Apodex 1.1 Mini now free on OpenRouter
Apodex's 35B open-weight reasoning model for long-horizon research and forecasting is now free to call via OpenRouter's free tier (200 requests/day).
Why it matters
A 35-billion-parameter open-weight model with reasoning, tool calling and a 262K context window, designed for multi-step professional and scientific work with a built-in verification layer - now free, making long-horizon agentic research workloads testable at zero token cost.
What you could build with it
An indie developer could wire the free Apodex 1.1 Mini endpoint into the open-source FrontierAgent terminal harness to run long research or code-refactoring sessions with no token spend, then switch to the paid flagship only for the hardest tasks.
Does it hold up?
Usable today via the free OpenRouter endpoint and the open-source FrontierAgent TUI, but independent head-to-head benchmarks are thin and the model relies on its agent harness for its full capability.
Built with Apodex 1.1 Mini now free on OpenRouter
- Apodex launches Apodex v1.1 Deep Discover model (Testing Catalog)article · Covers the Apodex 1.1 family: the Deep Discover Agent Team mode, FrontierAgent harness, and the 35B open-weight Mini sibling now free on OpenRouter.
- Apodex 1.1: Free Open-Source AI That Gets Real Work Done - AMA (The Neural Feed)article · Ask-me-anything with the Apodex team on the 1.1 release, open weights, and the FrontierAgent framework.
- Apodex 1.1 Mini free model profile (FreeLLM)article · Verified free API listing: 262K context, reasoning, tool calling and JSON mode at 121 tok/s observed speed, free listing since Oct 1, 2026.
- ApodexAI/FrontierAgentgithub · 5,126 ★ · Apache-2.0 open-source agent runtime and terminal TUI (ReAct and Agent Team modes) from Apodex that runs against the Apodex-1.1 API endpoints, including the free Mini model.
Learn more
First spotted on article: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.