awesome-free-ai-coding · every free model · every provider · filter the list

Where qwen3.8-27b is free

9 rows on the list serve qwen3.8-27b free: Groq, LLMTR, LLM Tech, Hetzner Inference API, Alibaba Cloud Model Studio (DashScope, international), IteraCompute, Regolo AI, VLM Run Gateway and OVHcloud AI Endpoints. None asks for a card; LLM Tech, VLM Run Gateway and OVHcloud AI Endpoints answer with no account at all. 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

Who serves it free

Groq

🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-17

Fast inference against a free plan Groq publishes as a per-model rate table

Provider-wide limits

These are the Free Plan limits for the coding models, shared by keys in the same organization. Classifiers, guardrails, speech and voice models have separate limits; their API examples do not establish free coding-model eligibility. Groq calls the table “a high level summary and there may be exceptions”; the account limits page gives the exact values.

LLMTR

🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-10-05

Turkish OpenAI-compatible gateway with free models on a zero balance and dated previews; some previews require a previous top-up

Provider-wide limits

Heabsy Qwen3.8 27B: Daily usage allowance: amount not published per account; for heabsy/qwen3.8-27b-heabsy-free

Nemotron3.5 Super VL: Daily usage allowance: amount not published; scope not published; for nvidia/nemotron-3.5-super-vl-free

Jais 3 MoVA: 200,000 tokens/day per account per model (Input and output count together; lower first-day allowance for new accounts); for ifm/jais-3-mova-36b-a4b. 00:00’da (TSİ)

K2 Horizon: 200,000 tokens/day per account per model (Input, output and reasoning count together; lower first-day allowance for new accounts); for ifm/k2-horizon-375b-a23b. 00:00’da (TSİ)

MiniMax M3.1 Flash: 5,000,000 tokens/day per account per model; for minimax/minimax-m3.1-flash-free. 00:00’da (TSİ)

Shanghai AI Lab models: 500,000 tokens/day sharing scope disputed (Per model; model pages say per person, the guide says per account. Input, output and reasoning count; new accounts have a lower first-day allowance.); for internlm/intern-s2-free, internlm/atria-dawn-free, internlm/atria-dawn-preview-free, internlm/agents-a1-free, internlm/sage-a1.5-free. 00:00’da (TSİ)

Free chat rows can be called on a new account with zero balance before any top-up. Paid use is prepaid; an 8% margin applies once at top-up, not to model prices. Prompt and response bodies are not permanently written to the usage and billing database. Heabsy requires provider-specific data-transfer consent: “Heabsy models cannot be called until your account has granted the data-transfer consent for Heabsy”. Its stream is buffered until completion, and reasoning_effort is unsupported. For free Nemotron3.5 Super VL, inputs “may be retained by the provider and used to improve the model”. Shanghai AI Lab prompts and completions may be logged by the provider and used to improve models.

LLM Tech

🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-18

EU provider of one model whose quickstart prints a shared trial key for anyone: 2M tokens a day per address and 4 concurrent requests, tool calls included, no account

Shared trial key: 4 requests at once per key

64 requests at once shared across the endpoint

The public trial key shares its concurrency among all callers; the daily token budget is per IP and counts both prompt and completion. Its context is 131,072 tokens; personal paid keys have the full 262,144 and share the endpoint’s separate inflight ceiling. Paid keys are issued by email, per token without subscription or minimum. Prompts and completions are volatile and never persisted or trained on; metadata, including IP, is retained 13 months. The sole proprietor operates in Poland, with GPUs in Italy behind a German edge.

Hetzner Inference API

🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-17

OpenAI-compatible API on Hetzner’s own EU hardware, free for as long as the experiment runs

Provider-wide limits

Free while the Inference API remains experimental; Hetzner says it will email advance notice of a change. Per-key request and token windows both apply, with HTTP 429 at a cap. No daily, monthly or lifetime cap or end date is published. The service is offered as is for experimental use, without guaranteed availability or backups. Minting a token needs a Hetzner account; payment verification can include a card charge or other routes.

Alibaba Cloud Model Studio (DashScope, international)

🔌 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

Provider-wide limits

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.

IteraCompute

🔌 LLM APIs with free tier · no card · provisional since 2026-10-18 · last probe 2026-10-26 · listed since 2026-10-21

OpenAI-compatible API with recurring free usage on a self-hosted open model

Qwen Free tier: 160,000 tokens/minute per account; for qwen/qwen3.8-27b

Register and verify an email, or sign in with Google. Input and output, including reasoning, count across all account keys. “Context includes input and requested output; output is capped at 8,192 tokens.” Free total context is 128K. Requests reserve maximum usage, then settle actual usage. Exhausted quota returns 429 without automatic paid overage. No recharge is required; optional cumulative $10/$50 top-ups unlock larger allowances. Recharge thresholds use completed principal minus refunds, excluding grants and fees. Spending the balance keeps the tier; refunds may lower it. Shared capacity may queue; honor Retry-After. No SLA. Zero data retention requires a separate signed agreement.

Regolo AI

🎁 Trials (no card when possible) · no card · last probe 2026-10-26 · listed since 2026-09-17

EU (Italian) zero-retention inference; a month of full model access on a daily token allowance, no card

Provider-wide limits

“Start your 30-day free trial … No credit card required, no commitment”: the trial card names “1 month duration” (“Full access for 30 days, then choose a plan”), and “Stricter rate limits” with “Fair usage throttling applies”, against “All Core Models”, which on the same page is every chat model in the library table (each marked Included under Core). Nothing survives the 30 days — the page names no grant after it, only paid plans — and the daily figure is the only number the trial publishes. One model is priced at €0.00 in and out outside any trial, brick-v1-beta, and it is not one to code with: its own page calls it “a lightweight prompt-complexity classifier designed for LLM routing pipelines”, a Qwen3.5-0.8B LoRA that labels a prompt easy, medium or hard for Regolo’s Brick router (read 2026-09-21)

VLM Run Gateway

🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-17

OpenAI-compatible gateway whose GPU-served vision and language models accept anonymous callers — no signup or key — in beta

Provider-wide limits

GPU-served models are public and anonymous; frontier models require paid access. All three IP windows apply together and are shared by callers behind the same NAT or proxy. The gateway is beta; anonymous access is intended for evaluation. The operator is Autonomi AI Inc.; its terms render in a browser.

OVHcloud AI Endpoints

🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-17

EU-hosted serverless API for open models, with anonymous OpenAI-compatible access and no signup, key or card

Provider-wide limits

The documentation attributes the anonymous cap to IP and model. Tests on 2026-09-24 instead observed callers sharing a model’s anonymous capacity, so its effective sharing scope remains disputed. Anonymous requests can receive 429 before a caller has spent the documented cap. Authenticated API keys are metered per token and use the paid project/model limits; they do not create a larger free allowance.

Rows that listed it before

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.

Something wrong or missing? Suggest a service or a change — or read how the list works.