What's new
Models joining the catalogue, new coverage of ones we already knew, and changes to the reference offering.
| When | Model | Price | What | From | To | Change |
|---|---|---|---|---|---|---|
Google: Gemini 2.5 FlashGoogle | Input (priority) | added | — | 0.54 | — | |
Google: Gemini 2.5 FlashGoogle | Input (flex) | added | — | 0.15 | — | |
Google: Gemini 2.5 FlashGoogle | Input (batch) | added | — | 0.15 | — | |
Google: Gemini 2.5 FlashGoogle | Input (cached read, priority) | added | — | 0.054 | — | |
Google: Gemini 2.5 FlashGoogle | Input (cached read, flex) | added | — | 0.03 | — | |
Google: Gemini 2.5 FlashGoogle | Input (audio, cached read) | added | — | 0.1 | — | |
Gemini-2.0-Flash-LiteGoogle | Output (batch) | added | — | 0.15 | — | |
Gemini-2.0-Flash-LiteGoogle | Input (batch) | added | — | 0.0375 | — | |
Gemini-2.0-Flash-LiteGoogle | Input (characters) | added | — | 0.000019 | — | |
Gemini-2.0-FlashGoogle | Output (batch) | added | — | 0.3 | — | |
Gemini-2.0-FlashGoogle | Input (batch) | added | — | 0.075 | — | |
Gemini-2.0-FlashGoogle | Input (characters) | added | — | 0.000038 | — | |
OpenAI: gpt-oss-120bOpenAI | Output (priority) | added | — | 0.72 | — | |
OpenAI: gpt-oss-120bOpenAI | Input (priority) | added | — | 0.18 | — | |
OpenAI: gpt-oss-120bOpenAI | Input (cached read, priority) | added | — | 0.018 | — | |
OpenAI: gpt-oss-120bOpenAI | Output (priority) | added | — | 0.72 | — | |
OpenAI: gpt-oss-120bOpenAI | Input (priority) | added | — | 0.18 | — | |
OpenAI: gpt-oss-120bOpenAI | Input (cached read, priority) | added | — | 0.018 | — | |
davinci-002OpenAI | Output (batch) | added | — | 1 | — | |
davinci-002OpenAI | Input (batch) | added | — | 1 | — | |
| Compute | added | — | 0.0001 | — | ||
babbage-002OpenAI | Output (batch) | added | — | 0.2 | — | |
babbage-002OpenAI | Input (batch) | added | — | 0.2 | — | |
Mistral: Mistral Large 4Mistral AI | Input (cached read) | added | — | 0.07 | — | |
Mistral: Mistral Large 4Mistral AI | Output | added | — | 2.09 | — |