| Spec | Kimi K3 | Kimi K2.6 |
|---|---|---|
| Lowest input | $0.60Wafer | $0.39Chutes |
| Lowest output | $9.50Chutes | $1.80Chutes |
| Lowest cached input | $0.185Chutes | $0.039Chutes |
| Context | 1.05M | 262K |
| Max output | 524K | 262K |
| Providers | 10 | 5 |
| Released | July 16, 2026 | April 20, 2026 |
| Weights | Open | Open |
| Lab | Moonshot AI | Moonshot AI |
| Model ID | moonshotai/kimi-k3 | moonshotai/kimi-k2.6 |
USD per 1M tokens, as of November 5, 2026.
| Provider | Kimi K3 | Kimi K2.6 |
|---|---|---|
| Chutes | $1.85 / $9.50 | $0.39 / $1.80 |
| Inference.net | $3.00 / $15.00 | $1.25 / $5.30 |
| Nebius | $3.00 / $15.00 | $0.95 / $4.00 |
| Phala | $3.00 / $15.00 | $1.09 / $4.60 |
| DeepInfra | $2.85 / $14.25 | – |
| Doubleword | $3.00 / $15.00 | – |
| Morph | $2.50 / $14.00 | – |
| Novita AI | $3.00 / $15.00 | – |
| Sail Research | $1.50 / $10.00 | – |
| StreamLake | – | $0.95 / $4.00 |
| Wafer | $0.60 / $15.00 | – |
Input / output, USD per 1M tokens.
Input: Kimi K2.6 at $0.39 per million input tokens vs $0.60 (Kimi K3), 54% lower. Output: Kimi K2.6 at $1.80 per million output tokens vs $9.50 (Kimi K3), 5.3x lower. Lowest listed prices as of November 5, 2026.
Kimi K3, with 1.05M tokens vs 262K.
4 providers serve both: Nebius, Inference.net, Chutes, Phala. Kimi K3 has 10 providers in total and Kimi K2.6 has 5.
Kimi K3 from $0.185 per million cached input tokens (Chutes). Kimi K2.6 from $0.039 (Chutes).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "moonshotai/kimi-k3" to "moonshotai/kimi-k2.6".
