OpenCode Zen Free Models
Free coding LLMs including Big Pickle, MiMo, DeepSeek, and Nemotron
The catch:
All free models are limited-time and you must add billing details and credits; Big Pickle, LL Alpha, Exo and MiMo data may be used to improve the models, and NVIDIA trial endpoints log use.
What you get from OpenCode Zen Free Models for free
OpenCode Zen offers a zero-cost tier for selected coding models to gather community feedback and benchmark performance. These models feature $0.00 input, output, and cached read rates per 1M tokens.
Available Free Models
- Big Pickle: A stealth model available at no cost during its testing period.
- GLM-5.3-Flash Free, DeepSeek V4.1 Flash Free, MiniMax M3.1 Flash Free, LongCat 2.5 Preview Free: Free from zero-retention providers.
- MiMo-V2.6-Flash Free, MiMo-V2.5 Free, Exo Free, LL Alpha Free: Free while the teams collect feedback.
- Nemotron 3 Ultra / 3.5 Lightning / 3.5 Super VL Free: NVIDIA trial endpoints.
- Beam Free: Free, 30-day retention, not available in some countries.
Access and Setup
- Create an account on OpenCode Zen and configure billing details to generate an API key.
- In the OpenCode TUI, run
/connect, choose the OpenCode pay-as-you-go provider, and paste your API key. - Access models directly via OpenAI-compatible endpoints or the OpenCode SDK:
- OpenAI-Compatible Endpoint:
https://opencode.ai/inference/openai/v1/chat/completions(all free chat models)
- Specify the model in your configuration using the format
opencode/<model-id>(e.g.,opencode/big-pickleoropencode/nemotron-3.5-lightning-free).
Important Conditions
- Account Requirements: Zen uses a pay-as-you-go architecture requiring valid billing details on file, even when using $0.00 models.
- Data Logging: Free-tier models operate outside Zen's standard zero-retention policy. NVIDIA Nemotron endpoints log session data under API trial terms, and Big Pickle, LL Alpha, Exo and MiMo data may be used to improve those models. Do not use confidential or sensitive codebases with free-tier endpoints.
Models served free
Limits as the provider publishes them; a dash means none is published.
| Model | Context | RPM | RPD | TPM | Tools | Vision |
|---|---|---|---|---|---|---|
| Big PickleModel id big-pickle; stealth model, data may be used to improve the model | — | — | — | — | — | — |
| GLM-5.3-Flash FreeModel id glm-5.3-flash-free; zero-retention provider | — | — | — | — | — | — |
| DeepSeek V4.1 Flash FreeModel id deepseek-v4.1-flash-free; zero-retention provider | — | — | — | — | — | — |
| MiniMax M3.1 Flash FreeModel id minimax-m3.1-flash-free; zero-retention provider | — | — | — | — | — | — |
| Beam FreeModel id beam-free; 30-day retention; not available in some countries | — | — | — | — | — | — |
| LL Alpha FreeModel id ll-alpha-free; stealth model, data used to improve it, 30-day retention | — | — | — | — | — | — |
| LongCat 2.5 Preview FreeModel id longcat-2.5-preview-free; zero-retention provider | — | — | — | — | — | — |
| Exo FreeModel id exo-free; data may be used to improve the model | — | — | — | — | — | — |
| MiMo-V2.6-Flash FreeModel id mimo-v2.6-flash-free; limited time | — | — | — | — | — | — |
| MiMo-V2.5 FreeModel id mimo-v2.5-free; limited time | — | — | — | — | — | — |
| Nemotron 3 Ultra FreeModel id nemotron-3-ultra-free; NVIDIA trial use only, use is logged | — | — | — | — | — | — |
| Nemotron 3.5 Lightning FreeModel id nemotron-3.5-lightning-free; NVIDIA trial use only, use is logged | — | — | — | — | — | — |
| Nemotron 3.5 Super VL FreeModel id nemotron-3.5-super-vl-free; NVIDIA trial use only, use is logged | — | — | — | — | — | — |
| Jev 1.13 FreeModel id jev-1.13-free; classification endpoint, not chat | — | — | — | — | — | — |
History
Verified by a person on · last automated check : a change was detected and is awaiting review. Automated findings never change this page until a person confirms them (how we verify).
- Change detectedby the monitor · +1 -6 pricing sentences
- Change detectedby the monitor · -3 pricing sentences
- Change detectedby the monitor · +6 -4 pricing sentences
- Terms updatedby a person · Content updated from https://opencode.ai/v2/docs/console/models/ (checked 2026-10-20).
- Change detectedby the monitor · +3 -6 pricing sentences
- Change detectedby the monitor · +3 -3 pricing sentences
Still works?
Work at opencode.ai? Add an aifree.dev badge
HTML
<a href="https://aifree.dev/offer/opencode-zen-free-models"><img src="https://aifree.dev/badge/opencode-zen-free-models" alt="OpenCode Zen Free Models on aifree.dev" height="20"></a>Markdown
[](https://aifree.dev/offer/opencode-zen-free-models)Compared in
More free coding tools
Related offers
Devin Free Plan
Free tier - Light agent coding quota
LLM7.io Free Tier
100,000 tokens/day - 100,000 tokens per 24 hours with a free token (input + output combined)
IteraCompute free Qwen3.8-27B
30,000,000 tokens/month - 30M tokens/month on the free tier (input + output, incl. reasoning)
Appwrite Education plan
6 months - 6 months of Pro-resources access, one-time per account
BrowserStack student plan
12 months - One-year license via the GitHub Student Pack