Moonshot AI · Model
Kimi K3.1 Pro API pricing, cost and context window
Kimi K3.1 Pro costs $2 per million input tokens and $10 per million output tokens. Cached input costs $0.20. It reads up to 1,048,576 tokens. Prices checked 2026-11-22. By blended price it is number 2 of Moonshot AI’s 3 current models here, counting from the cheapest.
- Input / 1M
- $2
- Output / 1M
- $10
- Cached / 1M
- $0.20
- Context
- 1,048,576
- Max output
- Not published
- Released
- 2026-10-23
Estimate your cost with Kimi K3.1 ProCompare all Moonshot AI modelsCount tokens for Kimi K3.1 Pro
Pricing
How much does Kimi K3.1 Pro cost per million tokens?
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $2 | $10 |
| Cached input (read) | $0.20 | – |
| Batch API | $0.70 | $6 |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price.
Work out your monthly Kimi K3.1 Pro bill in the cost calculatorSee what prompt caching savesSee what the Batch API saves
Examples
How much does a typical Kimi K3.1 Pro request cost?
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00565 | $171.85 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.0148 | $225.69 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0424 | $257.93 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.0092 | $83.95 |
Change any number in the cost calculator.
Context
What is Kimi K3.1 Pro’s context window and max output?
Kimi K3.1 Pro accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $2.10 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
What can Kimi K3.1 Pro do?
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text, image, video
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
What is the Kimi K3.1 Pro API model ID?
- OpenRouter
moonshotai/kimi-k3.1-pro- Open weights
- moonshotai/Kimi-K3.1-Pro
Use the OpenRouter ID when calling it through OpenRouter; Moonshot AI’s own API may name it differently. See the model ID reference for the providers we document.
Moonshot AI
Where does Kimi K3.1 Pro sit in Moonshot AI’s line-up?
Ranked by blended price (three parts input to one part output, $4 per 1M for Kimi K3.1 Pro), it is number 2 of Moonshot AI’s 3 current models here, counting from the cheapest. One step down, Kimi K2.7 Code costs $1.20 blended (70% less). Unlike Kimi K3.1 Pro, it doesn’t accept video and reads up to 262,144 tokens (1,048,576 here). One step up, Kimi K3 costs $6 (1.5× as much). It has the same published limits and features as Kimi K3.1 Pro. See every Moonshot AI model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Kimi K2.7 Code | $0.60 | $3 | 262,144 | 2026-06-12 |
| Kimi K3.1 Pro (this page) | $2 | $10 | 1,048,576 | 2026-10-23 |
| Kimi K3 | $3 | $15 | 1,048,576 | 2026-07-16 |
Moonshot AI’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
What are cheaper alternatives to Kimi K3.1 Pro?
- GLM 4.6VZ.ai89% cheaper
- DeepSeek V4.1 FlashDeepSeek87% cheaper
- MiniMax M3MiniMax87% cheaper
- Qwen3.7 PlusQwen86% cheaper
- Command A+Cohere85% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Which models cost about the same?
- GPT-6.2 SolOpenAI$2 / $10
- Claude Sonnet 5.5Anthropic$2 / $10
- Gemini 4 CarbonGoogle$2 / $10
- Pixtral Large 2502Mistral$2 / $6
- Qwen3.8 2.4T A95BQwen$2 / $6
Current models from other major providers, closest blended price.
FAQ
Kimi K3.1 Pro questions
How much does Kimi K3.1 Pro cost?
Kimi K3.1 Pro costs $2 per million input tokens and $10 per million output tokens, with cached input at $0.20. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.007. Use the LLM cost calculator for your own workload.
What is Kimi K3.1 Pro’s context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Kimi K3.1 Pro support prompt caching and batch requests?
Yes, cached input is billed at $0.20 per million tokens (10% of the normal input price). A batch API is available at $0.70 input and $6 output per million tokens.
What are cheaper alternatives to Kimi K3.1 Pro?
With the same essentials (image input and tool calling), the cheapest options are GLM 4.6V (89% cheaper), DeepSeek V4.1 Flash (87% cheaper), MiniMax M3 (87% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Kimi K3.1 Pro?
On OpenRouter it is moonshotai/kimi-k3.1-pro. Moonshot AI’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
When was Kimi K3.1 Pro released?
Kimi K3.1 Pro was first listed on 2026-10-23. It is the first model in its line in our data. Release dates here are when our price source first listed each model.
Is Kimi K3.1 Pro open source?
Yes, Kimi K3.1 Pro has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.
Keep exploring