Free AI Models

Free models are for experimenting, learning and shipping without a bill — AIHubMix covers the inference cost for all 56 models on this page, and every model answers all three protocols: Chat Completions, Messages and Responses. Every account starts with 10 trial calls, no credit card, and a $1 top-up switches you to permanent daily quotas.

56 models14 model authorsEvery model $0/M input & outputUpdated 2026-09-07

Before your first top-up

No credit card required, and trial calls never expire.

Trial calls 10 total, all free models

After a one-time $1 top-upRecommended

Top up once — any amount from $1 — and every free model switches to daily quotas with no expiry, reset every day.

Requests 100/dayRequests 10/minTokens 1M/dayResets daily

Usage

Last 30 days · 2026-08-09 to 2026-09-07

Tokens

36.7B

Requests

286K

Models in use

56 of 56

Tokens per day, stacked by model

coding-glm-5.3-free
coding-glm-5.3-flash-free
coding-glm-5.2-free
coding-kimi-k3-free
coding-glm-5.1-free
xiaomi-mimo-v2.5-pro-free
coding-minimax-m3-free
hy3-free
41 more models

Which models that traffic went to

Share of 36.7B tokens. 7 models with traffic report no token counts and are only in the request view.

All 56 Free Models

Open in model list

All free models on AIHubMix, in catalog order, with developer, input and output modalities, context length and the rate limit each model allows on a topped-up account.
Model	Modalities	Context	Rate limit	Paid version
coding-glm-4.6-free	Takes text, returns text.	200K	100/day · 10/min	vs paid →
coding-glm-4.7-free	Takes text, returns text.	—	100/day · 10/min	vs paid →
coding-glm-5-free	Takes text, returns text.	—	100/day · 10/min	vs paid →
coding-glm-5-turbo-free	Takes text, returns text.	—	50/day · 5/min	vs paid →
coding-glm-5.1-free	Takes text, returns text.	—	100/day · 10/min	vs paid →
coding-glm-5.2-free	Takes text, returns text.	—	100/day · 10/min	vs paid →
coding-glm-5.3-flash-freeNew	—	—	100/day · 10/min	vs paid →
coding-glm-5.3-freeNew	Takes , returns text.	—	100/day · 10/min	vs paid →
coding-kimi-k3-free	Takes text, vision, video, returns text.	1.05M	100/day · 10/min	vs paid →
coding-minimax-m2-free	Takes text, returns text.	205K	100/day · 10/min	vs paid →
coding-minimax-m2.1-free	Takes text, returns text.	205K	100/day · 10/min	vs paid →
coding-minimax-m2.5-free	Takes text, returns text.	205K	100/day · 10/min	vs paid →
coding-minimax-m2.7-free	Takes text, returns text.	205K	100/day · 10/min	vs paid →
coding-minimax-m3-free	Takes text, returns text.	205K	100/day · 10/min	vs paid →
dots-3-note-preview-freeNew	Takes text, vision, returns text.	512K	100/day · 10/min	—
gemini-3-flash-preview-free	Takes text, vision, audio, video, returns text.	1.05M	33/day · 3/min	vs paid →
gemini-3.1-flash-image-preview-free	Takes text, vision, returns vision.	—	10/day · 1/min	vs paid →
gemini-3.5-flash-lite-free	Takes text, vision, audio, video, returns text.	1.05M	100/day · 10/min	vs paid →
gemini-3.6-flash-free	Takes text, vision, audio, video, returns text.	1M	100/day · 10/min	vs paid →
gemini-3.7-flash-freeNew	Takes text, vision, audio, video, returns text.	1M	100/day · 10/min	vs paid →
gemini-3.8-flash-freeNew	Takes text, vision, audio, video, returns text.	1M	100/day · 10/min	vs paid →
gemma-4-26b-a4b-it-free	Takes text, vision, returns text.	262K	100/day · 10/min	vs paid →
gemma-4-31b-it-free	Takes text, vision, returns text.	262K	100/day · 10/min	vs paid →
glm-4.7-flash-free	Takes text, returns text.	—	100/day · 10/min	—
gpt-4.1-free	Takes text, vision, returns text.	1.05M	20/day · 2/min	vs paid →
gpt-4.1-mini-free	Takes text, vision, returns text.	1.05M	33/day · 3/min	vs paid →
gpt-4.1-nano-free	Takes text, vision, returns text.	1.05M	50/day · 5/min	vs paid →
gpt-4o-free	Takes text, vision, returns text.	1.05M	20/day · 2/min	vs paid →
gpt-5.5-free	Takes text, vision, returns text.	1.05M	100/day · 10/min	vs paid →
gpt-image-2-free	Takes text, vision, returns text, vision.	—	100/day · 10/min	vs paid →
gpt-oss-20b-free	Takes text, returns text.	131K	100/day · 10/min	vs paid →
hy3-freeNew	Takes text, returns text.	256K	100/day · 10/min	vs paid →
k2.6-code-preview-free	Takes text, returns text.	256K	50/day · 5/min	—
kimi-for-coding-free	Takes text, returns text.	256K	100/day · 10/min	—
laguna-s-2.1-free	Takes text, returns text.	262K	100/day · 10/min	—
laguna-xs-2.1-free	Takes text, returns text.	262K	100/day · 10/min	—
lfm-2.5-2.6b-freeNew	Takes text, returns text.	128K	100/day · 10/min	—
ling-3.0-flash-free	Takes text, returns text.	262K	100/day · 10/min	—
ling-3.0-tiny-freeNew	Takes text, returns text.	262K	100/day · 10/min	—
mimo-v2-flash-free	Takes text, returns text.	256K	100/day · 10/min	vs paid →
minimax-m2.7-freeNew	Takes text, returns text.	197K	100/day · 10/min	vs paid →
minimax-m3-freeNew	Takes text, vision, returns text.	1.05M	100/day · 10/min	vs paid →
nemotron-3-nano-30b-a3b-free	Takes text, returns text.	256K	100/day · 10/min	—
nemotron-3-nano-omni-30b-a3b-reasoning-free	Takes text, vision, returns text.	256K	100/day · 10/min	—
nemotron-3-super-120b-a12b-free	Takes text, returns text.	262K	100/day · 10/min	—
nemotron-3-ultra-550b-a55b-free	Takes text, returns text.	1M	100/day · 10/min	—
nemotron-3.5-content-safety-free	Takes text, vision, returns text.	128K	100/day · 10/min	—
nemotron-3.5-lightning-freeNew	Takes text, returns text.	1M	100/day · 10/min	—
nemotron-nano-12b-v2-vl-free	Takes text, vision, returns text.	128K	100/day · 10/min	—
nemotron-nano-9b-v2-free	Takes text, returns text.	128K	100/day · 10/min	—
north-mini-code-free	Takes text, returns text.	256K	100/day · 10/min	—
qwen3.6-plus-preview-free	Takes text, returns text.	1M	50/day · 5/min	—
xiaomi-mimo-v2-omni-free	Takes text, vision, audio, video, returns text.	256K	100/day · 10/min	—
xiaomi-mimo-v2-pro-free	Takes text, vision, audio, video, returns text.	256K	100/day · 10/min	—
xiaomi-mimo-v2.5-free	Takes text, vision, audio, video, returns text.	256K	100/day · 10/min	—
xiaomi-mimo-v2.5-pro-free	Takes text, vision, audio, video, returns text.	256K	100/day · 10/min	—

Rate limit shows the daily and per-minute request caps for topped-up accounts. Some models carry a higher request weight — one call counts as several requests — which is why their caps are lower. All free models share one pool of 1M tokens per day. Before your first top-up, the 10 trial calls apply instead. Context “—” means the value is not published in the catalog. Modalities read input → output — the same fact the developer pages show; a missing output side means the catalog does not publish it, not that the model returns nothing.

How to Start

1
Create an account
Email or OAuth, no credit card required. 10 trial calls are available immediately.
2
Create an API key
One key works for every model on the platform, free and paid alike. Open the API keys page →
3
Call a free model
Point any OpenAI-compatible client — Cursor, Cline, Cherry Studio, LiteLLM — at the gateway and pick a -free model ID.

POST /v1/chat/completions

curl https://aihubmix.com/v1/chat/completions \

-H "Authorization: Bearer sk-***" \

-H "Content-Type: application/json" \

-d '{

"model": "coding-glm-5.3-free",

"messages": [{"role":"user","content":"Hi"}]

}' # hy3-free / coding-glm-5.3-flash-free

A -free ID like coding-glm-5.3-free — the most-called free model this month — is the same upstream model as Coding GLM 5.3, served as a subsidized free variant. Swap the suffix off when you need paid throughput; nothing else in your code changes.

Free Models on AIHubMix

Are these models really free?

Yes. All 56 models bill $0 for input and output tokens. AIHubMix subsidizes the inference cost; usage is bounded by quotas instead of a bill.

What do I get before topping up?

10 trial calls, shared across all free models, with no expiry. When they run out the API keeps answering with a note that the trial is used up — your integration never sees a hard error.

What do I get after topping up?

Any top-up of $1 or more permanently switches your account to daily quotas: 10 requests per minute, 100 requests per day and 1M tokens per day, shared across the free catalog and reset every day. Models with a higher request weight count as several requests per call — the exact caps are in the table. Past a cap the API returns 429 until the next minute or day starts.

What is the difference between Coding GLM 5.3 (free) and Coding GLM 5.3?

Price is the only difference — they are the same upstream model with identical capability. The -free ID bills $0 within the quotas above; the paid ID bills per token with no daily cap. Switching between them is a one-line model-name change.

Keep Exploring

All Models

The full catalog — 880 models across chat, image, video and audio, with per-token pricing.

Browse all models →

LLM Router

Fill in auto as the model ID and the gateway routes each request to the optimal model by cost and quality.

Try the router →

Apps

Ready-to-use apps in the AIHubMix app store — and model discounts beyond the free catalog.

Browse the app store →

Free AI Models

Before your first top-up

After a one-time $1 top-upRecommended

Usage

Which models that traffic went to

All 56 Free Models

How to Start

Create an account

Create an API key

Call a free model

Free Models on AIHubMix

Keep Exploring

All Models

LLM Router

Apps

Product

Company

Developer

Connect