| Spec | MiniMax M3 | Kimi K3 |
|---|---|---|
| Lowest input | $0.28DeepInfra | $0.60Wafer |
| Lowest output | $1.10DeepInfra | $9.50Chutes |
| Lowest cached input | $0.056DeepInfra | $0.185Chutes |
| Context | 524K | 1.05M |
| Max output | 131K | 524K |
| Providers | 3 | 10 |
| Released | June 1, 2026 | July 16, 2026 |
| Weights | Open | Open |
| Lab | MiniMax | Moonshot AI |
| Model ID | minimax/minimax-m3 | moonshotai/kimi-k3 |
USD per 1M tokens, as of November 5, 2026.
| Provider | MiniMax M3 | Kimi K3 |
|---|---|---|
| DeepInfra | $0.28 / $1.10 | $2.85 / $14.25 |
| Nebius | $0.30 / $1.20 | $3.00 / $15.00 |
| Chutes | – | $1.85 / $9.50 |
| Doubleword | – | $3.00 / $15.00 |
| Inference.net | – | $3.00 / $15.00 |
| Morph | – | $2.50 / $14.00 |
| Novita AI | – | $3.00 / $15.00 |
| Phala | – | $3.00 / $15.00 |
| Sail Research | – | $1.50 / $10.00 |
| StreamLake | $0.60 / $2.40 | – |
| Wafer | – | $0.60 / $15.00 |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| MiniMax M3DeepInfra | $1.11 | $19.50 | $195.00 |
| Kimi K3Chutes | $8.45 | $140.00 | $1,400.00 |
On each model's cheapest provider by input plus output list price.
Input: MiniMax M3 at $0.28 per million input tokens vs $0.60 (Kimi K3), 2.1x lower. Output: MiniMax M3 at $1.10 per million output tokens vs $9.50 (Kimi K3), 8.6x lower. Lowest listed prices as of November 5, 2026.
Kimi K3, with 1.05M tokens vs 524K.
2 providers serve both: DeepInfra, Nebius. MiniMax M3 has 3 providers in total and Kimi K3 has 10.
MiniMax M3 from $0.056 per million cached input tokens (DeepInfra). Kimi K3 from $0.185 (Chutes).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "minimax/minimax-m3" to "moonshotai/kimi-k3".
