Kimi K2 API

Model details

Context window

131K tokens

Max output

131K tokens

Input

Text

Output

Text

Capabilities

Tool calling, Streaming

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Kimi K2 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Kimi K2

Kimi K2 answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kimi-k2",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kimi-k2",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kimi-k2",
  "input": "Hello"
}'

Use Kimi K2 in your tools

Every coding agent below has a setup guide. Set the model to kimi-k2.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from Moonshot AI

Alternatives to Kimi K2

• Gemini 3.8 FlashFast multimodal reasoning for coding and agents.Google
• GLM-5GLM-5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Z.ai
• Grok 4.20 Non-ReasoningGrok 4.20 Non-Reasoning for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.xAI

Questions about this model

How much does the Kimi K2 API cost?

Kimi K2 costs $1 per 1M input tokens and $3 per 1M output tokens on Inferray, and cached input is $0.5 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Kimi K2?

No. You add credit and pay Kimi K2's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Kimi K2 included in Token Plans?

No. Kimi K2 is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Kimi K2 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to kimi-k2. The same key works in Codex, opencode, Cline, and other agents.

Does Kimi K2 support tool calling and vision?

Kimi K2 supports tool calling and streaming on Inferray. It does not take image input.

Is it the real Kimi K2?

Yes. A request for kimi-k2 is answered by Kimi K2 from Moonshot AI, billed at its published list price. Inferray never substitutes a different or smaller model.