AllModelModel catalogueModels with no charge
Models with no charge
DeepSeek V4 Flash
The cheapest serious reasoner on the market.
DeepSeek V4 Pro
Open-weight frontier reasoning at rock-bottom prices.
DiffusionGemma 26B A4B IT
An open 26B Gemma built on diffusion
FLUX.1 Dev
FLUX.1 Dev — the open research build for images
FLUX.2 Klein 4B
4B FLUX.2 Klein — the smallest open model of the line
Free Models Auto Router
Automatically selects a currently available free model.
Gemma 4 31B IT
Google's open-weight model — near-free tokens for bulk work.
GLM 5.2
Zhipu's MIT-licensed flagship — a coding-agent favourite.
GPT-OSS 20B
OpenAI's smaller open model — high-volume work at no charge
Inkling
A small gateway text model — simple tasks at no charge
Laguna XS 2.1
A compact Laguna model — short answers at no charge
Llama 3.1 Nemotron Nano VL 8B v1
A small vision Llama from NVIDIA — images and documents
Llama 3.2 11B Vision Instruct
11B vision Llama 3.2 — an open model for images
Llama Nemotron Embed 1B v2
NVIDIA vectors built on Llama — search over your own corpus
Llama Nemotron Embed VL 1B v2
NVIDIA vision vectors — search across images and documents
MiniMax M3
Long-context multimodal reasoning at a budget price.
Mistral Nemotron
Mistral, tuned by NVIDIA — everyday text and tools
Nemotron 3 Embed 1B
1B Nemotron vectors — text indexing at no charge
Nemotron 3 Nano 30B A3B
Nemotron 3 Nano — a light 30B model at no charge
Nemotron 3 Nano Omni 30B A3B Reasoning
Nemotron Nano Omni with reasoning — text, images and audio together
Nemotron 3 Nano Omni 30B A3B Reasoning (Speech to Text)
Speech transcription on Nemotron Omni — audio to text
Nemotron 3 Super 120B A12B
The top 120B Nemotron — the line's heaviest tasks
Nemotron 3 Ultra
NVIDIA's open reasoning flagship, available free through AnyModel.
Nemotron 3.5 Content Safety
NVIDIA content safety — flags disallowed material in text
Nemotron 3.5 Lightning 30B A3B
The line's fastest Nemotron — short answers at speed
Nemotron Nano 12B v2 VL
A 12B vision Nemotron — screenshots and tables
NV Embed v1
NVIDIA's classic vectors — general semantic search
NV EmbedCode 7B v1
NVIDIA vectors for code — search across a repository
NV EmbedQA E5 v5
NVIDIA vectors for question answering — retrieval for RAG
NVIDIA Nemotron Nano 9B v2
The lightest 9B Nemotron — bulk runs at no charge
Riva Translate 4B Instruct v2
NVIDIA Riva translator — streaming text translation
Step 3.7 Flash
Step 3.7 Flash — a fast model for request volume