Public model catalog
Select one type tab. Search and pagination apply only to that type.
Language
text / multimodal
Language Models
Token-priced text and multimodal-capable language models.
| Model | Slug | Capability | Context Window | Input Price | Output Price | Image Price | Web Search |
|---|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | google/gemini-2.5-pro | Multimodal input | 1,048,576 tokens | $3.25 / 1M | $19.50 / 1M | — | $45.50 / 1K |
| Gemini 3 Flash | google/gemini-3-flash | Multimodal input | 1,000,000 tokens | $0.6500 / 1M | $3.90 / 1M | — | $18.20 / 1K |
| Gemini 3 Pro Preview | google/gemini-3-pro-preview | Multimodal input | 1,000,000 tokens | $5.20 / 1M | $23.40 / 1M | — | $18.20 / 1K |
| Gemini 3.1 Flash Image Preview (Nano Banana 2) | google/gemini-3.1-flash-image-preview | Text + image generation | 131,072 tokens | $0.6500 / 1M | $3.90 / 1M | — | $18.20 / 1K |
| Gemini 3.1 Flash Lite Preview | google/gemini-3.1-flash-lite-preview | Multimodal input | 1,000,000 tokens | $0.3250 / 1M | $1.95 / 1M | — | $18.20 / 1K |
| Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | Multimodal input | 1,000,000 tokens | $5.20 / 1M | $23.40 / 1M | — | $18.20 / 1K |
| Gemma 4 26B A4B IT | google/gemma-4-26b-a4b-it | Multimodal input | 262,144 tokens | $0.1690 / 1M | $0.5200 / 1M | — | — |
| Gemma 4 31B IT | google/gemma-4-31b-it | Multimodal input | 262,144 tokens | $0.1820 / 1M | $0.5200 / 1M | — | — |
| Grok 3 Beta | xai/grok-3 | Text-only | 131,072 tokens | $3.90 / 1M | $19.50 / 1M | — | — |
| Grok 3 Fast Beta | xai/grok-3-fast | Text-only | 131,072 tokens | $6.50 / 1M | $32.50 / 1M | — | — |
| Grok 3 Mini Beta | xai/grok-3-mini | Text-only | 131,072 tokens | $0.3900 / 1M | $0.6500 / 1M | — | — |
| Grok 3 Mini Fast Beta | xai/grok-3-mini-fast | Text-only | 131,072 tokens | $0.7800 / 1M | $5.20 / 1M | — | — |
Note: listed costs are approximate upper-tier reference rates across providers. Final billing depends on the provider route used for each request and may be lower or higher. Routes are selected automatically to prioritize availability and lower cost.