# Cheapest Kimi K3.1 Pro API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/kimi-k3-1-pro

> ernd partners with [Wafer](https://ernd.ai/partners/wafer). Prices are from OpenRouter's public listings.

Kimi K3.1 Pro is an open-weight model from Moonshot AI. On OpenRouter, 24 listings from 17 providers sell it, and the blended price runs from $2.27 to $8.00 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput | With ernd card |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Relace | $0.40 | $7.88 | $2.27 | $0.20 | 1.05M | FP4 | 1.33 s | 65 tok/s | – |
| Sail Research (US) | $1.10 | $10.00 | $3.33 | $0.20 | 1.05M | FP4 | 3.31 s | 50 tok/s | – |
| inference.net | $1.80 | $9.00 | $3.60 | $0.18 | 1.05M | MXFP4 | 0.96 s | 72 tok/s | – |
| inference.net (US) | $1.80 | $9.00 | $3.60 | $0.18 | 1.05M | MXFP4 | 1.03 s | 69 tok/s | – |
| PrimaLabs | $1.80 | $9.00 | $3.60 | $0.18 | 1.05M | MXFP4 | 1.62 s | 70 tok/s | – |
| Wafer, ernd partner | $1.80 | $9.00 | $3.60 | $0.18 | 1.05M | MXFP4 | 1.10 s | 68 tok/s | $3.24 after 10% cash back |
| Sail Research | $1.50 | $10.00 | $3.63 | $0.20 | 1.05M | FP4 | 2.67 s | 55 tok/s | – |
| DeepInfra | $1.90 | $9.50 | $3.80 | $0.19 | 1.05M | BF16 | 11.8 s | 23 tok/s | – |
| AkashML | $1.75 | $10.00 | $3.81 | $0.18 | 1.05M | FP4 | 1.79 s | 63 tok/s | – |
| DigitalOcean | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | Not listed | 1.17 s | 96 tok/s | – |
| Fireworks | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | Not listed | 1.84 s | 50 tok/s | – |
| Modal | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | MXFP4 | 0.80 s | 102 tok/s | – |
| Moonshot AI | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | MXFP4 | 5.57 s | 25 tok/s | – |
| Nebius Token Factory | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | FP4 | 2.95 s | 60 tok/s | – |
| Parasail | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | FP4 | 1.33 s | 65 tok/s | – |
| Phala | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | Not listed | 2.71 s | 51 tok/s | – |
| Phala (US) | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | Not listed | 1.41 s | 61 tok/s | – |
| Together | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | Not listed | 1.22 s | 49 tok/s | – |
| Wafer (US), ernd partner | $2.00 | $10.00 | $4.00 | $0.20 | 1.05M | MXFP4 | 0.91 s | 66 tok/s | $3.60 after 10% cash back |
| Morph | $1.91 | $12.00 | $4.43 | $0.47 | 1.05M | FP8 | 1.61 s | 64 tok/s | – |
| Alibaba Cloud Int. | $2.30 | $11.50 | $4.60 | $0.23 | 1.05M | Not listed | 2.40 s | 39 tok/s | – |
| inference.net (Fast) | $3.00 | $15.00 | $6.00 | $0.30 | 1.05M | MXFP4 | 0.90 s | 96 tok/s | – |
| inference.net (US, Fast) | $3.00 | $15.00 | $6.00 | $0.30 | 1.05M | MXFP4 | 1.24 s | 84 tok/s | – |
| Moonshot AI (Highspeed) | $4.00 | $20.00 | $8.00 | $0.20 | 1.05M | MXFP4 | 3.96 s | 52 tok/s | – |

Blended is three parts input price to one part output, per million tokens. Latency is time to first token and throughput is output tokens per second, both averaged from OpenRouter's daily figures for the last 7 days. Cheapest and fastest only count listings that were up when checked.

Wafer is an ernd partner: 10% back on Wafer inference with the ernd card. With ernd card is the blended price less 10% cash back on Wafer charges. It comes back on the card bill and doesn't change Wafer's list price. It applies when you pay Wafer directly, not through OpenRouter credits.

## Questions

### What is the cheapest Kimi K3.1 Pro API provider?

Relace, at $2.27 per million tokens blended ($0.40 input, $7.88 output), in OpenRouter's listings on November 7, 2026.

### How much does Kimi K3.1 Pro cost per million tokens?

Input runs from $0.40 to $4.00 per million tokens across 24 listings, and output from $7.88 to $20.00. The middle listing comes to $4.00 blended.

### Which Kimi K3.1 Pro provider is fastest?

Modal led on both counts over the last 7 days, at about 102 tokens per second and 0.80 s to the first token.

### How do I pay for Kimi K3.1 Pro inference?

Buy OpenRouter credits and it sends each request to one of these providers, or open an account with a provider and pay it directly. The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. Wafer charges on the card earn 10% back.

Source: OpenRouter public model and provider listings (https://openrouter.ai/models), checked November 7, 2026.

The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. [Request the card at app.ernd.ai](https://app.ernd.ai/login?next=%2Fapp%2Fcard%2Fapply&utm_source=llms&utm_campaign=inference_prices).