01 What happened
OpenAI has published API details for GPT-6.1 Sol in its developer documentation. According to the company, the model accepts up to 1,050,000 input tokens, returns up to 128,000 output tokens and has an April 30, 2026 knowledge cutoff. Prices are $2 per million input tokens and $10 per million output tokens, with higher rates for requests above 272K input tokens.
02 Key details
- Per 1M text tokens, OpenAI lists $2.00 for input, $0.10 for cached input, $2.50 for cache writes and $10.00 for output. Above 272K input tokens, input and cache rates double and output rises to 1.5x for the full request.
- According to OpenAI, Fast mode costs 2x Standard and Ultrafast costs 6x Standard. Batch and Flex are 50% lower than Standard. Regional processing adds a 10% premium where available.
- Tool calling requires the Responses API; Chat Completions is supported without tool calling. reasoning.effort supports low, medium (default), high, xhigh and max; none and minimal are not supported.
- Rate limits depend on usage tier: Free is not supported; Build is 5,000 RPM and 1,000,000 TPM; Launch is 10,000 RPM and 4,000,000 TPM; Grow is 15,000 RPM and 40,000,000 TPM.
03 Why it matters
Teams planning costs and capacity need to weigh several factors together: context length, service mode, region and usage tier each affect price or throughput. These are terms from OpenAI's documentation; the source material includes no independent evaluation of the model's performance.
04 Who it matters to
Software developers and engineering teams.