Reka AI: Models and Prices
Model lab that also serves other labs’ open-weight models.
Reka AI served 280B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #30 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | 2.3% | 117B | $0.021 | $0.528 | 102 | 98.6% | 262K |
| GLM 5.3 Flash | GLM | 1.0% | 115B | $0.06 | $1.60 | 87 | 99.3% | 262K |
| Qwen3.8 27B | Qwen | 4.4% | 25B | $0.14 | $1.40 | 62 | 98.7% | 262K |
| GLM 5.3 | GLM | 0.6% | 18B | $0.14 | $4.20 | 63 | 98.2% | 1.05M |
| DeepSeek V4 Pro 0423 | DeepSeek | 0.6% | 4B | $1.05 | $10.50 | 38 | 92.5% | 1.05M |
| Qwen3.6 27B | Qwen | 2.3% | 89M | $0.29 | $2.50 | 75 | 99.6% | 262K |
| Reka Flash 3 | Other open-weight | 100.0% | 39M | $0.10 | $0.20 | 94 | 83.3% | 66K |
| Reka Edge | Other open-weight | 100.0% | 15M | $0.10 | $0.10 | 97 | 100.0% | 16K |
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
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