Kimi K2 Thinking
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 262 K tokens
- Max output
- 98 K
- Input, $ per 1M tokens
- $0.600
- Output, $ per 1M tokens
- $2.50
- Cache read, $ per 1M
- $0.150
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 11/06/2025
- Knowledge cutoff
- —
- API id
- moonshotai/kimi-k2-thinking
Summary from the data
Kimi K2 Thinking is a Moonshot model available by API since 11/06/2025. It costs $0.600 per million input tokens and $2.50 per million output tokens, accepts 262 K tokens of context and generates up to 98 K tokens per response. Input: text; output: text. It has a reasoning mode. It supports tool calling. With 10,000 requests a month of 1,500 input and 400 output tokens it would cost about $19.00 a month.
Compare Kimi K2 Thinking with…
- Kimi K2 Thinking vs Kimi K3
- Kimi K2 Thinking vs Kimi K2.7 Code
- Kimi K2 Thinking vs Kimi K2.6
- Kimi K2 Thinking vs Kimi K2.5
- Kimi K2 Thinking vs Claude Sonnet 5.5
- Kimi K2 Thinking vs DeepSeek V4.1 Flash
- Kimi K2 Thinking vs Gemini 3.8 Flash
- Kimi K2 Thinking vs Mistral Medium 3.5
- Kimi K2 Thinking vs GPT-6.1 Sol
- Kimi K2 Thinking vs Qwen3.8 Max Prime
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Frequently asked questions
How much does Kimi K2 Thinking cost per million tokens?
Kimi K2 Thinking costs $0.600 per million input tokens and $2.50 per million output tokens (USD, list price). Cache read: $0.150. Batch tier: not published.
What context window does Kimi K2 Thinking have?
Kimi K2 Thinking accepts 262 K tokens of context per request and generates up to 98 K tokens per response.
Does Kimi K2 Thinking accept images, audio or files?
Input: text. Output: text.
Does Kimi K2 Thinking have a reasoning mode and tool calling?
It has a reasoning mode. It supports tool calling.
When was Kimi K2 Thinking released and what is its knowledge cutoff?
Kimi K2 Thinking has been available by API since 11/06/2025. Knowledge cutoff: not published.
What would an app built on Kimi K2 Thinking cost?
With 10,000 requests a month of 1,500 input and 400 output tokens, Kimi K2 Thinking would cost about $19.00 a month at list price, without cache or batch discounts.
What is the API id of Kimi K2 Thinking?
The id is moonshotai/kimi-k2-thinking. It is the name passed in the model parameter of the API (or on OpenRouter).
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.