Makora: Models and Prices
AI agent that writes and tunes GPU kernels, and serves models with them.
Makora served 414B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #25 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 | 0.7% | 259B | $0.27 | $1.15 | 134 | 99.9% | 1.05M |
| GLM 5.3 | GLM | 1.7% | 57B | $0.14 | $4.40 | 107 | 98.5% | 1.05M |
| MiMo-V2.6-Flash | MiMo | 0.4% | 47B | $0.13 | $0.28 | 69 | 99.0% | 1.05M |
| Gemma 4 26B A4B | Gemma | 12.9% | 34B | $0.08 | $0.32 | 212 | 99.9% | 256K |
| Kimi K3 | Kimi | 0.9% | 17B | $1.53 | $12.75 | 47 | 98.7% | 1.05M |
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
- makora.com
- Headquarters
- New York, NY
- Latest financing
- $8.5M+ seed led by M13 (August 2025).
- Status page
- makora.statuspage.io
Sources: M13.
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