| Spec | Kimi K3 | Kimi K3 Fast |
|---|---|---|
| Lowest input | $0.60Wafer | $4.50Inference.net |
| Lowest output | $9.50Chutes | $22.50Inference.net |
| Lowest cached input | $0.185Chutes | $0.45Inference.net |
| Context | 1.05M | 1.05M |
| Max output | 524K | 1.05M |
| Providers | 10 | 1 |
| Released | July 16, 2026 | July 16, 2026 |
| Weights | Open | Open |
| Lab | Moonshot AI | Moonshot AI |
| Model ID | moonshotai/kimi-k3 | moonshotai/kimi-k3-fast |
USD per 1M tokens, as of November 5, 2026.
| Provider | Kimi K3 | Kimi K3 Fast |
|---|---|---|
| Inference.net | $3.00 / $15.00 | $4.50 / $22.50 |
| Chutes | $1.85 / $9.50 | – |
| DeepInfra | $2.85 / $14.25 | – |
| Doubleword | $3.00 / $15.00 | – |
| Morph | $2.50 / $14.00 | – |
| Nebius | $3.00 / $15.00 | – |
| Novita AI | $3.00 / $15.00 | – |
| Phala | $3.00 / $15.00 | – |
| Sail Research | $1.50 / $10.00 | – |
| 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 |
|---|---|---|---|
| Kimi K3Chutes | $8.45 | $140.00 | $1,400.00 |
| Kimi K3 FastInference.net | $20.25 | $337.50 | $3,375.00 |
On each model's cheapest provider by input plus output list price.
Input: Kimi K3 at $0.60 per million input tokens vs $4.50 (Kimi K3 Fast), 7.5x lower. Output: Kimi K3 at $9.50 per million output tokens vs $22.50 (Kimi K3 Fast), 2.4x lower. Lowest listed prices as of November 5, 2026.
Both list 1.05M tokens of context.
1 provider serves both: Inference.net. Kimi K3 has 10 providers in total and Kimi K3 Fast has 1.
Kimi K3 from $0.185 per million cached input tokens (Chutes). Kimi K3 Fast from $0.45 (Inference.net).
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-k3-fast".
