Friendli: Models and Prices
Inference engine and serverless endpoints for open-weight models.
Friendli served 350B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #26 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 | 2.3% | 254B | $0.15 | $0.50 | 128 | 99.0% | 1.05M |
| Gemma 4 31B | Gemma | 11.3% | 48B | $0.14 | $0.40 | 105 | 98.4% | 262K |
| DeepSeek V3.2 | DeepSeek | 7.8% | 22B | $0.50 | $1.50 | 47 | 100.0% | 164K |
| GLM 5.2 | GLM | 0.8% | 12B | $1.40 | $4.40 | 115 | 99.2% | 1.05M |
| GLM 5.3 | GLM | 0.3% | 10B | $1.26 | $3.96 | 110 | 99.8% | 1.05M |
| GLM 5.1 | GLM | 30.4% | 3B | $1.40 | $4.40 | 128 | 100.0% | 203K |
| MiniMax M2.5 | MiniMax | 17.3% | 603M | $0.30 | $1.20 | 177 | 100.0% | 197K |
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
- friendli.ai
- Headquarters
- United States
- Latest financing
- $20M seed extension led by Capstone Partners (August 2025).
- Status page
- status.friendli.ai
Sources: FriendliAI.
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