 1.5x for the whole request. Batch is 50% of Standard. Fast mode is 2x. Ultrafast is 3x through February 28, 2027 and 6x from March 1, 2027 (Pacific time).
Requests that worked on older models can now fail or behave differently:
- The API rejects reasoning effort
none. The migration guide says to move fromnoneorminimaltolow, and to start new integrations atmedium. - Remove
temperature,top_p,logprobsandtop_logprobsfrom Chat Completions requests. Removetemperature,top_pandtop_logprobsfrom Responses requests, and dropmessage.output_text.logprobsfrominclude.
