Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

kimi-k2-thinking

302.AIOpen weights

kimi-k2-thinking by 302.AI costs $0.58 per 1M input tokens and $2.30 per 1M output tokens, with a 262K-token context window.

Pricing

Input (per 1M tokens)
$0.58
Output (per 1M tokens)
$2.30
Cached input (per 1M)
—

Specifications

Provider
302.AI
Context window
262K tokens
Parameters
1T
Released
Nov 2025
Open weights
Yes
Frontier model
No

Compare kimi-k2-thinking with…

kimi-k2-thinking vs Kimi K2 0711$2.30/1Mkimi-k2-thinking vs Qwen3.6 35B-A3B$2.25/1Mkimi-k2-thinking vs Qwen3.5 Plus$2.40/1Mkimi-k2-thinking vs Qwen3.5 27B$2.40/1Mkimi-k2-thinking vs QwQ Plus$2.40/1Mkimi-k2-thinking vs Nemotron 3 Ultra$2.40/1M

FAQ

How much does kimi-k2-thinking cost?

kimi-k2-thinking is priced at $0.58 per 1M input tokens and $2.30 per 1M output tokens. Output tokens cost more than input.

What is kimi-k2-thinking's context window?

kimi-k2-thinking supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.

Is kimi-k2-thinking open weight?

Yes — kimi-k2-thinking has openly available weights.

Data as of 2026-10-30. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.