Baseten: Models and Prices
Inference platform for dedicated and shared model deployments.
Baseten served 598B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #19 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 | 1.8% | 202B | $0.15 | $0.50 | 122 | 99.1% | 1.05M |
| DeepSeek V4.1 Flash | DeepSeek | 0.4% | 148B | $0.30 | $1.20 | 207.5 | 100.0% | 1.05M |
| GLM 5.3 | GLM | 3.7% | 123B | $1.40 | $4.40 | 66 | 99.8% | 1.05M |
| DeepSeek V4 Flash 0731 | DeepSeek | 0.9% | 45B | $0.13 | $0.26 | 177 | 100.0% | 1.05M |
| GLM 5.2 | GLM | 2.3% | 35B | $1.40 | $4.40 | 84 | 100.0% | 1.05M |
| Kimi K3 | Kimi | 1.0% | 20B | $3.00 | $15.00 | 27 | 100.0% | 1.05M |
| gpt-oss-120b | gpt-oss | 3.2% | 13B | $0.10 | $0.50 | 184 | 100.0% | 128K |
| Nemotron 3 Ultra | Nemotron | 0.2% | 12B | $0.60 | $2.40 | 103 | 100.0% | 203K |
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
- baseten.co
- Headquarters
- San Francisco, CA
- Latest financing
- $300M Series E at a $5B valuation co-led by IVP and CapitalG (early 2026); a larger round was reported in June 2026.
- Status page
- status.baseten.co
Sources: Lets Data Science.
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