Fireworks AI

Verified 💳 Trial Credits

The fastest production platform for Generative AI. Run open-source models with blazing speed and efficiency. Specialized in fire-function calling and JSON mode.

Fast Inference Open Source Function Calling Production Ready
Get API Key Suggest Edit
3812

Overview

Provider Type

Trial Credits

API Endpoint

https://api.fireworks.ai/inference/v1

Free Tier Highlights

10 RPM (no payment method) / up to 6000 RPM (with card + credits)

Why Choose Fireworks AI?

Fireworks AI is a fast production platform for open models, known for reliable function calling and JSON mode. Its catalog includes GLM 5.3, Kimi K3, DeepSeek V4.1 Flash and MiniMax M3.

Best for: trying a production-grade platform before committing to it.

Watch out: there is no lasting free tier. New accounts get a small starter credit and only 10 requests/minute without a payment method.

Quick Start Guide

1

Go to https://fireworks.ai/

2

Sign in with Google/GitHub

3

Navigate to API Keys

4

Create User API Key

5

Use with OpenAI client library

Available Models

7 free models
Model Name ID Context Capabilities
Nemotron 3.5 Lightning 30B A3B Free
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b
- -
MiniMax M3 Free
accounts/fireworks/models/minimax-m3
- -
GPT-OSS 120B Free
accounts/fireworks/models/gpt-oss-120b
- -
GLM 5.3 Flash Free
accounts/fireworks/models/glm-5p3-flash
- -
GLM 5.3 Free
accounts/fireworks/models/glm-5p3
1 000 000 Context
-
DeepSeek V4.1 Flash Free
accounts/fireworks/models/deepseek-v4p1-flash
1 000 000 Context
-
Kimi K3 Free
accounts/fireworks/models/kimi-k3
1 000 000 Context
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_FIREWORKS_KEY",
    base_url="https://api.fireworks.ai/inference/v1"
)

response = client.chat.completions.create(
    model="accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

print(response.choices[0].message.content)

Free Tier Pricing & Limits

Rate Limit

Requests per minute

10 Requests per minute (no payment method) / up to 6000 Requests per minute (with card + credits)

Daily Quota

Requests per day

Credit-based

Token Limit

Tokens per minute

Varies by model

Monthly Quota

Per month limit

One-time trial

Free Credits

One-time

Free starter credit for new accounts (amount no longer stated by Fireworks; historically $1)

Use Cases

Real-time Chat Apps

Agentic Workflows (Function Calling)

Structured Data Extraction

High Volume Processing

Limitations & Considerations

$1 credit is one-time only

Billing account needed for continued use

Rate limits apply to free tier

Credits may expire

Community Hub

Live

Join the discussion, share tips, and rate Fireworks AI.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using Fireworks AI

Start Building Now