Skip to content
CostPerPrompt

Kimi K2.5 API Pricing

Moonshot (Kimi) · context window 262K · prices updated 2026-08-02

Input per 1M tokens
$0.57
Output per 1M tokens
$2.85
Cached input per 1M
$0.095
83% cheaper than fresh input

What real workloads cost on Kimi K2.5

Workload Per request Per month
1K short requests/day (500 in / 150 out) $0.0007 $21.38
Support chatbot, 500 convs/day (~5K in / 1.4K out per conv) $0.0068 $103
Document pipeline, 10K docs/day (3K in / 500 out) $0.0031 $940

Model your exact traffic in the API cost calculator — it preloads Kimi K2.5 with caching and batch options.

Cheaper alternatives

More Moonshot (Kimi) models

Frequently asked questions

How much does the Kimi K2.5 API cost?

Kimi K2.5 costs $0.57 per million input tokens and $2.85 per million output tokens, with cached input at $0.095 per million (83% cheaper). In practice, a typical short request (500 tokens in, 150 out) costs about $0.0007.

What does 1,000 requests per day cost on Kimi K2.5?

At 500 input + 150 output tokens per request, 1,000 requests/day costs about $21.38 per month. Heavier workloads scale linearly — use our API cost calculator to model your exact traffic.

How can I reduce Kimi K2.5 costs?

Three levers, in order of impact: (1) route routine requests to a cheaper tier and keep Kimi K2.5 for hard cases; (2) enable prompt caching — cached input is 83% cheaper, which typically halves chatbot bills; (3) use the batch API for non-urgent jobs at a ~50% discount.

Is Kimi K2.5 worth the price?

It depends on task difficulty. Flagship models earn their premium on complex reasoning, coding, and high-stakes output; mini/flash tiers handle classification, extraction and routine chat at 10–30× lower cost. Benchmark a sample of your real workload on both before committing.