L LLM Cloud Hub
Model

Kimi K2 0905

MoonshotAI Kimi K2 0905 — pricing, 262k context window, API cost calculator and alternatives.

By MoonshotAI

🔧 Tools Function calling — the model can structure responses as tool calls with typed arguments. Reliability differs between providers. Glossary → {} JSON Forces output to be valid JSON, reducing parse errors. Some providers also let you constrain to a schema. Glossary →
Context window Maximum tokens (input + output) the model can process in a single request. Glossary →
262,144
tokens
Input price What the model charges for tokens you send (prompt + context). Glossary →
$0.6000
per 1M tokens
Output price What the model charges for tokens it generates. Usually 3–5× pricier than input. Glossary →
$2.5000
per 1M tokens

Specs

Provider
MoonshotAI
Slug
moonshotai/kimi-k2-0905
Capabilities
tools, json_mode

Pricing freshness

Tier
standard
Currency
USD
As of
2026-05-14 00:17 UTC
Estimate monthly cost → See alternatives to Kimi K2 0905 →

Pricing history

2 data points · since 2026-05-08
Input $/1M Output $/1M latest: $0.6 in / $2.5 out

Quickstart — call Kimi K2 0905 from your app

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "moonshotai/kimi-k2-0905",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Official docs: https://openrouter.ai/docs

Related models

Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.

Frequently asked questions

What is Kimi K2 0905?

Kimi K2 0905 is a large language model API from MoonshotAI with a 262k-token context window. It costs $0.6 per 1M input tokens and $2.5 per 1M output tokens.

How much does Kimi K2 0905 cost?

Kimi K2 0905 is priced at $0.6 per 1M input tokens and $2.5 per 1M output tokens via the MoonshotAI API. A 50/50 input/output workload of 1M total tokens costs about $1.55.

What is the context window of Kimi K2 0905?

Kimi K2 0905 supports up to 262k tokens of context per request — roughly 524 pages of English text or 32768 lines of code at a typical density.

Does Kimi K2 0905 support vision, tool use, or JSON mode?

Kimi K2 0905 supports tool/function calling and structured JSON mode. It does not support image input (vision).

Who makes Kimi K2 0905?

Kimi K2 0905 is built and operated by MoonshotAI. Pricing, context window, and capabilities on this page are refreshed nightly from MoonshotAI's public catalog.

Can I self-host Kimi K2 0905?

Kimi K2 0905 is API-only — its weights are not publicly distributed by MoonshotAI, so it cannot be self-hosted today.

Keyboard shortcuts

?
Show this overlay
/
Focus the first form field
g h
Go to / (home)
g b
Go to /best-llm-for
g c
Go to /cost
g s
Go to /self-hosted
g x
Go to /compliance
Esc
Close any overlay

Inspired by Linear and GitHub conventions. The two-key sequences (g then h) work within ~1 second.