| Spec | Kimi K3.1 Pro | DeepSeek V4 Pro |
|---|---|---|
| Lowest input | $2.00Nebius | $1.30DeepInfra |
| Lowest output | $10.00Nebius | $2.60DeepInfra |
| Lowest cached input | $0.20Nebius | $0.0036Inference.net |
| Context | 1.05M | 1.05M |
| Max output | 524K | 524K |
| Providers | 5 | 4 |
| Released | October 24, 2026 | April 24, 2026 |
| Weights | Open | Open |
| Lab | Moonshot AI | DeepSeek |
| Model ID | moonshotai/kimi-k3.1-pro | deepseek/deepseek-v4-pro |
USD per 1M tokens, as of November 5, 2026.
| Provider | Kimi K3.1 Pro | DeepSeek V4 Pro |
|---|---|---|
| Inference.net | $2.00 / $10.00 | $2.10 / $4.20 |
| Novita AI | $2.00 / $10.00 | $1.60 / $3.20 |
| DeepInfra | – | $1.30 / $2.60 |
| Doubleword | $2.00 / $10.00 | – |
| Nebius | $2.00 / $10.00 | – |
| StreamLake | – | $1.74 / $3.48 |
| Wafer | $2.00 / $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 |
| DeepSeek V4 ProDeepInfra | $3.90 | $78.00 | $780.00 |
On each model's cheapest provider by input plus output list price.
Input: DeepSeek V4 Pro at $1.30 per million input tokens vs $2.00 (Kimi K3.1 Pro), 54% lower. Output: DeepSeek V4 Pro at $2.60 per million output tokens vs $10.00 (Kimi K3.1 Pro), 3.8x lower. Lowest listed prices as of November 5, 2026.
Both list 1.05M tokens of context.
2 providers serve both: Novita AI, Inference.net. Kimi K3.1 Pro has 5 providers in total and DeepSeek V4 Pro has 4.
Kimi K3.1 Pro from $0.20 per million cached input tokens (Nebius). DeepSeek V4 Pro from $0.0036 (Inference.net).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "moonshotai/kimi-k3.1-pro" to "deepseek/deepseek-v4-pro".
