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 |
|---|---|---|---|---|---|---|---|
| Nova Micro | amazon/nova-micro | Text-only | 128,000 tokens | $0.0455 / 1M | $0.1820 / 1M | — | — |
| Nova Pro | amazon/nova-pro | Text-only | 300,000 tokens | $1.04 / 1M | $4.16 / 1M | — | — |
| Nvidia Nemotron Nano 12B V2 VL | nvidia/nemotron-nano-12b-v2-vl | Multimodal input | 131,072 tokens | $0.2600 / 1M | $0.7800 / 1M | — | — |
| Nvidia Nemotron Nano 9B V2 | nvidia/nemotron-nano-9b-v2 | Text-only | 131,072 tokens | $0.0520 / 1M | $0.2080 / 1M | — | — |
| Pixtral 12B 2409 | mistral/pixtral-12b | Multimodal input | 128,000 tokens | $0.1950 / 1M | $0.1950 / 1M | — | — |
| Pixtral Large | mistral/pixtral-large | Multimodal input | 128,000 tokens | $2.60 / 1M | $7.80 / 1M | — | — |
| Qwen 3 32B | alibaba/qwen-3-32b | Text-only | 40,960 tokens | $0.1300 / 1M | $0.3900 / 1M | — | — |
| Qwen 3 Coder 30B A3B Instruct | alibaba/qwen3-coder-30b-a3b | Text-only | 160,000 tokens | $0.0910 / 1M | $0.3510 / 1M | — | — |
| Qwen 3 Max Thinking | alibaba/qwen3-max-thinking | Text-only | 256,000 tokens | $3.90 / 1M | $19.50 / 1M | — | — |
| Qwen 3.5 Flash | alibaba/qwen3.5-flash | Multimodal input | 1,000,000 tokens | $0.1625 / 1M | $0.5200 / 1M | — | — |
| Qwen 3.5 Plus | alibaba/qwen3.5-plus | Multimodal input | 1,000,000 tokens | $1.95 / 1M | $9.36 / 1M | — | — |
| Qwen3 235B A22B Thinking 2507 | alibaba/qwen3-235b-a22b-thinking | Multimodal input | 262,114 tokens | $0.3900 / 1M | $3.77 / 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.