anytimelime — the free AI field report

2026-09-23 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free in AI right now — 2026-09-23

Today's free‑AI frontier is a study in opposites. A dozen models that had never spoken tools before just found their voice — MiniMax‑M2.7‑Official, agnes‑3.0‑flash, aion‑labs/aion‑3.0, deepseek‑ai/DeepSeek‑V3‑0324, glm‑4.5‑flash, glm‑4.7‑flash, and intern‑latest all logged clean tool calls on their first probe. The newcomers are noisy enough to keep a rotation script busy, and the latency spread is already carving out clear winners: agnes‑3.0‑flash at 1.8 s, deepseek‑ai/DeepSeek‑V3‑0324 at 1.2 s, and the zhipu AI glm‑4.5‑flash at a brisk 4.3 s.

While the rookies debut, the old reliable suffer setbacks. The inclusionai flash line has a new missing link: ling‑3.0‑flash‑vl:free disappeared after a solid run, and poolside/laguna‑xs‑2.1:free also vanished overnight. The steady‑hand crew that survived the last shake‑out (inclusionai/ling‑3.0‑flash‑fin:free, liquid/lfm‑2.5‑2.6b:free, cohere/north‑mini‑code:free) are still the workhorses, but the day’s churn reminds anyone building on free tiers that rotation isn’t a convenience — it’s survival.

Behind the scenes the SambaNova paywall keeps its slow crawl. DeepSeek‑V3.1, DeepSeek‑V3.2, Meta‑Llama‑3.3‑70B‑Instruct, MiniMax‑M2.7, MiniMax‑M3, gemma‑4‑31B‑it and gpt‑oss‑120b all sit behind a “add a payment method” screen. The probe never reached them, so the models themselves may still call tools if you can get past the gate — the endpoint flaked, not the model.

Running the day’s viable cast is now a matter of trusting the script. Clone the engine from github.com/fusionpoweredsoftware/anytimelime, set LIME_KEY to an OpenRouter key, and fire ./lime.sh. It pulls today’s verified roster, skips the empty‑response dead ends, and rotates across the passing models so no single free tier is overwhelmed. Your key never leaves the box.

Today's passing roster

openai — Pollinations · 0.5s · agentic 3/5
openai — Pollinations · 0.5s · agentic 3/5
liquid/lfm-2.5-2.6b:free — openrouter · 0.5s · agentic 3/5
meta/llama-3.2-11b-vision-instruct — nvidia · 0.6s · agentic 3/5
openai/gpt-oss-120b:free — FastRouter · 0.7s · agentic 3/5
openrouter/free — openrouter · 0.8s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b — nvidia · 0.8s · agentic 3/5
openai-fast — Pollinations · 1.0s · agentic 3/5
inclusionai/ling-3.0-flash-fin:free — openrouter · 1.1s · agentic 3/5
inclusionai/ling-3.0-flash-sante:free — openrouter · 1.1s · agentic 3/5
deepseek-ai/DeepSeek-V3-0324 — HuggingFace Inference Router · 1.2s · agentic 3/5
stealth/space-bunny-alpha — openrouter · 1.3s · agentic 3/5
google/diffusiongemma-26b-a4b-it — nvidia · 1.4s · agentic 3/5
qwen/qwen3.5-4b-free — Mixlayer · 1.5s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b — nvidia · 1.5s · agentic 3/5
qwen3.8-27b — Yolo-Auto · 1.6s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b:free — openrouter · 1.6s · agentic 3/5
nvidia/nemotron-3.5-lightning:free — openrouter · 1.6s · agentic 3/5
dots-studio/dots-3-note-preview:free — openrouter · 1.7s · agentic 3/5
dots-studio/dots-3-note-preview:free — openrouter · 1.7s · agentic 3/5
agnes-3.0-flash — Agnes AI · 1.8s · agentic 3/5
qwen3-8b — Free.ai · 1.8s · agentic 3/5
nemotron-3-super-120b-a12b:free — Naga AI · 1.8s · agentic 3/5
minimax/minimax-m3:free — xKiro AI · 1.9s · agentic 3/5
cohere/north-mini-code:free — openrouter · 2.2s · agentic 3/5
cohere/north-mini-code:free — openrouter · 2.2s · agentic 3/5
aion-labs/aion-3.0 — AION Labs · 2.3s · agentic 3/5
intern-latest — Intern AI · 2.3s · agentic 3/5
glm-4.7-flash — CloudCode.ONE · 2.5s · agentic 3/5
glm-4.7-flash — CloudCode.ONE · 2.5s · agentic 3/5
poolside/laguna-s-2.1:free — openrouter · 3.7s · agentic 3/5
MiniMax-M2.7-Official — Pooled AI · 4.0s · agentic 3/5
glm-4.5-flash — Zhipu AI (Z.ai) · 4.3s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning — nvidia · 4.4s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — openrouter · 4.7s · agentic 3/5
north-mini-code — TokenReply · 6.1s · agentic 3/5
MiniMaxAI/MiniMax-M2.7 — Gonka Broker · 8.4s · agentic 3/5
meta/muse-glimmer-30b — nvidia · 10.2s · agentic 3/5
zai-org/GLM-5.3-Flash — Gonka Broker · 10.3s · agentic 3/5
nvidia/nemotron-3.5-lightning-30b-a3b — nvidia · 14.9s · agentic 3/5
tokeness/free — Tokeness · 19.2s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b:free — openrouter · 32.7s · agentic 3/5
google/gemma-4-31b-it — nvidia · 41.4s · 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	yesterday	3 days ago	a week ago
0.2	`@cf/meta/llama-3.1-8b-instruct`	Cloudflare Workers AI	untested	DOWN	—	·	·	·
4.0	`MiniMax-M2.7-Official`	Pooled AI	yes	FREE	3/5	·	·	·
2.1	`THUDM/GLM-Z1-9B-0414`	SiliconFlow	untested	DOWN	—	·	·	·
1.8	`agnes-3.0-flash`	Agnes AI	yes	FREE	3/5	·	·	·
2.3	`aion-labs/aion-3.0`	AION Labs	yes	FREE	3/5	·	·	·
0.8	`am/free`	AnyModel	untested	DOWN	—	·	·	·
1.0	`auto:free`	BazaarLink	untested	DOWN	—	·	·	·
1.2	`deepseek-ai/DeepSeek-V3-0324`	HuggingFace Inference Router	yes	FREE	3/5	·	·	·
4.3	`glm-4.5-flash`	Zhipu AI (Z.ai)	yes	FREE	3/5	·	·	·
2.5	`glm-4.7-flash`	CloudCode.ONE	yes	FREE	3/5	·	·	·
2.5	`glm-4.7-flash`	CloudCode.ONE	yes	FREE	3/5	·	·	·
0.3	`gpt-oss:120b`	Ollama Cloud	untested	DOWN	—	·	·	·
2.3	`intern-latest`	Intern AI	yes	FREE	3/5	·	·	·
1.2	`muse-glimmer-30b:free`	Routeway AI	untested	DOWN	—	·	·	·
—	`nemotron-3-ultra-max`	Zydit AI	untested	DOWN	—	·	·	·
0.7	`openai/gpt-oss-120b:free`	FastRouter	yes	FREE	3/5	·	·	·
0.3	`orcarouter/free`	Orcarouter	untested	DOWN	—	·	·	·
1.5	`qwen/qwen3.5-4b-free`	Mixlayer	yes	FREE	3/5	·	·	·
1.8	`qwen3-8b`	Free.ai	yes	FREE	3/5	·	·	·
—	`qwen3.6-35b`	Hetzner AI Inference	untested	DOWN	—	·	·	·
1.3	`stealth/space-bunny-alpha`	openrouter	yes	FREE	3/5	·	·	·
0.3	`01-ai/yi-large`	nvidia	untested	DOWN	—	✗	✗	✗
0.5	`DeepSeek-V3.1`	sambanova	untested	CARD	—	✗	✗	✗
8.4	`MiniMaxAI/MiniMax-M2.7`	Gonka Broker	yes	FREE	3/5	✓	·	·
16.8	`aisingapore/Gemma-SEA-LION-v4-27B-IT`	SEA-LION	text-only	FREE	—	·	✗	·
0.3	`aisingapore/Qwen-SEA-LION-v4.5-27B-IT`	SEA-LION (AI Singapore)	yes (past)	DOWN	—	✗	·	✗
0.3	`codestral-latest`	Mistral	yes (past)	DOWN	—	✗	·	·
2.2	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5	✓	✓	✓
2.2	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`deepseek-ai/deepseek-v4-flash-0731`	NVIDIA NIM	yes (past)	DOWN	—	✗	✗	·
1.7	`dots-studio/dots-3-note-preview:free`	openrouter	yes	FREE	3/5	✓	✓	✓
—	`gpt-oss-20b`	Zylo API	untested	DOWN	—	·	·	·
0.3	`meganova-ai/manta-flash-1.0`	MegaNova AI	untested	DOWN	—	·	✗	✗
1.9	`minimax/minimax-m3:free`	xKiro AI	yes	FREE	3/5	·	·	·
1.8	`nemotron-3-super-120b-a12b:free`	Naga AI	yes	FREE	3/5	·	·	·
6.1	`north-mini-code`	TokenReply	yes	FREE	3/5	✓	·	·
1.0	`openai-fast`	Pollinations	yes	FREE	3/5	✓	·	·
0.5	`openai`	Pollinations	yes	FREE	3/5	✓	·	·
1.6	`qwen3.8-27b`	Yolo-Auto	yes	FREE	3/5	✗	·	✓
19.2	`tokeness/free`	Tokeness	yes	FREE	3/5	✓	✓	·
0.2	`adept/fuyu-8b`	nvidia	untested	DOWN	—	✗	✗	✗
0.5	`DeepSeek-V3.2`	sambanova	untested	CARD	—	✗	✗	✗
0.4	`deepseek-ai/DeepSeek-V4-Flash-0731`	Gonka Broker	yes (past)	DOWN	—	✗	·	·
1.7	`dots-studio/dots-3-note-preview:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.5	`openai`	Pollinations	yes	FREE	3/5	✓	·	·
0.2	`ai21labs/jamba-1.5-large-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`Meta-Llama-3.3-70B-Instruct`	sambanova	untested	CARD	—	✗	✗	✗
10.3	`zai-org/GLM-5.3-Flash`	Gonka Broker	yes	FREE	3/5	✓	✓	·
0.2	`google/gemma-4-26b-a4b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.2	`aisingapore/sea-lion-7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`MiniMax-M2.7`	sambanova	untested	CARD	—	✗	✗	✗
0.2	`google/gemma-4-31b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.1	`bigcode/starcoder2-15b`	nvidia	untested	DOWN	—	✗	✗	✗
0.9	`MiniMax-M3`	sambanova	untested	CARD	—	✗	✗	✗
1.1	`inclusionai/ling-3.0-flash-fin:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.2	`databricks/dbrx-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`gemma-4-31B-it`	sambanova	untested	CARD	—	✗	✗	✗
1.1	`inclusionai/ling-3.0-flash-sante:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.2	`deepseek-ai/deepseek-coder-6.7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`gpt-oss-120b`	sambanova	untested	CARD	—	✗	✗	·
0.5	`liquid/lfm-2.5-2.6b:free`	openrouter	yes	FREE	3/5	✓	✓	·
60.1	`deepseek-ai/deepseek-v4.1-flash`	nvidia	untested	DOWN	—	✗	·	·
47.4	`nex-agi/nex-n2.5-mini:free`	openrouter	yes (past)	DOWN	—	✗	✓	·
0.1	`google/codegemma-1.1-7b`	nvidia	untested	DOWN	—	✗	✗	·
47.3	`nex-agi/nex-n2.5-pro:free`	openrouter	yes (past)	DOWN	—	✗	✓	·
0.2	`google/codegemma-7b`	nvidia	untested	DOWN	—	✗	✗	·
4.7	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	openrouter	yes	FREE	3/5	✗	✗	·
0.2	`google/deplot`	nvidia	untested	DOWN	—	✗	✗	·
1.6	`nvidia/nemotron-3-super-120b-a12b:free`	openrouter	yes	FREE	3/5	✓	✗	·
1.4	`google/diffusiongemma-26b-a4b-it`	nvidia	yes	FREE	3/5	✓	✓	·
32.7	`nvidia/nemotron-3-ultra-550b-a55b:free`	openrouter	yes	FREE	3/5	✗	✓	·
0.2	`google/gemma-2b`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/nemotron-3.5-content-safety:free`	openrouter	untested	DOWN	—	✗	✗	·
0.1	`google/gemma-3-12b-it`	nvidia	untested	DOWN	—	✗	✗	·
1.6	`nvidia/nemotron-3.5-lightning:free`	openrouter	yes	FREE	3/5	✓	✓	·
0.1	`google/gemma-3-4b-it`	nvidia	untested	DOWN	—	✗	✗	·
0.8	`openrouter/free`	openrouter	yes	FREE	3/5	✓	✓	·
41.4	`google/gemma-4-31b-it`	nvidia	yes	FREE	3/5	✓	✓	·
3.7	`poolside/laguna-s-2.1:free`	openrouter	yes	FREE	3/5	✗	✗	·
0.3	`google/recurrentgemma-2b`	nvidia	untested	DOWN	—	✗	✗	·
0.7	`poolside/laguna-xs-2.1:free`	openrouter	yes (past)	DOWN	—	✓	✗	·
0.3	`ibm/granite-3.0-3b-a800m-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`qwen/qwen3.8-27b:free`	openrouter	yes (past)	DOWN	—	✗	✗	·
0.3	`ibm/granite-3.0-8b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`ibm/granite-34b-code-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`z-ai/glm-5.2:free`	openrouter	untested	DOWN	—	✗	✗	✗
0.2	`ibm/granite-8b-code-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`meta/codellama-70b`	nvidia	untested	DOWN	—	✗	✗	·
0.6	`meta/llama-3.2-11b-vision-instruct`	nvidia	yes	FREE	3/5	✓	✓	·
60.1	`meta/llama-3.2-90b-vision-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`meta/llama2-70b`	nvidia	untested	DOWN	—	✗	✗	·
10.2	`meta/muse-glimmer-30b`	nvidia	yes	FREE	3/5	✓	✓	·
0.2	`microsoft/kosmos-2`	nvidia	untested	DOWN	—	✗	✗	·
0.4	`microsoft/phi-3-vision-128k-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.4	`microsoft/phi-3.5-moe-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.4	`mistralai/codestral-22b-instruct-v0.1`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`mistralai/mistral-7b-instruct-v0.3`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`mistralai/mistral-large-2-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`mistralai/mistral-large`	nvidia	untested	DOWN	—	✗	✗	·
60.1	`mistralai/mistral-nemotron`	nvidia	yes (past)	DOWN	—	✗	✗	·
0.1	`mistralai/mixtral-8x22b-v0.1`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`moonshotai/kimi-k2.6`	nvidia	untested	DOWN	—	✗	✗	·
60.1	`moonshotai/kimi-k3`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nv-mistralai/mistral-nemo-12b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/ai-synthetic-video-detector`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/cosmos-reason2-8b`	nvidia	untested	DOWN	—	✗	✗	·
60.0	`nvidia/ising-calibration-1.5-31b`	nvidia	yes (past)	DOWN	—	✓	✓	·
0.1	`nvidia/llama-3.1-nemotron-51b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/llama-3.1-nemotron-70b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/llama-3.1-nemotron-ultra-253b-v1`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/llama3-chatqa-1.5-70b`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/mistral-nemo-minitron-8b-8k-instruct`	nvidia	untested	DOWN	—	✗	✗	·
4.4	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	nvidia	yes	FREE	3/5	✗	✓	·
0.8	`nvidia/nemotron-3-super-120b-a12b`	nvidia	yes	FREE	3/5	✗	✓	✓
1.5	`nvidia/nemotron-3-ultra-550b-a55b`	nvidia	yes	FREE	3/5	✓	✓	·
0.2	`nvidia/nemotron-3.5-content-safety`	nvidia	untested	DOWN	—	✗	✗	·
14.9	`nvidia/nemotron-3.5-lightning-30b-a3b`	nvidia	yes	FREE	3/5	✗	✗	·
0.1	`nvidia/nemotron-4-340b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/nemotron-4-340b-reward`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/nemotron-nano-3-30b-a3b`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/nemotron-parse-2.0`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/nemotron-parse`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/neva-22b`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/nvclip`	nvidia	untested	DOWN	—	✗	✗	·
1.9	`nvidia/riva-translate-4b-instruct-v1.1`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/riva-translate-4b-instruct`	nvidia	untested	DOWN	—	✗	✗	·

42 made a tool call, 1 answered in text only, of 126 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 cohere/north-mini-code:free; the table is measured, never model-written. Reproduce with ./free-scan.sh from the engine repo.