Prime Intellect: Models and Prices
Compute, training and inference stack for custom models: on-demand GPUs and dedicated clusters, agent and reinforcement-learning training tools, and an OpenAI-compatible inference API.
Prime Intellect served 1.39T tokens of other labs' open-weight models over Nov 2 to Nov 8, 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 |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | DeepSeek | 0.8% | 460B | $0.044 | $0.70 | 65 | 100.0% | 1.05M |
| DeepSeek V4.1 Flash | DeepSeek | 1.9% | 331B | $0.039 | $1.20 | 98 | 99.6% | 1.05M |
| GLM 5.3 Flash | GLM | 2.4% | 323B | $0.052 | $0.25 | 93.5 | 99.7% | 1.05M |
| GLM 5.3 | GLM | 3.0% | 107B | $0.40 | $2.46 | 58 | 99.9% | 1.05M |
| Nemotron 3.5 Super VL | Nemotron | 1.1% | 43B | $0.15 | $0.50 | 162 | 100.0% | 1.05M |
| DeepSeek V4 Flash 0731 | DeepSeek | 1.0% | 32B | $0.44 | $1.32 | 141 | 99.4% | 1.05M |
| Gemma 4 26B A4B | Gemma | 10.7% | 31B | $0.063 | $0.188 | 44 | 100.0% | 262K |
| Qwen3.5-9B | Qwen | 37.2% | 30B | $0.068 | $0.101 | 64 | 99.8% | 262K |
| gpt-oss-120b | gpt-oss | 8.4% | 22B | $0.042 | $0.091 | 72 | 100.0% | 131K |
| Gemma 4 31B | Gemma | 1.0% | 4B | $0.40 | $0.67 | 48 | 99.1% | 262K |
| gpt-oss-20b | gpt-oss | 2.9% | 3B | $0.02 | $0.03 | 121 | 100.0% | 131K |
| Qwen3.8 27B | Qwen | - | - | $0.049 | $0.348 | 29 | 97.9% | 262K |
| Qwen3.6 35B A3B | Qwen | - | - | $0.011 | $0.101 | 55 | 99.9% | 262K |
| Moondream 3.1 | Other open-weight | - | - | $0.30 | $2.50 | 172.5 | 100.0% | 32K |
| Moondream 3 Preview | Other open-weight | - | - | $0.30 | $2.50 | 230 | 100.0% | 32K |
List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- primeintellect.ai
- Compute
- Rents on-demand GPUs (1 to 256 by the hour) and dedicated clusters operated by its team; its terms say it also uses third-party infrastructure providers.
- Latest financing
- $130M Series A led by Radical Ventures at a $1B valuation, with NVIDIA Ventures, Intel Capital and Dell Technologies Capital (July 2026).
Sources: Prime Intellect, Prime Intellect, Prime Intellect, TechCrunch, Intel Capital.
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