GPT-6.1 Sol
GPT-6.1 SolRankingat max effort?
Full ranking →Alternatives?
CheaperClaude Haiku 5.5xhigh-7%-83%$0.12Context: 1.05M → 1M+6BetterClaude Opus 5.5medium+16%+84%$1.34Context: 1.05M → 1M+6
OpenMiMo v2.6 Prothinking-8%-82%$0.13Context: 1.05M → 1M+4
CheaperDeepSeek V4.1 Flash 1017maxOpen-11%-64%$0.26Context: 1.05M → 1M+5CheaperMiMo v2.6 FlashthinkingOpen-14%-91%$0.062Context: 1.05M → 1M+4Claude Haiku 5.5xhigh-7%-83%$0.12Context: 1.05M → 1M+6MiMo v2.6 ProthinkingOpen-8%-82%$0.13Context: 1.05M → 1M+4DeepSeek V4.1 Flash 1017maxOpen-11%-64%$0.26Context: 1.05M → 1M+5Claude Opus 5.5low-13%-24%$0.55Context: 1.05M → 1M+6MiMo v2.6 FlashthinkingOpen-14%-91%$0.062Context: 1.05M → 1M+4Claude Opus 5.5medium+16%+84%$1.34Context: 1.05M → 1M+6MiMo v2.6 ProthinkingOpen-8%-82%$0.13Context: 1.05M → 1M+4DeepSeek V4.1 Flash 1017maxOpen-11%-64%$0.26Context: 1.05M → 1M+5
Kimi K3maxOpen-11%+176%$2.00Context: 1.05M → 1M+4MiMo v2.6 FlashthinkingOpen-14%-91%$0.062Context: 1.05M → 1M+4
GLM 5.3 FlashmaxOpen-17%-61%$0.28Context: 1.05M → 1M+5GPT-6 Astramax-4%+350%$3.26Monitoring can return HTTP 403+2GPT-6 Lunamax-15%-91%$0.068Function calling only with none · Chat Completions+3GPT-6 Solmediumn/a—$0.25GPT-5.6 Lunamediumn/a—$0.016GPT-5.6 Solmediumn/a—$0.50GPT-5.6 Terramediumn/a—$0.18Prompts with >272K input tokensGPT-5.5 Instant (June 2026)n/a—$0.69Context: 1.05M → 400KGPT-5.5 Instant (May 2026)n/a——Context: 1.05M → 400KAll OpenAI models →Benchmarks
in CodingWatch out 6
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes. Source ↗
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling. Source ↗
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max. Source ↗
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request. Source ↗
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate. Source ↗
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices. Source ↗
FAQ
How much does GPT-6.1 Sol cost?›
$2 per 1M input tokens and $10 per 1M output tokens; cached input $0.10 per 1M. A typical benchmark task costs about $0.72 at max effort.
Is GPT-6.1 Sol free to use?›
There is no free API; the cheapest paid price is $2 per 1M input tokens.
How good is GPT-6.1 Sol, and what is it best at?›
#9 of 334 in Chat & Knowledge, #6 of 132 in Coding, #11 of 133 in Agents & Tool Use, #19 of 195 in Writing & Language, #3 of 124 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Reasoning, Long context, Knowledge, Vision.
Is GPT-6.1 Sol better than Claude Opus 5.5?›
On FrontierCode 1.1, GPT-6.1 Sol scores 49.1 vs 57.1 — lower. It is 46% cheaper per task.
How can I use GPT-6.1 Sol?›
Through the API of Amazon Bedrock, Azure, OpenAI.
What is the context window of GPT-6.1 Sol?›
1.05M tokens, with up to 128K output tokens.
When was GPT-6.1 Sol released? Is there a newer version?›
Released 2026-09-29. It is the current version in its line.
Is GPT-6.1 Sol open source?›
No, GPT-6.1 Sol is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-6.1 Sol read images?›
It accepts text and images, PDF files as input.
What is GPT-6.1 Sol?›
GPT-6.1 Sol is a closed language model from OpenAI, released Sep 2026, the successor to GPT-6 Sol.
What are the best alternatives to GPT-6.1 Sol?›
Claude Haiku 5.5 (cheaper), Claude Opus 5.5 (better), MiMo v2.6 Pro (open weights).