Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Model Library

Search our library of open source models and deploy in seconds.

Filters

Models (29)

Vision

Audio

FireLLaVA 13B

$0.2/M Tokens • 4096 Context

Firesearch OCR V6

$0.2/M Tokens • 8192 Context

Streaming ASR v1

Streaming ASR v2

z.ai

GLM-4.5V

$1.2/M Tokens • 131072 Context

InternVL3 38B

$0.9/M Tokens • 16384 Context

InternVL3 78B

$0.9/M Tokens • 16384 Context

InternVL3 8B

$0.2/M Tokens • 16384 Context

Meta Mark

Llama 3.2 11B Vision Instruct

$0.2/M Tokens • 131072 Context

Meta Mark

Llama 3.2 90B Vision Instruct

$0.9/M Tokens • 131072 Context

Meta Mark

Llama 4 Maverick Instruct (Basic)

$0.22/M Input • $0.88/M Output • 1048576 Context

Meta Mark

Llama 4 Scout Instruct (Basic)

$0.15/M Input • $0.6/M Output • 1048576 Context

LLaVA V1.6 Yi 34B

$0.9/M Tokens • 4096 Context

NVIDIA Nemotron Nano 2 VL

Phi-3.5 Vision Instruct

$0.2/M Tokens • 32064 Context

Qwen2-VL 2B Instruct

$0.1/M Tokens • 32768 Context

Qwen2-VL 72B Instruct

$0.9/M Tokens • 32768 Context

Qwen2-VL 7B Instruct

$0.2/M Tokens • 32768 Context

Qwen2.5-VL 32B Instruct

$0.9/M Tokens • 128000 Context

Qwen2.5-VL 3B Instruct

$0.2/M Tokens • 128000 Context

Qwen2.5-VL 72B Instruct

$0.9/M Tokens • 128000 Context

Qwen2.5-VL 7B Instruct

$0.2/M Tokens • 128000 Context

Qwen3 VL 235B A22B Instruct

$0.22/M Input • $0.88/M Output • 262144 Context

Qwen3 VL 235B A22B Thinking

$0.22/M Input • $0.88/M Output • 262144 Context

Qwen3 VL 30B A3B Instruct

$0.15/M Input • $0.6/M Output • 262144 Context

Qwen3 VL 30B A3B Thinking

$0.15/M Input • $0.6/M Output • 262144 Context

Rolm OCR

$0.2/M Tokens • 128000 Context

Whisper V3 Large

Whisper V3 Turbo

Featured Providers

Deepseek

Meta Mark

Meta

Microsoft

Qwen

Stability

Google

OpenAI

Nous

01.Ai

Black Forest Labs