All Models
| Model | Model ID | Input Cost | Output Cost | Context | Max Output | Capabilities |
|---|---|---|---|---|---|---|
| KB Whisper whisper | KBLab/kb-whisper-large | $0.0024/MTok | $0.0024/MTok | 448 | 448 | Open |
| Voxtral Small 24B voxtral | mistralai/Voxtral-Small-24B-2507 | $0.0024/MTok | $0.0024/MTok | 32K | 32K | Open |
| Whisper 3 Large whisper | openai/whisper-large-v3 | $0.0024/MTok | $0.0024/MTok | 448 | 4.1K | Open |
| E5 Multi-Lingual Large Embeddings 0.6B text-embedding | intfloat/multilingual-e5-large-instruct | $0.12/MTok | $0.12/MTok | 512 | 512 | Open |
| Qwen3 Embedding 8B text-embedding | Qwen/Qwen3-Embedding-8B | $0.12/MTok | $0.12/MTok | 41.0K | 41.0K | Open |
| Devstral Small 2 24B Instruct 2512 devstral | mistralai/devstral-small-2-24b-instruct-2512 | $0.12/MTok | $0.47/MTok | 32.8K | 32.8K | Tools Open |
| Phi-4 15B phi | microsoft/Phi-4-multimodal-instruct | $0.24/MTok | $0.47/MTok | 32K | 32K | Open |
| Qwen3 VL 30B qwen | Qwen/Qwen3-VL-30B-A3B-Instruct | $0.24/MTok | $0.94/MTok | 100K | 100K | Tools Open |
| GPT OSS 120B gpt-oss | openai/gpt-oss-120b | $0.24/MTok | $0.94/MTok | 65.5K | 65.5K | Reasoning Tools Open |
| Qwen3 30B 2507 qwen | Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 | $0.35/MTok | $1.42/MTok | 64K | 64K | Tools Open |
| Magistral Small 1.2 24B magistral-small | mistralai/Magistral-Small-2509 | $0.59/MTok | $2.36/MTok | 131.1K | 131.1K | Open |
| Llama 3.3 70B llama | nvidia/Llama-3.3-70B-Instruct-FP8 | $1.18/MTok | $1.18/MTok | 131.1K | 32.8K | Open |
| Kimi K2.5 kimi | moonshotai/Kimi-K2.5 | $1.47/MTok | $5.90/MTok | 262.1K | 262.1K | Reasoning Tools Open |