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

Kimi K2 Instruct

CortecsOpen weights

Kimi K2 Instruct by Cortecs costs $0.55 per 1M input tokens and $2.65 per 1M output tokens, with a 131K-token context window.

Pricing

Input (per 1M tokens)
$0.55
Output (per 1M tokens)
$2.65
Cached input (per 1M)
—

Specifications

Provider
Cortecs
Context window
131K tokens
Parameters
—
Released
Jul 2025
Open weights
Yes
Frontier model
No

Benchmarks

SWE-bench Verified
53.4

Compare Kimi K2 Instruct with…

Kimi K2 Instruct vs Step 5 Preview$2.70/1MKimi K2 Instruct vs kimi-k2-0905-preview$2.53/1MKimi K2 Instruct vs Hy4 preview$2.50/1MKimi K2 Instruct vs Qwen3 235B-A22B$2.80/1MKimi K2 Instruct vs Qwen2.5 32B Instruct$2.80/1MKimi K2 Instruct vs Qwen3-VL 235B-A22B$2.80/1M

FAQ

How much does Kimi K2 Instruct cost?

Kimi K2 Instruct is priced at $0.55 per 1M input tokens and $2.65 per 1M output tokens. Output tokens cost more than input.

What is Kimi K2 Instruct's context window?

Kimi K2 Instruct supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.

Is Kimi K2 Instruct open weight?

Yes — Kimi K2 Instruct has openly available weights.

Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.