256K
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
OpenRouterChat
Chat with free AI models.
Connect your own OpenRouter, Groq or Cerebras key once, then chat here or call the same models from code.
Free models17
dots-studio
Dots Studio: Dots3-Note Preview (free)
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
262K
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
262K
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
66K
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
OpenRouterChat
256K
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
262K
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
OpenRouterChat
1M
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
OpenRouterChat
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
How it works
- 1
Connect a provider
Paste a key from OpenRouter, Groq or Cerebras. It's encrypted on our server and never shown again.
- 2
Chat with any connected model
Pick a model for each message, or let Auto choose one that's available.
- 3
Call it from code
Point any OpenAI SDK at Free Model with your own API key.
One key for every model you connect.
Point any OpenAI SDK at Free Model. Use an exact model ID, or "auto" to move to another connected model when one is rate-limited.
API setupapp.py
from openai import OpenAI
client = OpenAI(
base_url="https://staging.freemodel.io/api/v1",
api_key="sk_…",
)
reply = client.chat.completions.create(
model="auto",
messages=[{"role": "user", "content": "Hello"}],
)Questions
Is it free?
OpenRouter models ending in :free are priced at zero, with daily limits set by OpenRouter. Groq and Cerebras use your own account's allowance; a paid account there can be billed, and free tiers can change.
Why do I need my own key?
Free limits apply per account. With your own key the allowance is yours, and you can revoke it at the provider at any time.
Are my chats saved?
No. A conversation stays in the open tab and is gone when you close it, start a new chat or sign out. Request records contain usage metadata such as model, tokens, status and timing, not conversation text.
Can I send images or files?
Not yet. Some models accept images upstream, but chat and the API here are text-only for now.
What can I help with?
Start chatting