Skip to content

Fireworks AI · chat

kimi-k2-instruct

fireworks/kimi-k2-instruct

Input price
$0.600 / 1M tokens
Output price
$2.50 / 1M tokens
Context window
131K tokens
Lifecycle
stable

kimi-k2-instruct for OpenAI-compatible gateway routing

kimi-k2-instruct is a Fireworks AI chat model in the Ferro Labs live catalog with a 131K tokens context window, 16K tokens maximum output, and capabilities including Function Calling, JSON Mode, and Response Schema, and more.

Token pricing is listed as $0.600 / 1M tokens for input tokens and $2.50 / 1M tokens for output tokens. Route calls through the Ferro Labs AI Gateway by sending model as fireworks/kimi-k2-instruct to the OpenAI-compatible chat completions endpoint. The catalog lists this model as stable for normal gateway routing.

OpenAI-compatible usage example

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

Capabilities

  • Function Calling
  • JSON Mode
  • Response Schema
  • Streaming

Modalities

Input

  • Text

Output

  • Text

More from Fireworks AI

Catalog prices may change. Verify current provider terms before purchasing.