anytimelime — the free AI field report

2026-10-04 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free in AI right now — 2026-10-04

This morning’s headline is a quiet shuffle. Four models have just unlocked tool‑use after a brief hiatus: google/diffusiongemma-26b-a4b-it (1.0 s), poolside/laguna-xs-2.1:free (0.6 s), qwen/qwen3.8-27b:free (0.2 s) and nvidia/ising-calibration-1.5-31b (0.6 s). In the same turnover, tokeness/free has vanished behind a 60‑second timeout, a harsh reminder that “free” is a temporary badge. Meanwhile, inclusionai/ling-3.1-flash (OpenRouter) sits quietly behind a payment wall — the probe never reached the model, but the endpoint still reports a credit‑required block.

The day’s usable lineup feels like a speed‑run through a handful of dependable workhorses. If latency is your north star, openai/gpt-oss-120b:free (0.9 s) and the Pollinations openai endpoint (0.3 s) stay sub‑second while retaining tool capability. The newly tool‑capable diffusion model, google/diffusiongemma-26b-a4b-it, offers a rare blend of visual reasoning and sub‑two‑second response, making it a niche pick for image‑aware tasks. A few high‑latency free tools still survive the shuffle: nvidia/nemotron-3.5-lightning:free pings at 37.6 s, yet passes the tool test, proving that “free” does not always mean “fast.” Older stand‑bys such as aion-labs/aion-3.0 (1.6 s) and cohere/north-mini-code:free keep humming without breaking a sweat.

For builders who rely on free tiers, today’s churn underlines a simple rule: rotate early, rotate often. The roster flipped in two directions at once — fresh tool‑capable entries and abrupt disappearances — while a handful of models that once answered tools now sit behind a paywall or error out. Treat the free pool as a living circuit; a model that answered yesterday can be silent tomorrow, and a “free” label can be stripped without warning. The latency spread from fractions of a second to minute‑long waits means any production script should prioritize speed first, then keep a fallback queue in motion before the next lock‑out hits.

To spin your own free‑tier spinner, grab the repo, drop your OpenRouter key into LIME_KEY, fire up lime.sh, and let it rotate through today’s verified models; your key stays locked in your terminal. That’s the whole cycle.

Today's passing roster

openai — Pollinations · 0.3s · agentic 3/5
openai — Pollinations · 0.3s · agentic 3/5
liquid/lfm-2.5-2.6b:free — openrouter · 0.5s · agentic 3/5
poolside/laguna-xs-2.1:free — openrouter · 0.6s · agentic 3/5
qwen/qwen3.8-27b:free — openrouter · 0.6s · agentic 3/5
nvidia/ising-calibration-1.5-31b — nvidia · 0.6s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b — nvidia · 0.6s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b:free — openrouter · 0.7s · agentic 3/5
inclusionai/ling-3.0-flash-sante:free — openrouter · 0.8s · agentic 3/5
openai/gpt-oss-120b:free — FastRouter · 0.9s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b — nvidia · 0.9s · agentic 3/5
meta-llama/Llama-3.3-70B-Instruct — Hugging Face Inference · 1.0s · agentic 3/5
openai/gpt-oss-20b:free — FastRouter · 1.0s · agentic 3/5
google/diffusiongemma-26b-a4b-it — nvidia · 1.0s · agentic 3/5
openrouter/free — openrouter · 1.0s · agentic 3/5
apodex/apodex-1.1-mini:free — openrouter · 1.2s · agentic 3/5
qwen3-8b — Free.ai · 1.2s · agentic 3/5
typhoon-v2.5-30b-a3b-instruct — Typhoon (SCB 10X) · 1.2s · agentic 3/5
poolside/laguna-s-2.1:free — openrouter · 1.2s · agentic 3/5
deepseek-ai/DeepSeek-V3-0324 — HuggingFace Inference Router · 1.3s · agentic 3/5
openai-fast — Pollinations · 1.3s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b:free — openrouter · 1.3s · agentic 3/5
stealth/space-bunny-alpha — openrouter · 1.3s · agentic 3/5
Qwen/Qwen3-Coder-480B-A35B-Instruct — HuggingFace Router · 1.4s · agentic 3/5
agnes-3.0-flash — Agnes AI · 1.4s · agentic 3/5
dots-studio/dots-3-note-preview:free — openrouter · 1.4s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — openrouter · 1.4s · agentic 3/5
aion-labs/aion-3.0 — AION Labs · 1.6s · agentic 3/5
cohere/north-mini-code:free — openrouter · 1.6s · agentic 3/5
intern-s2-preview — Intern AI · 1.6s · agentic 3/5
nemotron-3-super-120b-a12b:free — Naga AI · 1.7s · agentic 3/5
north-mini-code — TokenReply · 1.7s · agentic 3/5
qwen/qwen3.5-4b-free — Mixlayer · 1.7s · agentic 3/5
meta/llama-3.2-11b-vision-instruct — nvidia · 1.7s · agentic 3/5
glm-4.7-flash — Zhipu AI (Z.ai) · 2.8s · agentic 3/5
glm-4.7-flash — Zhipu AI (Z.ai) · 2.8s · agentic 3/5
nvidia/nemotron-3.5-lightning-30b-a3b — nvidia · 3.5s · agentic 3/5
meta/muse-glimmer-30b — nvidia · 3.7s · agentic 3/5
zai-org/GLM-5.3-Flash — Gonka Broker · 5.2s · agentic 3/5
MiniMaxAI/MiniMax-M2.7 — Gonka Broker · 6.3s · agentic 3/5
moonshotai/kimi-k3 — nvidia · 8.4s · agentic 3/5
meta/llama-3.2-90b-vision-instruct — nvidia · 11.7s · agentic 3/5
MiniMax-M2.7-Official — Pooled AI · 12.8s · agentic 3/5
nvidia/nemotron-3.5-lightning:free — openrouter · 37.6s · agentic 3/5
google/gemma-4-31b-it — nvidia · 42.1s · 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
0.4	`01-ai/yi-large`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`DeepSeek-V3.1`	sambanova	untested	DOWN	—	✗	✗	✗
12.8	`MiniMax-M2.7-Official`	Pooled AI	yes	FREE	3/5	✓	✓	✓
6.3	`MiniMaxAI/MiniMax-M2.7`	Gonka Broker	yes	FREE	3/5	✓	✓	✓
1.4	`Qwen/Qwen3-Coder-480B-A35B-Instruct`	HuggingFace Router	yes	FREE	3/5	✓	✓	✓
1.4	`agnes-3.0-flash`	Agnes AI	yes	FREE	3/5	✓	✓	✓
1.6	`aion-labs/aion-3.0`	AION Labs	yes	FREE	3/5	✓	✗	✓
0.5	`aisingapore/Qwen-SEA-LION-v4.5-27B-IT`	SEA-LION (AI Singapore)	yes (past)	DOWN	—	✗	✗	✗
1.2	`apodex/apodex-1.1-mini:free`	openrouter	yes	FREE	3/5	✓	✓	·
0.3	`codestral-latest`	Mistral	yes (past)	DOWN	—	✗	✗	✗
1.3	`deepseek-ai/DeepSeek-V3-0324`	HuggingFace Inference Router	yes	FREE	3/5	✓	✓	✓
0.4	`deepseek-ai/DeepSeek-V3.1`	SiliconFlow	yes (past)	DOWN	—	✗	✗	✗
0.1	`deepseek-ai/deepseek-v4-flash-0731`	NVIDIA NIM	yes (past)	DOWN	—	✗	✗	✗
0.5	`glm-4.5-flash`	Zhipu AI (Z.ai)	yes (past)	DOWN	—	✗	✗	✗
2.8	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes	FREE	3/5	✓	✗	✗
1.0	`intern-latest`	Intern AI	yes (past)	DOWN	—	✗	✗	✗
1.0	`meta-llama/Llama-3.3-70B-Instruct`	Hugging Face Inference	yes	FREE	3/5	✓	✓	·
0.4	`minimax/minimax-m3:free`	xKiro AI	yes (past)	DOWN	—	✗	✓	✗
1.7	`nemotron-3-super-120b-a12b:free`	Naga AI	yes	FREE	3/5	✓	✓	✓
1.7	`north-mini-code`	TokenReply	yes	FREE	3/5	✓	✓	✓
1.3	`openai-fast`	Pollinations	yes	FREE	3/5	✓	✓	·
0.9	`openai/gpt-oss-120b:free`	FastRouter	yes	FREE	3/5	✓	✓	✓
0.3	`openai`	Pollinations	yes	FREE	3/5	✓	✓	✓
1.7	`qwen/qwen3.5-4b-free`	Mixlayer	yes	FREE	3/5	✓	✓	✓
1.2	`qwen3-8b`	Free.ai	yes	FREE	3/5	✓	✓	✓
0.2	`qwen3.8-27b`	Yolo-Auto	yes (past)	DOWN	—	✗	✗	✗
60.1	`tokeness/free`	Tokeness	yes (past)	DOWN	—	✓	✓	✗
1.2	`typhoon-v2.5-30b-a3b-instruct`	Typhoon (SCB 10X)	yes	FREE	3/5	✓	✓	✓
0.1	`adept/fuyu-8b`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`DeepSeek-V3.2`	sambanova	untested	DOWN	—	✗	✗	✗
0.6	`deepseek-ai/DeepSeek-V4-Flash-0731`	Gonka Broker	yes (past)	DOWN	—	✗	✗	✗
1.6	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.3	`inclusionAI/Ling-flash-2.0`	SiliconFlow	yes (past)	DOWN	—	✗	✗	✗
2.8	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes	FREE	3/5	✓	✗	✗
1.6	`intern-s2-preview`	Intern AI	yes	FREE	3/5	✓	✓	✓
0.3	`openai`	Pollinations	yes	FREE	3/5	✓	✓	✓
1.0	`openai/gpt-oss-20b:free`	FastRouter	yes	FREE	3/5	✓	✓	✓
0.2	`ai21labs/jamba-1.5-large-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`Meta-Llama-3.3-70B-Instruct`	sambanova	untested	DOWN	—	✗	✗	✗
5.2	`zai-org/GLM-5.3-Flash`	Gonka Broker	yes	FREE	3/5	✓	✓	✓
1.4	`dots-studio/dots-3-note-preview:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`aisingapore/sea-lion-7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`MiniMax-M3`	sambanova	untested	DOWN	—	✗	✗	✗
0.4	`google/gemma-4-26b-a4b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.1	`bigcode/starcoder2-15b`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`gemma-4-31B-it`	sambanova	untested	DOWN	—	✗	✗	✗
0.3	`google/gemma-4-31b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.1	`databricks/dbrx-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`gpt-oss-120b`	sambanova	untested	DOWN	—	✗	✗	✗
0.8	`inclusionai/ling-3.0-flash-sante:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`deepseek-ai/deepseek-coder-6.7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`inclusionai/ling-3.1-flash`	openrouter	untested	CARD	—	✗	·	·
60.1	`deepseek-ai/deepseek-v4.1-flash`	nvidia	untested	DOWN	—	✗	✗	✗
0.5	`liquid/lfm-2.5-2.6b:free`	openrouter	yes	FREE	3/5	✓	✓	✗
0.2	`google/codegemma-1.1-7b`	nvidia	untested	DOWN	—	✗	✗	✗
1.4	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	openrouter	yes	FREE	3/5	✓	✗	✓
0.1	`google/codegemma-7b`	nvidia	untested	DOWN	—	✗	✗	✗
0.7	`nvidia/nemotron-3-super-120b-a12b:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/deplot`	nvidia	untested	DOWN	—	✗	✗	✗
1.3	`nvidia/nemotron-3-ultra-550b-a55b:free`	openrouter	yes	FREE	3/5	✓	✓	✓
1.0	`google/diffusiongemma-26b-a4b-it`	nvidia	yes	FREE	3/5	✗	✓	✓
0.1	`nvidia/nemotron-3.5-content-safety:free`	openrouter	untested	DOWN	—	✗	✗	✗
0.2	`google/gemma-2b`	nvidia	untested	DOWN	—	✗	✗	✗
37.6	`nvidia/nemotron-3.5-lightning:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/gemma-3-12b-it`	nvidia	untested	DOWN	—	✗	✗	✗
1.0	`openrouter/free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/gemma-3-4b-it`	nvidia	untested	DOWN	—	✗	✗	✗
1.2	`poolside/laguna-s-2.1:free`	openrouter	yes	FREE	3/5	✓	✗	✓
42.1	`google/gemma-4-31b-it`	nvidia	yes	FREE	3/5	✓	✓	✓
0.6	`poolside/laguna-xs-2.1:free`	openrouter	yes	FREE	3/5	✗	✓	✗
0.1	`google/recurrentgemma-2b`	nvidia	untested	DOWN	—	✗	✗	✗
0.6	`qwen/qwen3.8-27b:free`	openrouter	yes	FREE	3/5	✗	✗	✗
0.1	`ibm/granite-3.0-3b-a800m-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
1.3	`stealth/space-bunny-alpha`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`ibm/granite-3.0-8b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`ibm/granite-34b-code-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`ibm/granite-8b-code-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`meta/codellama-70b`	nvidia	untested	DOWN	—	✗	✗	✗
1.7	`meta/llama-3.2-11b-vision-instruct`	nvidia	yes	FREE	3/5	✓	✓	✓
11.7	`meta/llama-3.2-90b-vision-instruct`	nvidia	yes	FREE	3/5	✓	✓	✗
0.2	`meta/llama2-70b`	nvidia	untested	DOWN	—	✗	✗	✗
3.7	`meta/muse-glimmer-30b`	nvidia	yes	FREE	3/5	✓	✓	✓
0.1	`microsoft/kosmos-2`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`microsoft/phi-3-vision-128k-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`microsoft/phi-3.5-moe-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`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	—	✗	✗	✗
0.1	`mistralai/mixtral-8x22b-v0.1`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`moonshotai/kimi-k2.6`	nvidia	untested	DOWN	—	✗	✗	✗
8.4	`moonshotai/kimi-k3`	nvidia	yes	FREE	3/5	✓	✓	✓
0.1	`nv-mistralai/mistral-nemo-12b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/ai-synthetic-video-detector`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/cosmos-reason2-8b`	nvidia	untested	DOWN	—	✗	✗	✗
0.6	`nvidia/ising-calibration-1.5-31b`	nvidia	yes	FREE	3/5	✓	✓	✓
0.1	`nvidia/llama-3.1-nemotron-51b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/llama-3.1-nemotron-70b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/llama-3.1-nemotron-ultra-253b-v1`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/llama3-chatqa-1.5-70b`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/mistral-nemo-minitron-8b-8k-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	nvidia	yes (past)	DOWN	—	✗	✗	✗
0.6	`nvidia/nemotron-3-super-120b-a12b`	nvidia	yes	FREE	3/5	✓	✓	✗
0.9	`nvidia/nemotron-3-ultra-550b-a55b`	nvidia	yes	FREE	3/5	✓	✓	✓
0.1	`nvidia/nemotron-3.5-content-safety`	nvidia	untested	DOWN	—	✗	✗	✗
3.5	`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	—	✗	✗	✗
0.2	`nvidia/nemotron-parse-2.0`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/nemotron-parse`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/neva-22b`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`nvidia/nvclip`	nvidia	untested	DOWN	—	✗	✗	✗
1.3	`nvidia/riva-translate-4b-instruct-v1.1`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/riva-translate-4b-instruct-v2`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/riva-translate-4b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗

44 made a tool call, 0 answered in text only, of 116 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.