Open Inference: Models and Prices
Inference API for open-weight models.
Open Inference served 759B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #18 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| GLM 5.3 Flash | GLM | 4.2% | 467B | $0.044 | $0.45 | 23 | 99.6% | 1.05M |
| DeepSeek V4.1 Flash | DeepSeek | 0.5% | 193B | $0.0028 | $0.36 | 26 | 90.0% | 1.05M |
| DeepSeek V4 Flash 0423 | DeepSeek | 1.8% | 54B | $0.012 | $1.15 | 24 | 98.0% | 1.05M |
| DeepSeek V4 Flash 0731 | DeepSeek | 0.9% | 45B | $0.0069 | $0.27 | 19 | 99.2% | 1.05M |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- openinference.xyz
- Headquarters
- United States
Sources: Open Inference.
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com