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 |
|---|---|---|---|---|---|---|
| Input (image tokens) | added | — | 1 | — | ||
| Input (image tokens) | added | — | 1 | — | ||
| Input (image tokens) | added | — | 1 | — | ||
| Input (image tokens) | added | — | 2 | — | ||
| Input (image tokens) | added | — | 2 | — | ||
| Input (image tokens) | added | — | 2 | — | ||
| Input (image tokens) | added | — | 1.25 | — | ||
baseten/openai/gpt-oss-120bbaseten | Input (cached read) | added | — | 0.1 | — | |
baseten/zai-org/GLM-4.7baseten | Input (cached read) | added | — | 0.12 | — | |
| Input (image tokens) | added | — | 1.25 | — | ||
| Input (image tokens) | added | — | 1.25 | — | ||
| Input (image tokens) | added | — | 1.25 | — | ||
| Output | added | — | 1.01 | — | ||
| Input | added | — | 0.23 | — | ||
GLM 5.3 FP4coralbricks | Input (cache write) | added | — | 1.68 | — | |
GLM 5.3 Flash FP4coralbricks | Input (cache write) | added | — | 0.23 | — | |
Qwen3.5 Flashqwen | Output (reasoning) | added | — | 1.15 | — | |
Qwen3.5 Flashqwen | Output (>128k ctx) | added | — | 1.15 | — | |
Qwen3.5 Flashqwen | Input (>128k ctx) | added | — | 0.115 | — | |
GPT OSS 120Bgreenpt | Input (cache write) | added | — | 0.18 | — | |
| Input (cached read) | new coverage | 0.4 | 0.4 | 0% | ||
| Query | added | — | 0.005 | — | ||
| Output | new coverage | 4.8 | 4.8 | 0% | ||
| Input | new coverage | 1.6 | 1.6 | 0% | ||
Xiaomi: MiMo-V2.6-ProXiaomi | Input (cached read) | new coverage | 0.0036 | 0.0036 | 0% |