Kimi K3 Fast API

Model details

Context window

1.0M tokens

Max output

1.0M tokens

Input

Text, images

Output

Text

Capabilities

Reasoning, Vision, Tool calling, Streaming, JSON output

Interfaces

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

Why teams pick it

• Kimi K3 Fast for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Kimi K3 Fast

Kimi K3 Fast 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-k3-fast",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kimi-k3-fast",
  "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-k3-fast",
  "input": "Hello"
}'

Use Kimi K3 Fast in your tools

Every coding agent below has a setup guide. Set the model to kimi-k3-fast.

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

More from Moonshot AI

Alternatives to Kimi K3 Fast

• Claude Opus 5State-of-the-art agentic coding for enterprise work.Anthropic
• GPT-5.6 SolFrontier GPT-5.6 reasoning for complex professional work.OpenAI
• Gemini 4 ArgonGoogle's frontier model for long-horizon coding and knowledge work.Google

Questions about this model

How much does the Kimi K3 Fast API cost?

Kimi K3 Fast costs $4.5 per 1M input tokens and $22.5 per 1M output tokens on Inferray, and cached input is $0.45 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Kimi K3 Fast?

No. You add credit and pay Kimi K3 Fast'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 K3 Fast included in Token Plans?

No. Kimi K3 Fast is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Kimi K3 Fast 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-k3-fast. The same key works in Codex, opencode, Cline, and other agents.

Does Kimi K3 Fast support tool calling and vision?

Kimi K3 Fast supports tool calling, image input, reasoning, JSON output and streaming on Inferray.

Is it the real Kimi K3 Fast?

Yes. A request for kimi-k3-fast is answered by Kimi K3 Fast from Moonshot AI, billed at its published list price. Inferray never substitutes a different or smaller model.