Kimi K3.1 Pro pricing & specs
Moonshot AI · released 2026-10-23 · ● verified 2026-11-21
Kimi K3.1 Pro is a Moonshot AI model released on 2026-10-23. At $2.00 per million input tokens and $10.00 per million output tokens, its blended price of $4.00 per 1M tokens is lower than 19% of the 186 models we track. It offers text, image and video input, a 1.05M-token context window, built-in reasoning, tool calling and structured output. Its weights are open, and it is available from 7 tracked hosting providers.
Ranked #5 of 6 in Cheapest Kimi Models and #10 of 20 in Newest AI Models.
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Kimi K3.1 Pro |
|---|---|---|---|---|
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −98.6% |
| Qwen3.5 Flash | $0.10 | $0.40 | 1M | −95.6% |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | −95.6% |
| Muse Ember | $0.10 | $0.50 | 1.05M | −95% |
| Qwen3.8 Flash | $0.15 | $0.47 | 1M | −94.2% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Baseten | $2.00 | $10.00 |
| DeepInfra | $2.00 | $10.00 |
| Fireworks AI | $2.00 | $10.00 |
| Nebius | $2.00 | $10.00 |
| Novita AI | $2.00 | $10.00 |
| Together AI | $2.00 | $10.00 |
| Amazon Bedrock | $4.00 | $20.00 |
// embed this price badge
Show the live price of Kimi K3.1 Pro in your README or docs (updated daily):
[](https://aisignals.dev/models/moonshotai/kimi-k3.1-pro)
// faq
How much does Kimi K3.1 Pro cost?
Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens. At 50M input and 10M output tokens per month that is about $200.
What is the context window of Kimi K3.1 Pro?
1.05M tokens, with up to 1.05M output tokens per request.
Does Kimi K3.1 Pro support prompt caching?
Yes. Cached input tokens cost $0.20 per million and cache writes cost $2.00 per million.
What are cheaper alternatives to Kimi K3.1 Pro?
Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen3.5 Flash ($0.10 in / $0.40 out), Gemini 2.5 Flash-Lite ($0.10 in / $0.40 out) offer the same input types and capabilities for less.
Is Kimi K3.1 Pro open weights?
Yes. It is available from 7 tracked hosts; the cheapest is Baseten at $2.00 input and $10.00 output per million tokens.
// spec sheet
- input / 1M
- $2.00
- output / 1M
- $10.00
- cache read / 1M
- $0.20
- cache write / 1M
- $2.00
- blended (3:1)
- $4.00
- context
- 1.05M
- max output
- 1.05M
- input types
- text · image · video
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Moonshot AI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $9.00 |
| Qwen3.5 Flash | $0.10 | $0.40 | $9.00 |
| Kimi K3.1 Pro | $2.00 | $10.00 | $200 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.