Llama 3.1 70BLOCAL
via Ollama · :11434
Balanced local flagship. Strong general reasoning, runs on your own GPU.
- ctx 128K
- ~38 tok/s
- text
FreeLLM
LOCAL ROUTER15 free providers via a local sidecar — no keys, no card.
FREE TOKENS / MO~0.93B
API KEYS0
No messages yet. Type below and press Send — this chat is wired to a live
model and will answer for real.
Model Catalog
12 MODELSBrowse every model wired into the sidecar. Pick one and it loads straight into your chat — no keys, no card.
⌕
Qwen2.5 Coder 32BLOCAL
via llama.cpp
Code-specialized. Repo edits, refactors, and test generation.
- ctx 32K
- code
- fill-in-middle
DeepSeek V3CLOUD
via DeepSeek
Frontier-class reasoning at near-zero cost through the free sidecar.
- ctx 64K
- 671B MoE
- text
Cerebras Llama 3.1 8BCLOUD
via Cerebras
Wafer-scale inference. Blistering output for instant replies.
- ctx 8K
- ~1800 tok/s
- text
Mistral Nemo 12BCLOUD
via OpenGateway
Long-context multilingual chat. A reliable default for drafting.
- ctx 128K
- multilingual
- text
FLUX.1 SchnellCLOUD
via Pollinations
Text-to-image in a few steps. No key, no card, just prompts.
- image
- 1024²
- 4-step
Venice UncensoredCLOUD
via Venice
Privacy-first, unfiltered. Web search and image gen built in.
- ctx 32K
- private
- web
Phi-3 MiniLOCAL
via Ollama
3.8B tiny model for quick local tasks on modest hardware.
- ctx 4K
- 3.8B
- text
Gemma 2 9BLOCAL
via Ollama
Efficient open model. A solid local all-rounder for chat.
- ctx 8K
- 9B
- text
GPT-OSS 120BCLOUD
via Surplus Intelligence
Open weights, cheapest-seller routed. Heavy reasoning on demand.
- ctx 128K
- USDC/Base
- text
Premium ReasonerX402
via Bankr X402 Cloud
Pay-per-request premium models. Settled in USDC/BNKR on Base.
- ctx 200K
- x402
- text
SDXL TurboCLOUD
via Pollinations
High-fidelity image generation on the free tier.
- image
- 1024²
- turbo
No models match that filter.