inference.net: Models and Prices
OpenAI-compatible API for open-weight models plus custom model training and deployment for enterprises. Formerly Kuzco.
inference.net served 4.13T tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #4 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | 6.8% | 2.56T | $0.105 | $0.60 | 97 | 100.0% | 1.04M |
| Kimi K3 | Kimi | 29.7% | 571B | $0.64 | $13.50 | 67 | 100.0% | 1.05M |
| GLM 5.3 Flash | GLM | 4.5% | 505B | $0.07 | $0.50 | 83 | 99.8% | 1.05M |
| GLM 5.3 | GLM | 8.8% | 291B | $0.08 | $4.40 | 108 | 100.0% | 1.05M |
| GLM 5.2 | GLM | 10.4% | 159B | $0.18 | $4.40 | 68 | 100.0% | 1.05M |
| Schematron V2 Turbo | Other open-weight | 100.0% | 194M | $0.03 | $0.15 | 76 | 99.0% | 128K |
| Schematron V2 Small | Other open-weight | 100.0% | 67M | $0.05 | $0.23 | 32 | 100.0% | 128K |
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
- inference.net
- Headquarters
- United States
- Latest financing
- $11.8M seed led by Multicoin Capital and a16z CSX (October 2025).
- Status page
- status.inference.net
Sources: Techleap.
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