Models
Open-weight models, wholesale prices.
We run the best open-weight models at scale at the most competitive prices — text, vision, and embeddings. All accessible through one OpenAI-compatible API.
Need a model we don't list yet? New models added within 24 hours on request.
Full pricing
Model-by-model breakdown
| Model | SLA | Input $/MTok | Output $/MTok | Cost / 1B in+out | vs Big Token | |
|---|---|---|---|---|---|---|
| DeepSeek-V4-ProNew | High throughput API | $1.31 | $2.75 | $4.1K | 86% cheaper | Try Model API |
| ↳ | Batch | $1.05 | $2.20 | $3.3K | 89% cheaper | |
| DeepSeek-V4-FlashNew | High throughput API | $0.10 | $0.20 | $300 | 89% cheaper | Try Model API |
| ↳ | Batch | $0.07 | $0.14 | $210 | 93% cheaper | |
| Kimi-K2.6New | High throughput API | $0.70 | $3.00 | $3.7K | 79% cheaper | Try Model API |
| ↳ | Batch | $0.45 | $2.00 | $2.5K | 86% cheaper | |
| GLM-5.2-FP8New | High throughput API | $1.05 | $3.30 | $4.3K | 76% cheaper | Try Model API |
| ↳ | Batch | $0.70 | $2.20 | $2.9K | 84% cheaper | |
| GLM-5.1-FP8 | High throughput API | $1.05 | $3.30 | $4.3K | 76% cheaper | Try Model API |
| ↳ | Batch | $0.70 | $2.20 | $2.9K | 84% cheaper | |
| Qwen3.5-397B-A17B | High throughput API | $0.30 | $1.80 | $2.1K | 93% cheaper | Try Model API |
| ↳ | Batch | $0.15 | $1.20 | $1.3K | 96% cheaper | |
| Qwen3.6-35B-A3B-FP8New | High throughput API | $0.07 | $0.30 | $370 | 98% cheaper | Try Model API |
| ↳ | Batch | $0.05 | $0.20 | $250 | 99% cheaper | |
| Qwen3.5-35B-A3B-FP8 | High throughput API | $0.07 | $0.30 | $370 | 94% cheaper | Try Model API |
| ↳ | Batch | $0.05 | $0.20 | $250 | 96% cheaper | |
| Qwen3.5-4B | High throughput API | $0.05 | $0.08 | $130 | 99% cheaper | Try Model API |
| ↳ | Batch | $0.04 | $0.06 | $100 | 99% cheaper | |
| Qwen3.5-9B | High throughput API | $0.04 | $0.35 | $390 | 94% cheaper | Try Model API |
| ↳ | Batch | $0.03 | $0.29 | $320 | 95% cheaper | |
| Gemma-4-31BNew | High throughput API | $0.11 | $0.30 | $410 | 93% cheaper | Try Model API |
| ↳ | Batch | $0.07 | $0.20 | $270 | 96% cheaper | |
| Nemotron-3-Ultra-550B-A55BNew | High throughput API | $0.37 | $1.87 | $2.2K | 93% cheaper | Try Model API |
| ↳ | Batch | $0.25 | $1.25 | $1.5K | 95% cheaper | |
| Nemotron-3-Super-120B-A12B | High throughput API | $0.23 | $0.56 | $790 | 87% cheaper | Try Model API |
| ↳ | Batch | $0.15 | $0.38 | $530 | 91% cheaper | |
| GPT-OSS-20B | High throughput API | $0.03 | $0.20 | $230 | 98% cheaper | Try Model API |
| ↳ | Batch | $0.02 | $0.15 | $170 | 98% cheaper | |
| Qwen3-VL-235B-A22B | High throughput API | $0.15 | $0.55 | $700 | 69% cheaper | Try Model API |
| ↳ | Batch | $0.10 | $0.40 | $500 | 78% cheaper | |
| Qwen3-VL-30B-A3B | High throughput API | $0.07 | $0.30 | $370 | 75% cheaper | Try Model API |
| ↳ | Batch | $0.05 | $0.20 | $250 | 83% cheaper | |
| Qwen3-14B-FP8 | High throughput API | $0.03 | $0.30 | $330 | 78% cheaper | Try Model API |
| ↳ | Batch | $0.02 | $0.20 | $220 | 85% cheaper | |
| DeepSeek-OCR-2OCR | High throughput API | $0.08 | $0.08 | $160 | — | Try Model API |
| ↳ | Batch | $0.05 | $0.05 | $100 | — | |
| olmOCR-2-7BOCR | High throughput API | $0.15 | $0.15 | $300 | — | Try Model API |
| ↳ | Batch | $0.10 | $0.10 | $200 | — | |
| LightOnOCR-2-1BOCR | High throughput API | $0.08 | $0.08 | $160 | — | Try Model API |
| ↳ | Batch | $0.05 | $0.05 | $100 | — | |
| Qwen3-Embedding-8B | High throughput API | $0.03 | — | $30 | — | Try Model API |
| ↳ | Batch | $0.02 | — | $20 | — |