awesome-free-ai-coding · every free model · every provider · filter the list
5 rows on the list serve deepseek-v4-flash free: Routeway, Alibaba Cloud Model Studio (DashScope, international), BazaarLink, AtomCode and FreeInference (Harvard SEAS). None asks for a card. The providers’ last scheduled probes were on 2026-10-26; their offers are rechecked twice a week. It measures strong: within 25 points of the top of the Artificial Analysis Intelligence Index.
Every free model · the whole list
🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-09-16
OpenAI-compatible gateway with a rotating :free chat-model lane beside metered models
FAQ: 20 requests/minute (published sources disagree) per account
Free models: 200 requests/day per account
The FAQ and rate-limit docs disagree on the per-minute cap; both publish the same daily cap. Free IDs end in :free, rotate and may be removed at any time. At a cap they return 429; paid twins require a positive balance. The FAQ describes signup and key creation without payment, but the older terms list a payment method. No legal entity is named; support is email and Discord.
https://api.routeway.ai/v1ROUTEWAY_API_KEY — get one at https://routeway.ai/dashboard/keysconfigs/codex/routeway.config.toml — copy it to ~/.codex/, then codex -p routeway; set up on the lane by the vendor’s own page, https://docs.routeway.ai/integrations/agents/codex: “Use OpenAI’s Codex with Routeway by adding a custom provider”deepseek-v4-flash:free🔌 LLM APIs with free tier · no card · not offered in mainland China · last probe 2026-10-26 · listed since 2026-09-25
A million free tokens on each of its chat models in the Singapore region — Qwen, DeepSeek and GLM among them — valid 90 days from activation or the model’s release; OpenAI-compatible
Free grants apply in Singapore (international) only, independently per model and dated snapshot. The model pricing tables decide eligibility: Kimi has no free-quota column and glm-5.2-fast-preview has none. Account information must be completed before activation. After the grant, usage is automatically billed pay-as-you-go unless Free Quota Only is enabled separately for the model; that switch is disabled by default.
https://dashscope-intl.aliyuncs.com/compatible-mode/v1ALIBABA_MODEL_STUDIO_API_KEY — get one at https://modelstudio.console.alibabacloud.comdeepseek-v4-flash-0731🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-09-28
OpenAI-compatible gateway with a shared free allowance on selected models and an auto:free router
With credit: 20 requests/rolling minute; 120 weighted units/day per account
Free models: 2 requests at once per account
Free models: 20 requests/minute shared across the endpoint
Additional IP guard: Requests allowance: amount not published (period not published) per IP
The free models share each account’s daily weighted allowance, reset at 00:00 UTC. Longer inputs can consume more units. Account concurrency and the site-wide rate also apply. Paid fallback happens only when enabled and the account has sufficient credit. Free IDs and their metered twins are separate catalog routes.
https://api.bazaarlink.ai/v1BAZAARLINK_API_KEY — get one at https://bazaarlink.ai/keysdeepseek/deepseek-v4-flash-0731free:free🎁 Trials (no card when possible) · no card · last probe 2026-10-26 · listed since 2026-09-27
Open-source terminal coding agent from AtomGit, the code host run by CSDN and the Open Atom Foundation, whose sign-in claims a free 30-day coding plan, its quota counted in five-hour windows and its claims capped at a thousand a day
Claimed Lite lasts 30 days; claims have a platform-wide pool of 1,000 slots per day, not a per-user inference cap. GLM-5.2 needs a separate Pro claim: “Pro Trial 7 days Free claim, 100 slots/day at 10:00” or “Pro 30 days Free claim, requires a merged PR in the activity repository”. All plan usage is measured in rolling five-hour windows without published numerical budgets. CodingPlan works inside AtomCode via AtomGit sign-in; other providers use your own key.
🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-05
Harvard SEAS’s MadSys Lab serving open models free to every account behind both an OpenAI-shaped and an Anthropic-shaped endpoint, with a documented Claude Code setup
No card. This is an experimental research service with capacity-dependent limits. Prompts and responses may be logged for research; sanitized content, usage statistics and routing metrics may be published or open-sourced. Only models marked Free accept a Free key; Pro catalog rows need a Pro-enabled key.
https://freeinference.org/v1FREEINFERENCE_API_KEY — get one at https://freeinference.orgANTHROPIC_BASE_URL): https://freeinference.org/anthropicdeepseek-v4-flashdeepseek-v4.1-flash — free at NVIDIA NIM (build.nvidia.com), Freebuff, Alibaba Cloud Model Studio (DashScope, international) and Token Harbordeepseek-v3.2 — free at Kirodeepseek-v4-pro — free at Alibaba Cloud Model Studio (DashScope, international)Generated from registry.yaml on 2026-10-27 and re-verified twice a week; every free model on the list is at https://mvalentsev.github.io/awesome-free-ai-coding/models/, and the full list, the Atom feed and the machinery at https://github.com/mvalentsev/awesome-free-ai-coding.