Kimi K2 Instruct pricing & specs
Moonshot AI · released 2025-07-11 · ● verified 2026-10-11
input / 1M$0.57via Novita AI
output / 1M$2.30via Novita AI
context131.1K
max output98.3K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Kimi K2 Instruct |
|---|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | 131K | −98% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −95% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −94.5% |
| Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | −93.8% |
| Command R7B | $0.0375 | $0.15 | 128K | −93.5% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Novita AI | $0.57 | $2.30 |
// faq
How much does Kimi K2 Instruct cost?
Kimi K2 Instruct costs $0.57 per million input tokens and $2.30 per million output tokens (cheapest tracked host: Novita AI). At 50M input and 10M output tokens per month that is about $51.50.
What is the context window of Kimi K2 Instruct?
131.1K tokens, with up to 98.3K output tokens per request.
What are cheaper alternatives to Kimi K2 Instruct?
Llama 3.2 1B Instruct ($0.02 in / $0.02 out), Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out) offer the same input types and capabilities for less.
Is Kimi K2 Instruct open weights?
Yes. It is available from 1 tracked hosts; the cheapest is Novita AI at $0.57 input and $2.30 output per million tokens.
// spec sheet
- input / 1M
- $0.57
- output / 1M
- $2.30
- blended (3:1)
- $1.0025
- context
- 131.1K
- max output
- 98.3K
- input types
- text
- reasoning
- no
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Novita AI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Kimi K2 Instruct | $0.57 | $2.30 | $51.50 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.