anytimelime — the free AI field report

2026-09-11 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free right now

8 free models made a real tool call today, out of 24 discovered, and the morning diff tells the story: deepseek-ai/deepseek-v4-flash-0731 joined the tool-call club today. The table below is measured, not marketed — each model got a real request with a real tool schema, timed from request to response. It says nothing a catalog can't; what it doesn't say is how long any of this survives.

How to use them with AnytimeLime

Clone the engine from github.com/fusionpoweredsoftware/anytimelime, set LIME_KEY to your OpenRouter key, and run ./lime.sh. It fetches today's verified roster and rotates across the passing models so no single free tier carries all your traffic. Your key stays on your own machine — the website never asks for it.

The churn

Free rosters change weekly — models die, rate-limit, or resurrect without notice. Last week's config is this week's outage. Re-squeeze before you depend on it.

Today's passing roster

inclusionai/ling-3.0-flash-fin:free — openrouter · 0.7s · agentic 3/5
deepseek-ai/deepseek-v4-flash-0731 — nvidia · 0.7s · agentic 3/5
inclusionai/ling-3.0-flash-sante:free — openrouter · 0.9s · agentic 3/5
liquid/lfm-2.5-2.6b:free — openrouter · 0.9s · agentic 3/5
inclusionai/ling-3.0-flash-vl:free — openrouter · 1.3s · agentic 3/5
dots-studio/dots-3-note-preview:free — openrouter · 1.8s · agentic 3/5
cohere/north-mini-code:free — openrouter · 1.9s · agentic 3/5
deepseek-ai/deepseek-v4-pro-0813 — nvidia · 10.6s · agentic 3/5

The measured table

Click any model for its endpoint and ready-to-run snippets in curl, Python, Go, Rust, and more.

latency	model	vendor	tool call	free now	agentic
0.2	`01-ai/yi-large`	nvidia	untested	DOWN	—
1.9	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5
0.3	`DeepSeek-V3.1`	sambanova	untested	CARD	—
0.2	`adept/fuyu-8b`	nvidia	untested	DOWN	—
1.8	`dots-studio/dots-3-note-preview:free`	openrouter	yes	FREE	3/5
0.3	`DeepSeek-V3.2`	sambanova	untested	CARD	—
0.1	`ai21labs/jamba-1.5-large-instruct`	nvidia	untested	DOWN	—
0.3	`google/gemma-4-26b-a4b-it:free`	openrouter	yes (past)	DOWN	—
0.3	`Meta-Llama-3.3-70B-Instruct`	sambanova	untested	CARD	—
0.1	`aisingapore/sea-lion-7b-instruct`	nvidia	untested	DOWN	—
0.3	`google/gemma-4-31b-it:free`	openrouter	yes (past)	DOWN	—
0.3	`MiniMax-M2.7`	sambanova	untested	CARD	—
0.1	`bigcode/starcoder2-15b`	nvidia	untested	DOWN	—
0.7	`inclusionai/ling-3.0-flash-fin:free`	openrouter	yes	FREE	3/5
0.3	`MiniMax-M3`	sambanova	untested	CARD	—
0.1	`databricks/dbrx-instruct`	nvidia	untested	DOWN	—
0.9	`inclusionai/ling-3.0-flash-sante:free`	openrouter	yes	FREE	3/5
0.3	`gemma-4-31B-it`	sambanova	untested	CARD	—
0.1	`deepseek-ai/deepseek-coder-6.7b-instruct`	nvidia	untested	DOWN	—
1.3	`inclusionai/ling-3.0-flash-vl:free`	openrouter	yes	FREE	3/5
0.3	`gpt-oss-120b`	sambanova	untested	CARD	—
0.7	`deepseek-ai/deepseek-v4-flash-0731`	nvidia	yes	FREE	3/5
0.9	`liquid/lfm-2.5-2.6b:free`	openrouter	yes	FREE	3/5
10.6	`deepseek-ai/deepseek-v4-pro-0813`	nvidia	yes	FREE	3/5

8 made a tool call, 0 answered in text only, of 24 discovered. A fail only means the endpoint wasn't free to use right then — it demanded a payment method, or it was down or erroring — so tool-call ability stayed untested, not disproven; a model that passed in a past report keeps its yes. Numbers are single-run measurements from one location — your mileage will vary. Prose by fallback (no model produced usable prose); the table is measured, never model-written. Reproduce with ./free-scan.sh from the engine repo.