| Spec | Kimi K3.1 Pro | Kimi K3 |
|---|---|---|
| Lowest input | $2.00Nebius | $0.60Wafer |
| Lowest output | $10.00Nebius | $9.50Chutes |
| Lowest cached input | $0.20Nebius | $0.185Chutes |
| Context | 1.05M | 1.05M |
| Max output | 524K | 524K |
| Providers | 5 | 10 |
| Released | October 24, 2026 | July 16, 2026 |
| Weights | Open | Open |
| Lab | Moonshot AI | Moonshot AI |
| Model ID | moonshotai/kimi-k3.1-pro | moonshotai/kimi-k3 |
USD per 1M tokens, as of November 5, 2026.
| Provider | Kimi K3.1 Pro | Kimi K3 |
|---|---|---|
| Doubleword | $2.00 / $10.00 | $3.00 / $15.00 |
| Inference.net | $2.00 / $10.00 | $3.00 / $15.00 |
| Nebius | $2.00 / $10.00 | $3.00 / $15.00 |
| Novita AI | $2.00 / $10.00 | $3.00 / $15.00 |
| Wafer | $2.00 / $10.00 | $0.60 / $15.00 |
| Chutes | – | $1.85 / $9.50 |
| DeepInfra | – | $2.85 / $14.25 |
| Morph | – | $2.50 / $14.00 |
| Phala | – | $3.00 / $15.00 |
| Sail Research | – | $1.50 / $10.00 |
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 |
|---|---|---|---|
| Kimi K3.1 ProNebius | $9.00 | $150.00 | $1,500.00 |
| Kimi K3Chutes | $8.45 | $140.00 | $1,400.00 |
On each model's cheapest provider by input plus output list price.
Input: Kimi K3 at $0.60 per million input tokens vs $2.00 (Kimi K3.1 Pro), 3.3x lower. Output: Kimi K3 at $9.50 per million output tokens vs $10.00 (Kimi K3.1 Pro), 5% lower. Lowest listed prices as of November 5, 2026.
Both list 1.05M tokens of context.
5 providers serve both: Nebius, Novita AI, Inference.net, Doubleword, Wafer. Kimi K3.1 Pro has 5 providers in total and Kimi K3 has 10.
Kimi K3.1 Pro from $0.20 per million cached input tokens (Nebius). 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 "moonshotai/kimi-k3.1-pro" to "moonshotai/kimi-k3".
