Fireworks AI

Provider

Inference, fine-tuning and dedicated GPU deployments for open models

Price: Free credits, then paid
Access: API key

About

Fireworks AI serves open models such as Kimi, GLM, DeepSeek and Qwen through an OpenAI-compatible API, with managed fine-tuning that includes reinforcement learning. It is for teams taking open models to production. New accounts get $1 in free credits.

What you can do with it

Run open LLMs and vision models serverless, priced per token
Fine-tune models with SFT, DPO or reinforcement fine-tuning
Deploy models on dedicated H100 or H200 GPUs

Get started

Create an API key in the Fireworks dashboard
Set FIREWORKS_API_KEY in your environment

Example

curl https://api.fireworks.ai/inference/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $FIREWORKS_API_KEY" \
  -d '{
    "model": "accounts/fireworks/models/glm-5p3-flash",
    "messages": [
      {"role": "user", "content": "Say hello in Spanish"}
    ]
  }'

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: Python
MCP server: None