| Inkling (Together AI) | together-ai | 524,288 | - Input
- Input (cached read)
- Output
|
| GPT OSS 20B (Together AI) | together-ai | 131,072 | |
| GPT OSS 120B (Together AI) | together-ai | 131,072 | |
| Llama-3.3-70B-Instruct (IONOS) | ionos | 128,000 | |
| GPT OSS 120B (IONOS) | ionos | 131,072 | |
| Qwen3 Coder 30B | qwen | 262,144 | |
| Lynkr Auto (complexity routing) | lynkr | 128,000 | |
| Meta-Llama-3.1-405B-Instruct | avian | — | |
| Meta-Llama-3.1-70B-Instruct | avian | — | |
| Meta-Llama-3.1-8B-Instruct | avian | — | |
| Meta-Llama-3.3-70B-Instruct | avian | — | |
| Nova 2 Sonic | aws | — | - Input
- Input (audio)
- Output
- Output (audio)
|
| Nova Lite | aws | — | - Input
- Input (cached read)
- Output
|
| Nova Micro | aws | — | - Input
- Input (cached read)
$0.00875 per 1M tokens low- Output
|
| Nova Premier | aws | — | - Input
- Input (cached read)
- Output
|
| Nova Pro | aws | — | - Input
- Input (cached read)
- Output
|
| Nova Sonic | aws | — | - Input
- Input (audio)
- Output
- Output (audio)
|
| Titan Embeddings G1 - Text | aws | — | |
| Titan Text G1 - Express | aws | — | |
| Titan Text G1 - Lite | aws | — | |
| DeepSeek-R1 | aws | — | |
| Gemma 3 12B IT | aws | — | |
| Gemma 3 27B IT | aws | — | |
| Gemma 3 4B IT | aws | — | |
| Llama 3.1 70B Instruct | aws | — | |