llmgauge

Moonshot · model

Kimi K2 Thinking

$0.60/1M in · $2.50/1M out · 262K context. That's cheaper than 35% of the 298 models we track, by output price. Here's what it costs, how its price has moved, and where it fits.

output price · per 1M tokens
$2.50
input $0.60/1M · routed
Context
262K
Input / 1M
$0.60
Output / 1M
$2.50
Modality
Text only
Provider
Moonshot
Tokenizer
Other

Snapshot · source: OpenRouter ↗ · how we measure →

cost at a typical workload
$430 / mo

For 1,500 input + 500 output tokens across 200,000 requests/month. That's 72× the cheapest tracked option (Ling-2.6-flash, $6.00/mo).

Tune the workload in the calculator →

output price history
output / 1M

Flat at $2.50 since tracking began 2026-06-14. Full history →

Where it fits

  • A mid-range option — $0.60 in / $2.50 out per 1M with a 262K-token context.

Watch for

  • Priced from OpenRouter's routed market, not a first-party list price — availability and rate can shift without notice.
  • Text-only — no image, audio, or file input.

These notes are derived from price, context and modality — structural facts, not measured quality. Measured cost-to-finish-a-task lives on the real-cost index.

Compare Kimi K2 Thinking

Kimi K2 Thinking vs GPT-5.4 miniKimi K2 Thinking vs GPT-5.4 nanoKimi K2 Thinking vs Claude Haiku 4.5Kimi K2 Thinking vs Gemini 3.1 ProKimi K2 Thinking vs Gemini 2.5 ProKimi K2 Thinking vs Gemini 2.5 FlashKimi K2 Thinking vs Grok 4.3Kimi K2 Thinking vs Grok 4.20Kimi K2 Thinking vs DeepSeek V4 ProKimi K2 Thinking vs Mistral Medium 3.5Kimi K2 Thinking vs Mistral Large 3Kimi K2 Thinking vs Llama 4 MaverickKimi K2 Thinking vs Qwen3 MaxKimi K2 Thinking vs GLM 4.6Kimi K2 Thinking vs MiniMax M2.5

Related models

Kimi K2 0905 Moonshot · $2.50/1M out · 262K Kimi K2 0711 Moonshot · $2.30/1M out · 131K Kimi K2.5 Moonshot · $2.02/1M out · 262K Kimi K2.6 Moonshot · $3.41/1M out · 262K Gemini 2.5 Flash Google · $2.50/1M out · 1.0M Nova 2 Lite Amazon · $2.50/1M out · 1M

How to read Kimi K2 Thinking's pricing

Two numbers decide most of the bill: $0.60/1M for input (everything you send — prompt, context, attachments) and $2.50/1M for output (everything it generates, including hidden reasoning tokens). Output is priced 4.2× the input rate here, so the shape of your workload — how much it reads versus writes — matters as much as the headline figure. This row is OpenRouter's routed market price; it can move as providers and routing change.

Frequently asked questions

How much does Kimi K2 Thinking cost per million tokens?

Kimi K2 Thinking is priced at $0.60 per 1M input tokens and $2.50 per 1M output tokens, from OpenRouter's routed market price as of the 2026-06-15 snapshot. Output is the figure that usually drives the bill. Enter your own token volumes in the cost calculator for a monthly estimate.

What is Kimi K2 Thinking's context window?

Kimi K2 Thinking has a 262K-token context window — roughly 393 pages of text. Prompt, attachments, conversation and the model's own output all share that budget, and every token you send is billed at the input rate.

Related