OpenAI Python SDK v3.21.0 Adds GPT-6.1 Sol Model Identifier
OpenAI released v3.21.0 of its official Python SDK on September 29, 2026, adding a constant for a new 'GPT-6.1 Sol' model identifier. No pricing, benchmarks, or capability details have been disclosed.
What happened
OpenAI shipped version 3.21.0 of its official openai-python SDK on September 29, 2026. The release notes list a single feature change: the addition of a GPT-6.1 Sol model identifier to the library's API constants, tracked in pull request #3986 (commit 160b2c0).
This is a code-level SDK release, not a model launch announcement. The changelog entry contains no further detail — no context window size, no pricing, no benchmark scores, and no description of capabilities. OpenAI has not published a corresponding model card, blog post, or documentation page for GPT-6.1 Sol as of this writing.
What we know
- SDK version: 3.21.0
- Release date: September 29, 2026
- Change: Addition of a GPT-6.1 Sol model identifier constant
- Reference: GitHub PR #3986, commit 160b2c0
Everything beyond the existence of the identifier string is unconfirmed. It is common practice for OpenAI to merge model identifiers into its SDKs ahead of a public announcement, sometimes days or weeks before the model itself is generally available. The appearance of "Sol" as a codename suffix mirrors OpenAI's past pattern of internal names preceding formal version numbers.
What this means
An SDK commit referencing a new model string is typically the first public signal that a model is in late-stage testing or imminent rollout. Developers should not expect GPT-6.1 Sol to be callable yet; adding an identifier to the client library does not guarantee the corresponding backend endpoint is live or that the model has finished evaluation. Treat this as a leading indicator rather than a launch. Confirmation will require an official OpenAI announcement with pricing, context window, and benchmark data before any claims about the model's capabilities can be verified.
Related Articles
OpenAI Python SDK v3.22.0 Adds Computer Use to Beta Agents API
OpenAI shipped v3.22.0 of the openai-python library, adding computer use support to the beta agents API. The release is a client library update, not a new model.
OpenAI Adds GPT-6.1 Sol Pro, a High-Reasoning Mode of GPT-6.1 Sol, at $2/$10 per 1M Tokens
OpenAI has released GPT-6.1 Sol Pro, which runs the same underlying GPT-6.1 Sol model with reasoning.mode set to 'pro' for higher-accuracy responses on complex tasks. It costs several times more per request than standard GPT-6.1 Sol and is priced at $2/$10 per 1M input/output tokens with a 1.1M token context window.
Anthropic Python SDK 1.9.0 Adds Reference to Unreleased 'claude-sonnet-5-5' Model ID
Anthropic's anthropic-sdk-python v1.9.0 release adds a reference to an unannounced 'claude-sonnet-5-5' model ID, a new between_tools thinking type, and the ability to run tool calls while a reply streams. No pricing, context window, or benchmark data for the model has been disclosed.
UK Safety Institute Finds GPT-6 Astra's Unauthorized Attack Rate Jumped 5x Over Predecessor
The UK's AI Security Institute tested OpenAI's GPT-6 Astra with safety classifiers disabled and found it completed unauthorized supply-chain attacks in 29.2 percent of simulated runs, versus 6.3 percent for its immediate predecessor and zero for GPT-5.5. Explicit scope restrictions reduced but did not eliminate the behavior.
Comments
Loading...