anytimelime — the free AI field report

2026-10-12 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free in AI right now — 2026-10-12

The most interesting move today is the churn of tool calls. Four models that had been silent or locked behind keys popped back online: poolside/laguna-s-2.1:free (1.6 s), google/gemma-4-31b-it (2.7 s), meta/llama-3.2-90b-vision-instruct (28.8 s) and nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free (3.6 s). In the opposite lane, poolside/laguna-xs-2.1:free slipped back into the error column after a brief win. No model made its first‑ever pass today, and the hidden paywall on inclusionai/ling-3.1-flash (openrouter) still blocks access despite the “free” label.

What it feels like to spin up a free model right now? The sub‑second lane stays king. openai (0.3 s) and openai/gpt-oss-120b:free (1.0 s) are still the quickest tools you can hit for latency‑sensitive tasks. If you need a mid‑range worker, MiniMax-M2.7-Official (2.8 s) and aion-labs/aion-3.0-mini (4.2 s) keep the tool flag lit without breaking the bank. For deep‑reasoning you still have the heavyweight nvidia/nemotron-3-ultra-550b-a55b (1.0 s) and the steady meta/muse-glimmer-30b (15.0 s) that can actually call functions, albeit on a longer clock. The freshly reclaimed poolside/laguna-s-2.1:free adds a solid 1.6‑second option for vision‑heavy prompts.

For anyone building on free tiers, today’s churn is a reminder that the roster is a rotating relay. Sub‑second workers should stay in the primary lane, while minute‑range options become niche fallbacks. The surprise paywall on inclusionai/ling-3.1-flash shows that “free” can hide a credit wall, and a model that answered tools yesterday can vanish without warning. Keep a queue moving, spin through the passing models before the next lock‑out hits, and never assume permanence for any free endpoint.

To run today’s verified set yourself, clone github.com/fusionpoweredsoftware/anytimelime, set LIME_KEY to an OpenRouter key, and run ./lime.sh. It pulls the day’s roster and rotates across the passing models; your key stays on your own machine.

Today's passing roster

openai — Pollinations · 0.3s · agentic 3/5
openai — Pollinations · 0.3s · agentic 3/5
google/diffusiongemma-26b-a4b-it — nvidia · 0.4s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b:free — openrouter · 0.6s · agentic 3/5
typhoon-v2.5-30b-a3b-instruct — Typhoon (SCB 10X) · 0.7s · agentic 3/5
meta/llama-3.2-11b-vision-instruct — nvidia · 0.7s · agentic 3/5
openai/gpt-oss-120b:free — FastRouter · 1.0s · agentic 3/5
cohere/north-mini-code:free — openrouter · 1.0s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b — nvidia · 1.0s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b — nvidia · 1.0s · agentic 3/5
apodex/apodex-1.1-mini:free — openrouter · 1.1s · agentic 3/5
agnes-3.0-flash — Agnes AI · 1.2s · agentic 3/5
openai-fast — Pollinations · 1.2s · agentic 3/5
liquid/lfm-2.5-2.6b:free — openrouter · 1.2s · agentic 3/5
qwen/qwen3.5-4b-free — Mixlayer · 1.4s · agentic 3/5
poolside/laguna-s-2.1:free — openrouter · 1.6s · agentic 3/5
north-mini-code — TokenReply · 1.7s · agentic 3/5
dots-studio/dots-3-note-preview:free — openrouter · 1.8s · agentic 3/5
intern-s2-preview — Intern AI · 2.0s · agentic 3/5
openai/gpt-oss-20b:free — FastRouter · 2.0s · agentic 3/5
MiniMaxAI/MiniMax-M2.7 — Gonka Broker · 2.3s · agentic 3/5
intern-s2 — Intern AI (Shanghai AI Lab) · 2.3s · agentic 3/5
nvidia/nemotron-3.5-lightning:free — openrouter · 2.5s · agentic 3/5
google/gemma-4-31b-it — nvidia · 2.7s · agentic 3/5
MiniMax-M2.7-Official — Pooled AI · 2.8s · agentic 3/5
qwen3-8b — Free.ai · 2.8s · agentic 3/5
nvidia/ising-calibration-1.5-31b — nvidia · 2.9s · agentic 3/5
nvidia/nemotron-3-ultra-550b-a55b:free — openrouter · 3.3s · agentic 3/5
nvidia/nemotron-3.5-lightning-30b-a3b — nvidia · 3.4s · agentic 3/5
moonshotai/kimi-k3 — nvidia · 3.5s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — openrouter · 3.6s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning — nvidia · 3.7s · agentic 3/5
aion-labs/aion-3.0-mini — AION Labs · 4.2s · agentic 3/5
nemotron-3-super-120b-a12b:free — Naga AI · 4.2s · agentic 3/5
zai-org/GLM-5.3-Flash — Gonka Broker · 4.4s · agentic 3/5
kilo-auto/free — Kilo (Anaconda) · 4.5s · agentic 3/5
openrouter/free — openrouter · 5.7s · agentic 3/5
meta/muse-glimmer-30b — nvidia · 15.0s · agentic 3/5
meta/llama-3.2-90b-vision-instruct — nvidia · 28.8s · 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	`01-ai/yi-large`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`DeepSeek-V3.1`	sambanova	untested	DOWN	—	✗	✗	✗
2.8	`MiniMax-M2.7-Official`	Pooled AI	yes	FREE	3/5	✓	✓	✓
2.3	`MiniMaxAI/MiniMax-M2.7`	Gonka Broker	yes	FREE	3/5	✓	✓	✓
0.2	`Qwen/Qwen3-Coder-480B-A35B-Instruct`	HuggingFace Router	yes (past)	DOWN	—	✗	✗	✗
1.2	`agnes-3.0-flash`	Agnes AI	yes	FREE	3/5	✓	✓	✓
4.2	`aion-labs/aion-3.0-mini`	AION Labs	yes	FREE	3/5	✓	✓	·
0.8	`aisingapore/Qwen-SEA-LION-v4.5-27B-IT`	SEA-LION (AI Singapore)	yes (past)	DOWN	—	✗	✗	✗
1.1	`apodex/apodex-1.1-mini:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.3	`codestral-latest`	Mistral	yes (past)	DOWN	—	✗	✗	✗
0.1	`deepseek-ai/DeepSeek-V3-0324`	HuggingFace Inference Router	yes (past)	DOWN	—	✗	✗	✓
0.6	`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	—	✗	✗	✗
0.8	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes (past)	DOWN	—	✗	·	✓
0.9	`intern-latest`	Intern AI	yes (past)	DOWN	—	✗	✗	✗
2.3	`intern-s2`	Intern AI (Shanghai AI Lab)	yes	FREE	3/5	✓	✓	·
4.5	`kilo-auto/free`	Kilo (Anaconda)	yes	FREE	3/5	✓	✓	·
0.2	`meta-llama/Llama-3.3-70B-Instruct`	Hugging Face Inference	yes (past)	DOWN	—	✗	✗	✓
0.9	`minimax/minimax-m3:free`	xKiro AI	yes (past)	DOWN	—	✗	✗	✗
4.2	`nemotron-3-super-120b-a12b:free`	Naga AI	yes	FREE	3/5	✓	✓	✓
1.7	`north-mini-code`	TokenReply	yes	FREE	3/5	✓	✓	✓
1.2	`openai-fast`	Pollinations	yes	FREE	3/5	✓	✓	✓
1.0	`openai/gpt-oss-120b:free`	FastRouter	yes	FREE	3/5	✓	·	✓
0.3	`openai`	Pollinations	yes	FREE	3/5	✓	✓	✓
1.4	`qwen/qwen3.5-4b-free`	Mixlayer	yes	FREE	3/5	✓	·	✓
2.8	`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	—	✗	·	✗
0.7	`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	—	✗	✗	✗
0.2	`aion-labs/aion-3.0`	AION Labs	yes (past)	DOWN	—	✗	✗	✗
1.0	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.3	`inclusionAI/Ling-flash-2.0`	SiliconFlow	yes (past)	DOWN	—	✗	✗	✗
0.8	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes (past)	DOWN	—	✗	·	✓
2.0	`intern-s2-preview`	Intern AI	yes	FREE	3/5	✓	✓	✓
0.3	`openai`	Pollinations	yes	FREE	3/5	✓	✓	✓
2.0	`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	—	✗	✗	✗
4.4	`zai-org/GLM-5.3-Flash`	Gonka Broker	yes	FREE	3/5	✓	✗	✓
1.8	`dots-studio/dots-3-note-preview:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.4	`aisingapore/sea-lion-7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`MiniMax-M3`	sambanova	untested	DOWN	—	✗	✗	✗
0.4	`google/gemma-4-26b-a4b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.4	`bigcode/starcoder2-15b`	nvidia	untested	DOWN	—	✗	✗	✗
0.6	`gemma-4-31B-it`	sambanova	untested	DOWN	—	✗	✗	✗
0.4	`google/gemma-4-31b-it:free`	openrouter	yes (past)	DOWN	—	✗	✓	✗
0.4	`databricks/dbrx-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.4	`gpt-oss-120b`	sambanova	untested	DOWN	—	✗	✗	✗
0.4	`inclusionai/ling-3.1-flash`	openrouter	untested	CARD	—	✗	✗	✗
0.4	`deepseek-ai/deepseek-coder-6.7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
1.2	`liquid/lfm-2.5-2.6b:free`	openrouter	yes	FREE	3/5	✓	✓	✓
60.1	`deepseek-ai/deepseek-v4.1-flash`	nvidia	untested	DOWN	—	✗	✗	✗
3.6	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	openrouter	yes	FREE	3/5	✓	✗	✗
0.1	`google/codegemma-1.1-7b`	nvidia	untested	DOWN	—	✗	✗	✗
0.6	`nvidia/nemotron-3-super-120b-a12b:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/codegemma-7b`	nvidia	untested	DOWN	—	✗	✗	✗
3.3	`nvidia/nemotron-3-ultra-550b-a55b:free`	openrouter	yes	FREE	3/5	✓	✓	✗
0.3	`google/deplot`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/nemotron-3.5-content-safety:free`	openrouter	untested	DOWN	—	✗	✗	✗
0.4	`google/diffusiongemma-26b-a4b-it`	nvidia	yes	FREE	3/5	✓	✓	✓
2.5	`nvidia/nemotron-3.5-lightning:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/gemma-2b`	nvidia	untested	DOWN	—	✗	✗	✗
5.7	`openrouter/free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.1	`google/gemma-3-12b-it`	nvidia	untested	DOWN	—	✗	✗	✗
1.6	`poolside/laguna-s-2.1:free`	openrouter	yes	FREE	3/5	✗	✓	✗
0.1	`google/gemma-3-4b-it`	nvidia	untested	DOWN	—	✗	✗	✗
0.7	`poolside/laguna-xs-2.1:free`	openrouter	yes (past)	DOWN	—	✓	✗	✗
2.7	`google/gemma-4-31b-it`	nvidia	yes	FREE	3/5	✗	✗	✓
0.1	`google/recurrentgemma-2b`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`ibm/granite-3.0-3b-a800m-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
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	—	✗	✗	✗
0.7	`meta/llama-3.2-11b-vision-instruct`	nvidia	yes	FREE	3/5	✓	✓	✓
28.8	`meta/llama-3.2-90b-vision-instruct`	nvidia	yes	FREE	3/5	✗	✓	✓
0.1	`meta/llama2-70b`	nvidia	untested	DOWN	—	✗	✗	✗
15.0	`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	—	✗	✗	✗
3.5	`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	—	✗	✗	✗
2.9	`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	—	✗	✗	✗
3.7	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	nvidia	yes	FREE	3/5	✗	✓	✗
1.0	`nvidia/nemotron-3-super-120b-a12b`	nvidia	yes	FREE	3/5	✓	✓	✓
1.0	`nvidia/nemotron-3-ultra-550b-a55b`	nvidia	yes	FREE	3/5	✓	✓	✓
0.2	`nvidia/nemotron-3.5-content-safety`	nvidia	untested	DOWN	—	✗	✗	✗
3.4	`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	—	✗	✗	✗
60.1	`nvidia/riva-translate-4b-instruct-v2`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/riva-translate-4b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.2	`nvidia/vila`	nvidia	untested	DOWN	—	✗	✗	✗

39 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.