1,050,000-token context window
Processes up to 922,000 input tokens and generates up to 128,000 output tokens from text and image inputs with per-token billing.

Handles demanding multistep engineering, complex codebase changes, and screenshot-led web design.
By OpenAI

Processes up to 922,000 input tokens and generates up to 128,000 output tokens from text and image inputs with per-token billing.
Supports web search, file search, computer use, and an optional multi-agent beta for coordinating multistep workflows.
Accepts screenshots alongside code or prose and returns text or schema-validated structured outputs.
OpenAI standard API, up to 272,000 input tokens: USD $8 per million uncached input tokens and $40 per million output tokens. Above 272,000 input tokens: USD $16 per million uncached input tokens and $60 per million output tokens for the entire request.
Use gpt-6.2-astra to call this model.
Vals AI reports 63.13% on Terminal-Bench 4.0 with the Mini-SWE-agent harness. The score applies to that evaluated setup. Source: https://www.vals.ai/benchmarks/terminal-bench-4
Public experiences and discussions, with links to the originals.
No discussions collected yet.
Explore 11 products that share at least one second-level category.
View all 11 alternativesFound something incorrect? Suggest a correction for our editors. It’s free; no account or email is needed.