OpenAI Python SDK v3.53.0 adds GPT-6.2 Astra, Astra Law and Sol identifiers
OpenAI Python SDK v3.53.0, dated 2026-11-17, adds model identifiers for GPT-6.2 Astra, GPT-6.2 Astra Law and GPT-6.2 Sol. It also adds 2-hour and 8-hour Responses background windows.
OpenAI Python SDK v3.53.0, dated 2026-11-17, adds model identifiers for GPT-6.2 Astra, GPT-6.2 Astra Law and GPT-6.2 Sol, along with 2-hour and 8-hour Responses background windows.
What changed in v3.53.0
The release notes list four features, all under the api scope:
- Add 2-hour and 8-hour Responses background windows.
- Add the GPT-6.2 Astra Law Responses model identifier.
- Add the GPT-6.2 Astra model identifier.
- Add the GPT-6.2 Sol model identifier.
All four entries point to the same commit (720bcb5). The full diff is available in the GitHub comparison between v3.52.0 and v3.53.0.
Details
Context window size, pricing per 1M tokens, benchmark scores and parameter counts for the GPT-6.2 identifiers are not yet disclosed in the release notes. The notes also do not describe how the new background windows are configured.
The release is published in the openai/openai-python repository on GitHub.
What this means
Developers using the OpenAI Python SDK can see three new GPT-6.2 model identifiers in the v3.53.0 release: Astra, Astra Law and Sol. The Astra Law entry is described specifically as a Responses model identifier. The 2-hour and 8-hour background windows are new additions to the Responses API in the same release.
Related Articles
OpenAI releases GPT-6.2 Sol with 1.1M context at $2 input, $10 output per 1M tokens
OpenAI released GPT-6.2 Sol on November 17, 2026, an upgrade to GPT-6.1 Sol with a 1.1M-token context window. It is priced at $2 per 1M input tokens and $10 per 1M output tokens, and it is not currently available through EU in-region routing.
OpenAI Reports Up to 14% PPA Gain on AMD Flagship GPU IP From Model-Rewritten RTL
OpenAI reported on November 18, 2026 that its models achieved up to a 14% improvement in power, performance and area (PPA) on AMD flagship GPU intellectual property, measured against heavily optimized baselines. Some of the circuit rewrites were included in a design sent for manufacturing.
OpenAI models optimized circuits used in Jalapeño silicon and improved RISC-V core designs
OpenAI reports that its models optimized circuits used in Jalapeño silicon and improved RISC-V core designs. The company presents the work as progress in AI-assisted chip design with GPT-6 Astra.
iOS 27.3 adds daily usage limits to advanced Siri AI requests; basic requests stay unlimited
Apple's iOS 27.3 introduces usage limits for advanced Siri AI tasks, and basic requests are not limited. A leaker has published the criteria Siri AI uses to classify a request as advanced, while Apple has shared only two examples.
Comments
Loading...