Using Kimi K2.5 on Fireworks AI

Implementation guide · Kimi · Moonshot AI

Serverless

Fireworks AI exposes Kimi K2.5 through model ID accounts/fireworks/models/kimi-k2p5. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-04. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Fireworks AI and generate an API key.
  2. 2
    Use the Fireworks AI SDK or REST API to call accounts/fireworks/models/kimi-k2p5 — see the documentation for request format.
  3. 3
    You'll be billed $0.60/1M input, $3.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install openai
API key
FIREWORKS_API_KEY
Model ID
accounts/fireworks/models/kimi-k2p5

Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],
    base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
    model="accounts/fireworks/models/kimi-k2p5",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Fireworks AI

TypePrice (per 1M)
Input tokens$0.60
Output tokens$3.00

Capabilities

VisionMultimodalJSON / Tool useStructured Outputs

About Kimi K2.5

Kimi K2.5 is Moonshot AI's Kimi model focused on code generation and software engineering. It offers a 256K-token context window and scores 87.9 on GPQA.

Full model details →

Model Specs

Released2026-03-15
Parameters1T (MoE, 384 experts)
Context256k
ArchitectureMixture of Experts

Also available on(9)

OpenRouter$0.44/1MTogether AI$0.50/1MAWS Bedrock$0.60/1M
Compare all providers →

Provider

Fireworks AI

San Mateo, California, United States