anytimelime — the free AI field report

2026-09-17 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free right now

22 free models made a real tool call today, out of 90 discovered, and the morning diff tells the story: qwen/qwen3.8-27b:free, stealth/union-alpha, inclusionai/ling-3.0-flash-vl:free, liquid/lfm-2.5-2.6b:free, nex-agi/nex-n2.5-mini:free, google/diffusiongemma-26b-a4b-it, nvidia/nemotron-3-super-120b-a12b:free, nvidia/nemotron-3-ultra-550b-a55b:free, nvidia/nemotron-3.5-lightning:free, google/gemma-4-31b-it, openrouter/free, poolside/laguna-xs-2.1:free, meta/llama-3.2-11b-vision-instruct, meta/muse-glimmer-30b, mistralai/mistral-nemotron, nvidia/nemotron-3-ultra-550b-a55b, nvidia/nemotron-3.5-lightning-30b-a3b joined the tool-call club today, and qwen3.8-27b lost theirs since the 2026-09-16 report. 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

The measured table

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

latencymodelvendortool callfree nowagenticyesterday3 days agoa week ago
8.3qwen/qwen3.8-27b:freeopenrouteryesFREE3/5···
1.2stealth/union-alphaopenrouteryesFREE3/5···
0.5meganova-ai/manta-flash-1.0MegaNova AIuntestedDOWN—✗✗·
0.3aisingapore/Gemma-SEA-LION-v4-27B-ITSEA-LIONuntestedDOWN—···
0.201-ai/yi-largenvidiauntestedDOWN—✗✗✗
1.9cohere/north-mini-code:freeopenrouteryesFREE3/5✓✓✓
0.6DeepSeek-V3.1sambanovauntestedCARD—✗✗✗
0.2adept/fuyu-8bnvidiauntestedDOWN—✗✗✗
1.6dots-studio/dots-3-note-preview:freeopenrouteryesFREE3/5✓✓✓
0.6DeepSeek-V3.2sambanovauntestedCARD—✗✗✗
0.2ai21labs/jamba-1.5-large-instructnvidiauntestedDOWN—✗✗✗
0.3google/gemma-4-26b-a4b-it:freeopenrouteryes (past)DOWN—✗✗✗
0.3Meta-Llama-3.3-70B-InstructsambanovauntestedCARD—✗✗✗
0.1aisingapore/sea-lion-7b-instructnvidiauntestedDOWN—✗✗✗
0.3google/gemma-4-31b-it:freeopenrouteryes (past)DOWN—✗✗✗
0.3MiniMax-M2.7sambanovauntestedCARD—✗✗✗
0.1bigcode/starcoder2-15bnvidiauntestedDOWN—✗✗✗
0.8inclusionai/ling-3.0-flash-fin:freeopenrouteryesFREE3/5✓✓✓
0.3MiniMax-M3sambanovauntestedCARD—✗✗✗
0.2databricks/dbrx-instructnvidiauntestedDOWN—✗·✗
1.3inclusionai/ling-3.0-flash-sante:freeopenrouteryesFREE3/5✓·✓
0.3gemma-4-31B-itsambanovauntestedCARD—✗·✗
0.2deepseek-ai/deepseek-coder-6.7b-instructnvidiauntestedDOWN—✗·✗
1.4inclusionai/ling-3.0-flash-vl:freeopenrouteryesFREE3/5··✓
0.3gpt-oss-120bsambanovauntestedCARD—·✗✗
60.1deepseek-ai/deepseek-v4-flash-0731nvidiayes (past)DOWN—·✓✗
2.7liquid/lfm-2.5-2.6b:freeopenrouteryesFREE3/5··✓
0.1google/codegemma-1.1-7bnvidiauntestedDOWN—···
1.8nex-agi/nex-n2.5-mini:freeopenrouteryesFREE3/5···
0.1google/codegemma-7bnvidiauntestedDOWN—···
21.0nex-agi/nex-n2.5-pro:freeopenrouteruntestedDOWN—···
0.2google/deplotnvidiauntestedDOWN—···
0.5nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeopenrouteruntestedDOWN—···
26.8google/diffusiongemma-26b-a4b-itnvidiayesFREE3/5···
1.8nvidia/nemotron-3-super-120b-a12b:freeopenrouteryesFREE3/5···
0.1google/gemma-2bnvidiauntestedDOWN—···
16.9nvidia/nemotron-3-ultra-550b-a55b:freeopenrouteryesFREE3/5···
0.1google/gemma-3-12b-itnvidiauntestedDOWN—···
0.2nvidia/nemotron-3.5-content-safety:freeopenrouteruntestedDOWN—···
0.1google/gemma-3-4b-itnvidiauntestedDOWN—···
5.3nvidia/nemotron-3.5-lightning:freeopenrouteryesFREE3/5···
2.2google/gemma-4-31b-itnvidiayesFREE3/5···
0.7openrouter/freeopenrouteryesFREE3/5···
0.1google/recurrentgemma-2bnvidiauntestedDOWN—···
2.0poolside/laguna-s-2.1:freeopenrouteruntestedDOWN—···
0.1ibm/granite-3.0-3b-a800m-instructnvidiauntestedDOWN—···
0.6poolside/laguna-xs-2.1:freeopenrouteryesFREE3/5···
0.1ibm/granite-3.0-8b-instructnvidiauntestedDOWN—···
0.1ibm/granite-34b-code-instructnvidiauntestedDOWN—···
0.2ibm/granite-8b-code-instructnvidiauntestedDOWN—···
0.2z-ai/glm-5.2:freeopenrouteruntestedDOWN—✗··
0.2meta/codellama-70bnvidiauntestedDOWN—···
15.5meta/llama-3.2-11b-vision-instructnvidiayesFREE3/5···
60.1meta/llama-3.2-90b-vision-instructnvidiauntestedDOWN—···
0.1meta/llama2-70bnvidiauntestedDOWN—···
1.8meta/muse-glimmer-30bnvidiayesFREE3/5···
0.1microsoft/kosmos-2nvidiauntestedDOWN—···
0.1microsoft/phi-3-vision-128k-instructnvidiauntestedDOWN—···
0.2microsoft/phi-3.5-moe-instructnvidiauntestedDOWN—···
0.1mistralai/codestral-22b-instruct-v0.1nvidiauntestedDOWN—···
0.1mistralai/mistral-7b-instruct-v0.3nvidiauntestedDOWN—···
0.1mistralai/mistral-largenvidiauntestedDOWN—···
0.1mistralai/mistral-large-2-instructnvidiauntestedDOWN—···
2.8mistralai/mistral-nemotronnvidiayesFREE3/5···
0.1mistralai/mixtral-8x22b-v0.1nvidiauntestedDOWN—···
0.1moonshotai/kimi-k2.6nvidiauntestedDOWN—···
60.1moonshotai/kimi-k3nvidiauntestedDOWN—···
0.2nv-mistralai/mistral-nemo-12b-instructnvidiauntestedDOWN—···
0.2nvidia/ai-synthetic-video-detectornvidiauntestedDOWN—···
0.1nvidia/cosmos-reason2-8bnvidiauntestedDOWN—···
3.2nvidia/ising-calibration-1.5-31bnvidiatext-onlyFREE—···
0.1nvidia/llama-3.1-nemotron-51b-instructnvidiauntestedDOWN—···
0.2nvidia/llama-3.1-nemotron-70b-instructnvidiauntestedDOWN—···
0.2nvidia/llama-3.1-nemotron-ultra-253b-v1nvidiauntestedDOWN—···
0.2nvidia/llama3-chatqa-1.5-70bnvidiauntestedDOWN—···
0.1nvidia/mistral-nemo-minitron-8b-8k-instructnvidiauntestedDOWN—···
0.1nvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidiauntestedDOWN—···
1.3nvidia/nemotron-3-super-120b-a12bnvidiayesFREE3/5✓✓·
29.7nvidia/nemotron-3-ultra-550b-a55bnvidiayesFREE3/5···
0.2nvidia/nemotron-3.5-content-safetynvidiauntestedDOWN—···
4.9nvidia/nemotron-3.5-lightning-30b-a3bnvidiayesFREE3/5···
0.1nvidia/nemotron-4-340b-instructnvidiauntestedDOWN—···
0.1nvidia/nemotron-4-340b-rewardnvidiauntestedDOWN—···
0.1nvidia/nemotron-nano-3-30b-a3bnvidiauntestedDOWN—···
0.2nvidia/nemotron-parsenvidiauntestedDOWN—···
0.2nvidia/nemotron-parse-2.0nvidiauntestedDOWN—···
0.1nvidia/neva-22bnvidiauntestedDOWN—···
0.1nvidia/nvclipnvidiauntestedDOWN—···
0.1nvidia/riva-translate-4b-instructnvidiauntestedDOWN—···
0.2nvidia/riva-translate-4b-instruct-v1.1nvidiauntestedDOWN—·✗·

22 made a tool call, 1 answered in text only, of 90 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.