Fireworks AI

Serverless Featured

Visit Provider Docs Pricing

Fast serverless inference for open-source models with per-token pricing, fine-tuning, and on-demand deployments.

Features

OpenAI Compatible

Streaming

Batching

Fine-tuning

Embeddings

Vision

Audio

Function Calling

JSON Mode

Compliance

SOC 2

HIPAA

GDPR

Pricing Model

per token

Free tier: $1 in free credits

Details

Models 40

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

Audio / MusicImage GenerationLLM Inference

Model Catalog (40)

Model	Type	Input $/1M	Output $/1M	Context	Speed
DeepSeek R1 DeepSeek · 671B MoE	llm	$0.560	$1.68	—	—
DeepSeek R1 0528 DeepSeek · 671B MoE	llm	$0.560	$1.68	—	—
DeepSeek V3 DeepSeek · 671B MoE	llm	$0.560	$1.68	—	—
DeepSeek V4 Flash DeepSeek	llm	$0.140	$0.280	—	—
DeepSeek V4 Pro DeepSeek	llm	$1.74	$3.48	—	—
DeepSeek V4.1 Flash DeepSeek	llm	$0.300	$1.20	—	—
Ember-1 Fireworks AI	llm	$3.00	$15.00	—	—
GLM 4.5 Zhipu AI · 106B MoE (12B active)	llm	$0.900	$0.900	—	—
GLM 4.6 Zhipu AI · 355B	llm	$0.900	$0.900	—	—
GLM 4.7 Zhipu AI	llm	$0.600	$2.20	—	—
GLM 5 Zhipu AI · 744B	llm	$1.00	$3.20	—	—
GLM 5.1 Z.ai · 744B MoE (40B active)	llm	$1.40	$4.40	—	—
GLM 5.2 Z.ai	llm	$1.40	$4.40	—	—
GLM 5.3 Z.ai	llm	$1.40	$4.40	—	—
GLM 5.3 Flash Z.ai	llm	$0.150	$0.500	—	—
GPT OSS 120B OpenAI · 117B MoE (5.1B active)	llm	$0.150	$0.600	—	—
Gemma 3 12B Google · 12B	llm	$0.200	$0.200	—	—
Gemma 3 27B Google · 27B	llm	$0.900	$0.900	—	—
Gemma 3 4B Google · 4B	llm	$0.100	$0.100	—	—
Gemma 4 31B Google · 27B	llm	$0.900	$0.900	—	—
Inkling Thinking Machines	llm	$1.00	$4.05	1.0M	—
Kimi K2 Moonshot AI · 1T MoE (32B active)	llm	$0.600	$2.50	—	—
Kimi K2.5 Moonshot AI · 1T MoE (32B active)	llm	$0.600	$3.00	—	—
Kimi K2.6 Moonshot AI · 1T MoE (32B active)	llm	$0.950	$4.00	—	—
Kimi K2.7 Code Moonshot AI · 1T MoE (32B active)	code	$0.950	$4.00	—	—
Kimi K3 Moonshot AI	llm	$3.00	$15.00	—	—
Llama 3.3 70B Meta · 70B	llm	$0.900	$0.900	—	—
Llama 4 Maverick Meta · 400B (17B active)	llm	$0.900	$0.900	—	—
Llama 4 Scout Meta · 109B (17B active)	llm	$0.900	$0.900	—	—
MiniMax M2.7 MiniMax	llm	$0.300	$1.20	—	—
MiniMax M3 MiniMax	llm	$0.300	$1.20	—	—
Ministral 3 8B Mistral AI · 8B	llm	$0.200	$0.200	—	—
Mistral Large 3 Mistral AI · 675B MoE (41B active)	llm	$1.20	$1.20	—	—
Qwen 3 235B Alibaba · 235B MoE	llm	$1.20	$1.20	—	—
Qwen 3 32B Alibaba · 32B	llm	$0.900	$0.900	—	—
Qwen 3 8B Alibaba · 8B	llm	$0.200	$0.200	—	—
Qwen 3.6 Plus Alibaba	llm	$0.900	$0.900	—	—
Qwen3.7 Plus Alibaba	llm	$0.400	$1.60	—	—
Qwen3.8 Max Alibaba	llm	$2.00	$6.00	—	—
gpt-oss-20b OpenAI	llm	$0.070	$0.300	—	—

Fireworks AI API FAQ

Is the Fireworks AI API free?

Yes, Fireworks AI has a free tier: $1 in free credits. Paid usage is billed per model.

What is the cheapest Fireworks AI model?

Gpt-oss-20b at $0.07 in / $0.30 out per 1M tokens, based on the 40 models we track for Fireworks AI.

How many models does Fireworks AI offer?

We track 40 Fireworks AI models: 39 LLM, 1 coding.

Is the Fireworks AI API OpenAI-compatible?

Yes. Fireworks AI exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.