anytimelime — the free AI field report

2026-10-07 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free in AI right now — 2026-10-07

Today's most interesting fact

The free tier is playing a game of musical chairs. kilo-auto/free just stepped into the spotlight as the first model to pass a tool call today after weeks of being a key‑required stub; it now answers at a still‑solid 20.6 seconds. Across the hall, the long‑rumored comeback of tokeness/free ended abruptly—the endpoint timed out after a minute, erasing a brief spell of tool‑capable life. Meanwhile, inclusionai/ling-3.1-flash sits quietly behind a paywall on OpenRouter, a surprise “free‑looking” model that still demands credit. The shuffle underlines that the free pool is a revolving door, not a static shelf.

What it feels like to spin up a free model right now

If you need a tool‑ready endpoint without spending a cent, start with the Pollinations openai gateway (0.4 s) – it stays sub‑second and tool‑capable. For something a bit deeper, nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free (0.1 s) from OpenRouter offers lightning‑fast reasoning with tool support. The newly tool‑capable kilo-auto/free (20.6 s) is a slow‑burn workhorse that proves even the stubborn can join the free‑tool club. A few standouts for a balanced mix: MiniMax-M2.7-Official (2.5 s), agnes-3.0-flash (1.1 s), glm-4.5-flash (4.0 s), nvidia/nemotron-3-super-120b-a12b:free (1.9 s), qwen/qwen3.5-4b-free (1.7 s), typhoon-v2.5-30b-a3b-instruct (0.7 s) and zai-org/GLM-5.3-Flash (2.5 s). The roster also includes the slower but functional qwen3-8b (10.6 s) and the steady openrouter/free (1.3 s). The full measured table follows later for anyone who wants the exhaustive list.

What this churn means for free‑tier builders

Latency is the first guardrail; sub‑second workers (openai, meta-llama/llama-3.3-70b-instruct where it still works) should be the primary lane, while minute‑range options become niche fallbacks. Treat the free pool as a rotating relay: a model that answered tools yesterday can be silent tomorrow, and a “free” label can be stripped without warning. The surprise paywall on inclusionai/ling-3.1-flash is a reminder that some endpoints hide behind credit walls even when the probe says “yes”. Keep a rotation queue in motion, spin through the passing models before the next lock‑out hits, and never assume permanence for any free tier.

To run the day’s verified set yourself, clone github.com/fusionpoweredsoftware/anytimelime, set LIME_KEY to an OpenRouter key, and execute ./lime.sh. It fetches today’s roster and rotates across the passing models; your key never leaves your machine.

Today's passing roster

openai — Pollinations · 0.4s · agentic 3/5
openai — Pollinations · 0.4s · agentic 3/5
google/diffusiongemma-26b-a4b-it — nvidia · 0.4s · agentic 3/5
meta/llama-3.2-11b-vision-instruct — nvidia · 0.6s · agentic 3/5
typhoon-v2.5-30b-a3b-instruct — Typhoon (SCB 10X) · 0.7s · agentic 3/5
openai/gpt-oss-120b:free — FastRouter · 0.8s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b:free — openrouter · 0.9s · agentic 3/5
liquid/lfm-2.5-2.6b:free — openrouter · 1.0s · agentic 3/5
agnes-3.0-flash — Agnes AI · 1.1s · agentic 3/5
apodex/apodex-1.1-mini:free — openrouter · 1.3s · agentic 3/5
inclusionai/ling-3.0-flash-sante:free — openrouter · 1.3s · agentic 3/5
openrouter/free — openrouter · 1.3s · agentic 3/5
nvidia/nemotron-3-super-120b-a12b — nvidia · 1.3s · agentic 3/5
qwen/qwen3.5-4b-free — Mixlayer · 1.7s · agentic 3/5
intern-s2-preview — Intern AI · 1.7s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — openrouter · 1.7s · agentic 3/5
nemotron-3-super-120b-a12b:free — Naga AI · 1.9s · agentic 3/5
openai/gpt-oss-20b:free — FastRouter · 1.9s · agentic 3/5
MiniMax-M2.7-Official — Pooled AI · 2.5s · agentic 3/5
zai-org/GLM-5.3-Flash — Gonka Broker · 2.5s · agentic 3/5
zai-org/GLM-5.3-Flash — Gonka Broker · 2.5s · agentic 3/5
MiniMaxAI/MiniMax-M2.7 — Gonka Broker · 3.0s · agentic 3/5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning — nvidia · 3.3s · agentic 3/5
glm-4.5-flash — Z.ai (Zhipu) · 4.0s · agentic 3/5
north-mini-code — TokenReply · 4.2s · agentic 3/5
nvidia/nemotron-3.5-lightning-30b-a3b — nvidia · 6.6s · agentic 3/5
cohere/north-mini-code:free — openrouter · 6.9s · agentic 3/5
meta/muse-glimmer-30b — nvidia · 7.5s · agentic 3/5
qwen3-8b — Free.ai · 10.6s · agentic 3/5
kilo-auto/free — Kilo (Anaconda) · 20.6s · agentic 3/5
google/gemma-4-31b-it — nvidia · 29.9s · 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
—	`anyrouter/free`	AnyRouter	untested	DOWN	—	·	·	·
20.6	`kilo-auto/free`	Kilo (Anaconda)	yes	FREE	3/5	·	·	·
—	`meta-llama/llama-3.3-70b-instruct`	OpenTau (Bittensor)	untested	DOWN	—	·	·	·
0.3	`01-ai/yi-large`	nvidia	untested	DOWN	—	✗	✗	✗
0.5	`DeepSeek-V3.1`	sambanova	untested	DOWN	—	✗	✗	✗
0.5	`Meta-Llama-3.3-70B-Instruct`	SambaNova Cloud	untested	DOWN	—	✗	✗	✗
2.5	`MiniMax-M2.7-Official`	Pooled AI	yes	FREE	3/5	·	✓	·
3.0	`MiniMaxAI/MiniMax-M2.7`	Gonka Broker	yes	FREE	3/5	✓	✓	·
0.2	`Qwen/Qwen3-Coder-480B-A35B-Instruct`	HuggingFace Router	yes (past)	DOWN	—	·	✓	·
1.1	`agnes-3.0-flash`	Agnes AI	yes	FREE	3/5	·	✓	·
0.3	`aion-labs/aion-3.0`	AION Labs	yes (past)	DOWN	—	✗	✓	·
0.4	`aisingapore/Qwen-SEA-LION-v4.5-27B-IT`	SEA-LION (AI Singapore)	yes (past)	DOWN	—	✗	✗	·
0.5	`am/free`	AnyModel	untested	DOWN	—	·	·	·
1.3	`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	—	✗	✗	✓
4.0	`glm-4.5-flash`	Z.ai (Zhipu)	yes	FREE	3/5	·	✗	·
0.9	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes (past)	DOWN	—	·	✓	·
0.9	`glm-4.7-flash`	Zhipu AI (Z.ai)	yes (past)	DOWN	—	·	✓	·
0.3	`gpt-oss-120b`	sambanova	untested	DOWN	—	·	✗	✗
1.4	`intern-latest`	Intern AI	yes (past)	DOWN	—	✗	✗	·
0.1	`meta-llama/Llama-3.3-70B-Instruct`	Hugging Face Inference	yes (past)	DOWN	—	✓	✓	·
0.4	`minimax/minimax-m3:free`	xKiro AI	yes (past)	DOWN	—	✗	✗	·
1.9	`nemotron-3-super-120b-a12b:free`	Naga AI	yes	FREE	3/5	·	✓	·
4.2	`north-mini-code`	TokenReply	yes	FREE	3/5	✓	✓	·
0.1	`openai-fast`	KeylessAI	untested	DOWN	—	✗	·	·
0.1	`openai-fast`	KeylessAI	untested	DOWN	—	✗	·	·
0.8	`openai/gpt-oss-120b:free`	FastRouter	yes	FREE	3/5	·	✓	·
0.4	`openai`	Pollinations	yes	FREE	3/5	✓	✓	·
1.7	`qwen/qwen3.5-4b-free`	Mixlayer	yes	FREE	3/5	·	✓	·
10.6	`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	·	✓	·
2.5	`zai-org/GLM-5.3-Flash`	Gonka Broker	yes	FREE	3/5	✗	✓	·
0.2	`adept/fuyu-8b`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`DeepSeek-V3.2`	sambanova	untested	DOWN	—	✗	✗	✗
0.5	`deepseek-ai/DeepSeek-V4-Flash-0731`	Gonka Broker	yes (past)	DOWN	—	✗	✗	·
6.9	`cohere/north-mini-code:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.3	`inclusionAI/Ling-flash-2.0`	SiliconFlow	yes (past)	DOWN	—	✗	✗	·
1.7	`intern-s2-preview`	Intern AI	yes	FREE	3/5	·	✓	·
0.4	`openai`	Pollinations	yes	FREE	3/5	✓	✓	·
1.9	`openai/gpt-oss-20b:free`	FastRouter	yes	FREE	3/5	✓	✓	·
0.1	`ai21labs/jamba-1.5-large-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`MiniMax-M3`	sambanova	untested	DOWN	—	✗	✗	✗
2.5	`zai-org/GLM-5.3-Flash`	Gonka Broker	yes	FREE	3/5	✗	✓	·
15.4	`dots-studio/dots-3-note-preview:free`	openrouter	yes (past)	DOWN	—	·	✓	✓
0.2	`aisingapore/sea-lion-7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`gemma-4-31B-it`	sambanova	untested	DOWN	—	✗	✗	✗
0.2	`google/gemma-4-26b-a4b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✗
0.1	`bigcode/starcoder2-15b`	nvidia	untested	DOWN	—	✗	✗	✗
0.3	`gpt-oss-120b`	sambanova	untested	DOWN	—	·	✗	✗
0.3	`google/gemma-4-31b-it:free`	openrouter	yes (past)	DOWN	—	✗	✗	✓
0.2	`databricks/dbrx-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
1.3	`inclusionai/ling-3.0-flash-sante:free`	openrouter	yes	FREE	3/5	✓	✓	·
0.2	`deepseek-ai/deepseek-coder-6.7b-instruct`	nvidia	untested	DOWN	—	✗	✗	✗
0.1	`inclusionai/ling-3.1-flash`	openrouter	untested	CARD	—	✗	✗	·
60.1	`deepseek-ai/deepseek-v4.1-flash`	nvidia	untested	DOWN	—	✗	✗	·
1.0	`liquid/lfm-2.5-2.6b:free`	openrouter	yes	FREE	3/5	✓	✓	✓
0.2	`google/codegemma-1.1-7b`	nvidia	untested	DOWN	—	✗	✗	·
1.7	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	openrouter	yes	FREE	3/5	✗	✓	·
0.2	`google/codegemma-7b`	nvidia	untested	DOWN	—	✗	✗	·
0.9	`nvidia/nemotron-3-super-120b-a12b:free`	openrouter	yes	FREE	3/5	✓	✓	·
0.2	`google/deplot`	nvidia	untested	DOWN	—	✗	✗	·
0.5	`nvidia/nemotron-3-ultra-550b-a55b:free`	openrouter	yes (past)	DOWN	—	✓	✓	·
0.4	`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	—	✗	✗	·
22.6	`nvidia/nemotron-3.5-lightning:free`	openrouter	text-only	FREE	—	✓	✓	·
0.2	`google/gemma-3-12b-it`	nvidia	untested	DOWN	—	✗	✗	·
1.3	`openrouter/free`	openrouter	yes	FREE	3/5	✓	✓	·
0.2	`google/gemma-3-4b-it`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`poolside/laguna-s-2.1:free`	openrouter	yes (past)	DOWN	—	✗	✓	·
29.9	`google/gemma-4-31b-it`	nvidia	yes	FREE	3/5	✓	✓	·
0.2	`poolside/laguna-xs-2.1:free`	openrouter	yes (past)	DOWN	—	✗	✓	·
0.1	`google/recurrentgemma-2b`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`ibm/granite-3.0-3b-a800m-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`ibm/granite-3.0-8b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`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	—	✗	✗	·
0.6	`meta/llama-3.2-11b-vision-instruct`	nvidia	yes	FREE	3/5	✓	✓	·
60.1	`meta/llama-3.2-90b-vision-instruct`	nvidia	yes (past)	DOWN	—	✓	✓	·
0.2	`meta/llama2-70b`	nvidia	untested	DOWN	—	✗	✗	·
7.5	`meta/muse-glimmer-30b`	nvidia	yes	FREE	3/5	✓	✓	·
0.1	`microsoft/kosmos-2`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`microsoft/phi-3-vision-128k-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`microsoft/phi-3.5-moe-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`mistralai/codestral-22b-instruct-v0.1`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`mistralai/mistral-7b-instruct-v0.3`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`mistralai/mistral-large-2-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`mistralai/mistral-large`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`mistralai/mixtral-8x22b-v0.1`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`moonshotai/kimi-k2.6`	nvidia	untested	DOWN	—	✗	✗	·
60.1	`moonshotai/kimi-k3`	nvidia	yes (past)	DOWN	—	✗	✓	·
0.1	`nv-mistralai/mistral-nemo-12b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/ai-synthetic-video-detector`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/cosmos-reason2-8b`	nvidia	untested	DOWN	—	✗	✗	·
0.6	`nvidia/ising-calibration-1.5-31b`	nvidia	text-only	FREE	—	✓	✓	·
0.2	`nvidia/llama-3.1-nemotron-51b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/llama-3.1-nemotron-70b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/llama-3.1-nemotron-ultra-253b-v1`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/llama3-chatqa-1.5-70b`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/mistral-nemo-minitron-8b-8k-instruct`	nvidia	untested	DOWN	—	✗	✗	·
3.3	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	nvidia	yes	FREE	3/5	✓	✗	·
1.3	`nvidia/nemotron-3-super-120b-a12b`	nvidia	yes	FREE	3/5	✓	✓	·
0.4	`nvidia/nemotron-3-ultra-550b-a55b`	nvidia	yes (past)	DOWN	—	✓	✓	·
0.2	`nvidia/nemotron-3.5-content-safety`	nvidia	untested	DOWN	—	✗	✗	·
6.6	`nvidia/nemotron-3.5-lightning-30b-a3b`	nvidia	yes	FREE	3/5	✓	✓	·
0.2	`nvidia/nemotron-4-340b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/nemotron-4-340b-reward`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/nemotron-nano-3-30b-a3b`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/nemotron-parse-2.0`	nvidia	untested	DOWN	—	✗	✗	·
0.3	`nvidia/nemotron-parse`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/neva-22b`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/nvclip`	nvidia	untested	DOWN	—	✗	✗	·
11.8	`nvidia/riva-translate-4b-instruct-v2`	nvidia	untested	DOWN	—	✗	✗	·
0.2	`nvidia/riva-translate-4b-instruct`	nvidia	untested	DOWN	—	✗	✗	·
0.1	`nvidia/vila`	nvidia	untested	DOWN	—	✗	·	·

32 made a tool call, 2 answered in text only, of 121 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.