This browser is not keeping saved items, so they will be forgotten when you leave this page. Everything else still works.
Reference · AI provider
OpenAI
18 facts collected from their sources, each linked with its date. Nothing here is written from memory; a fact appears only as its source states it.
SDK releases
- OpenAI Python SDK v3.33.0 was released. OpenAI Python SDK releases,
- OpenAI Python SDK v3.32.0 was released. OpenAI Python SDK releases,
- OpenAI Python SDK v3.31.0 was released. OpenAI Python SDK releases,
- OpenAI Python SDK v3.30.0 was released. OpenAI Python SDK releases,
- OpenAI Python SDK v3.29.0 was released. OpenAI Python SDK releases,
- OpenAI Python SDK v3.28.0 was released. OpenAI Python SDK releases,
Prices
- gpt-4.1 at openai: $2 input and $8 output per million tokens (USD). LiteLLM model price map,
- gpt-4.1-mini at openai: $0.4 input and $1.6 output per million tokens (USD). LiteLLM model price map,
- gpt-4.1-nano at openai: $0.1 input and $0.4 output per million tokens (USD). LiteLLM model price map,
- gpt-4o-2024-08-06 at openai: $2.5 input and $10 output per million tokens (USD). LiteLLM model price map,
- gpt-4o-2024-11-20 at openai: $2.5 input and $10 output per million tokens (USD). LiteLLM model price map,
- gpt-4o-mini-2024-07-18 at openai: $0.15 input and $0.6 output per million tokens (USD). LiteLLM model price map,
Benchmark results
- gpt-5 (low): 81.3% (pass rate, second attempt) on Aider polyglot, 225 exercises. Aider polyglot leaderboard,
- gpt-5 (medium): 86.7% (pass rate, second attempt) on Aider polyglot, 225 exercises. Aider polyglot leaderboard,
- gpt-5 (high): 88% (pass rate, second attempt) on Aider polyglot, 225 exercises. Aider polyglot leaderboard,
- mini-SWE-agent with gpt-5-2025-08-07: 65% (resolved) on SWE-bench, Verified. SWE-bench leaderboard,
- mini-SWE-agent with gpt-5-mini-2025-08-07: 59.8% (resolved) on SWE-bench, Verified. SWE-bench leaderboard,
- mini-SWE-agent with gpt-5-nano-2025-08-07: 34.8% (resolved) on SWE-bench, Verified. SWE-bench leaderboard,