anytimelime — the free AI field report

2026-10-14 · generated by a free model interviewing free models · anytimelime, formerly Project42 · get the engine →

What's free in AI right now — 2026-10-14

The morning’s headline is a modest shuffle of tool‑flags. After weeks of silence, Meta-Llama-3_3-70B-Instruct (OVHcloud AI Endpoints) re‑appeared with a 3.7‑second latency and the tool flag lit—its first pass in the log. Just as brisk, two instances of openai-fast (Pollinations) slipped back into the free lane at 5.5 seconds and 5.7 seconds, both reporting PASS (tool). A third newcomer, tokeness/free (Tokeness) hit a solid 3.0 seconds while also supporting tools, and google/gemma-4-31b-it (Nvidia) finally answered the tool probe after a long outage, though its latency sits at 0.2 seconds for a quick hit.

What it feels like to spin up a model now? The sub‑second tier still rules. openai (Pollinations, 0.3 s) and openai/gpt-oss-120b:free (FastRouter, 1.0 s) remain the quickest functional endpoints for latency‑sensitive work. If you need a mid‑range worker with actual tool support, MiniMax-M2.7-Official (Pooled AI, 5.5 s) and MiniMaxAI/MiniMax-M2.7 (Gonka Broker, 4.5 s) are steady picks. The newly revived Llama now gives you a heavier‑weight option at 3.7 seconds, while the freshly unlocked tokeness/free provides a reliable 3‑second slot for anything that can’t be done in sub‑second time. Meanwhile, the Nvidia‑hosted reasoning block—nvidia/nemotron-3-ultra-550b-a55b (1.6 s) and meta/muse-glimmer-30b (6.6 s)—keeps the tool flag alive for deep‑thinking tasks, albeit at a slower pace.

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; the newly reclaimed mid‑range models can serve as niche fallbacks when the fast lanes go quiet. The brief return of google/gemma-4-31b-it (now tool‑capable) shows that a model can flip back onto the free track without warning, and the Llama’s comeback proves that even the “stable” models can re‑emerge after a quiet spell.

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

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
3.7Meta-Llama-3_3-70B-InstructOVHcloud AI EndpointsyesFREE3/5···
0.601-ai/yi-largenvidiauntestedDOWN—✗✗✗
0.7DeepSeek-V3.1sambanovauntestedDOWN—✗✗✗
5.5MiniMax-M2.7-OfficialPooled AIyesFREE3/5✓✓✓
4.5MiniMaxAI/MiniMax-M2.7Gonka BrokeryesFREE3/5✓✓✓
0.7Qwen/Qwen3-Coder-480B-A35B-InstructHuggingFace Routeryes (past)DOWN—✗✗✗
2.1agnes-3.0-flashAgnes AIyesFREE3/5✓✓✓
7.7aion-labs/aion-3.0-miniAION LabsyesFREE3/5✓✓·
6.4aisingapore/Qwen-SEA-LION-v4.5-27B-ITSEA-LION (AI Singapore)yes (past)DOWN—✗✗✗
0.3am/freeAnyModeluntestedDOWN—··✗
3.9auto:freeBazaarLinkyesFREE3/5✓··
0.3codestral-latestMistralyes (past)DOWN—✗✗✗
1.1cohere/north-mini-code:freeopenrouteryesFREE3/5✓✓✓
0.1deepseek-ai/DeepSeek-V3-0324HuggingFace Inference Routeryes (past)DOWN—✗✗✗
1.0deepseek-ai/DeepSeek-V3.1SiliconFlowyes (past)DOWN—✗✗✗
0.1deepseek-ai/deepseek-v4-flash-0731NVIDIA NIMyes (past)DOWN—✗✗✗
4.4deepseek-v4-flash:freeRouteway AIyesFREE3/5✓··
—freeAnyRouteruntestedDOWN—···
0.6glm-4.5-flashZhipu AI (Z.ai)yes (past)DOWN—✗✗✓
0.8glm-4.7-flashZhipu AI (Z.ai)yes (past)DOWN—✓✗✗
1.0intern-latestIntern AIyes (past)DOWN—✗✗✗
2.9intern-s2Intern AI (Shanghai AI Lab)yesFREE3/5✓✓·
6.3kilo-auto/freeKilo (Anaconda)yesFREE3/5✓✓✓
0.1meta-llama/Llama-3.3-70B-InstructHugging Face Inferenceyes (past)DOWN—✗✗✗
0.4minimax/minimax-m3:freexKiro AIyes (past)DOWN—✗✗✗
3.4nemotron-3-super-120b-a12b:freeNaga AIyesFREE3/5✓✓✓
2.3north-mini-codeTokenReplyyesFREE3/5✓✓✓
5.7openai-fastPollinationsyesFREE3/5···
1.0openai/gpt-oss-120b:freeFastRouteryesFREE3/5✓✓✓
0.4openaiPollinationsyesFREE3/5✓✓✓
1.4qwen/qwen3.5-4b-freeMixlayeryesFREE3/5✓✓✓
1.3qwen3-8bFree.aiyesFREE3/5✓✓✓
0.2qwen3.8-27bYolo-Autoyes (past)DOWN—✗✗✗
3.0tokeness/freeTokenessyesFREE3/5✗✗✗
0.7typhoon-v2.5-30b-a3b-instructTyphoon (SCB 10X)yesFREE3/5✓✓✓
0.2adept/fuyu-8bnvidiauntestedDOWN—✗✗✗
0.3DeepSeek-V3.2sambanovauntestedDOWN—✗✗✗
0.5deepseek-ai/DeepSeek-V4-Flash-0731Gonka Brokeryes (past)DOWN—✗✗✗
0.2aion-labs/aion-3.0AION Labsyes (past)DOWN—✓✗✗
1.4dots-studio/dots-3-note-preview:freeopenrouteryesFREE3/5✓✓✗
0.1openai/gpt-oss-120bHuggingFace Inference RouteruntestedDOWN—···
0.1inclusionAI/Ling-flash-2.0SiliconFlowyes (past)DOWN—✗✗✗
0.8glm-4.7-flashZhipu AI (Z.ai)yes (past)DOWN—✓✗✗
2.2intern-s2-previewIntern AIyesFREE3/5✓✓✓
3.9qwen/qwen3-coder-plus:freexKiro AIyesFREE3/5✓··
5.7openai-fastPollinationsyesFREE3/5···
1.1openai/gpt-oss-20b:freeFastRouteryesFREE3/5✓✓✓
0.1ai21labs/jamba-1.5-large-instructnvidiauntestedDOWN—✗✗✗
0.3Meta-Llama-3.3-70B-InstructsambanovauntestedDOWN—✗✗✗
2.3zai-org/GLM-5.3-FlashGonka BrokeryesFREE3/5✓✓✓
0.2google/gemma-4-26b-a4b-it:freeopenrouteryes (past)DOWN—✗✗✗
0.4openaiPollinationsyesFREE3/5✓✓✓
0.2aisingapore/sea-lion-7b-instructnvidiauntestedDOWN—✗✗✗
0.3MiniMax-M3sambanovauntestedDOWN—✗✗✗
0.1google/gemma-4-31b-it:freeopenrouteryes (past)DOWN—✗✗✗
0.1bigcode/starcoder2-15bnvidiauntestedDOWN—✗✗✗
0.3gemma-4-31B-itsambanovauntestedDOWN—✗✗✗
0.5liquid/lfm-2.5-2.6b:freeopenrouteryesFREE3/5✓✓✓
0.1databricks/dbrx-instructnvidiauntestedDOWN—✗✗✗
0.3gpt-oss-120bsambanovauntestedDOWN—✗✗✗
0.2nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeopenrouteryes (past)DOWN—✗✓✓
0.1deepseek-ai/deepseek-coder-6.7b-instructnvidiauntestedDOWN—✗✗✗
0.8nvidia/nemotron-3-super-120b-a12b:freeopenrouteryesFREE3/5✓✓✓
60.0deepseek-ai/deepseek-v4.1-flashnvidiauntestedDOWN—✗✗✗
1.6nvidia/nemotron-3-ultra-550b-a55b:freeopenrouteryesFREE3/5✓✓✗
0.1google/codegemma-1.1-7bnvidiauntestedDOWN—✗✗✗
0.2nvidia/nemotron-3.5-content-safety:freeopenrouteruntestedDOWN—✗✗✗
0.2google/codegemma-7bnvidiauntestedDOWN—✗✗✗
12.9nvidia/nemotron-3.5-lightning:freeopenrouteryesFREE3/5✓✓✓
0.2google/deplotnvidiauntestedDOWN—✗✗✗
2.5openrouter/freeopenrouteryesFREE3/5✓✓✓
0.4google/diffusiongemma-26b-a4b-itnvidiayesFREE3/5✓✓✓
0.3poolside/laguna-s-2.1:freeopenrouteryes (past)DOWN—✗✗✗
0.1google/gemma-2bnvidiauntestedDOWN—✗✗✗
0.3poolside/laguna-xs-2.1:freeopenrouteryes (past)DOWN—✗✓✗
0.1google/gemma-3-12b-itnvidiauntestedDOWN—✗✗✗
0.1google/gemma-3-4b-itnvidiauntestedDOWN—✗✗✗
31.7google/gemma-4-31b-itnvidiayesFREE3/5✗✗✓
0.1google/recurrentgemma-2bnvidiauntestedDOWN—✗✗✗
0.1ibm/granite-3.0-3b-a800m-instructnvidiauntestedDOWN—✗✗✗
0.1ibm/granite-3.0-8b-instructnvidiauntestedDOWN—✗✗✗
0.1ibm/granite-34b-code-instructnvidiauntestedDOWN—✗✗✗
0.1ibm/granite-8b-code-instructnvidiauntestedDOWN—✗✗✗
0.1meta/codellama-70bnvidiauntestedDOWN—✗✗✗
12.7meta/llama-3.2-11b-vision-instructnvidiayesFREE3/5✓✓✓
60.1meta/llama-3.2-90b-vision-instructnvidiayes (past)DOWN—✗✗✗
0.1meta/llama2-70bnvidiauntestedDOWN—✗✗✗
6.6meta/muse-glimmer-30bnvidiayesFREE3/5✓✓✓
0.1microsoft/kosmos-2nvidiauntestedDOWN—✗✗✗
0.1microsoft/phi-3-vision-128k-instructnvidiauntestedDOWN—✗✗✗
0.1microsoft/phi-3.5-moe-instructnvidiauntestedDOWN—✗✗✗
0.1mistralai/codestral-22b-instruct-v0.1nvidiauntestedDOWN—✗✗✗
0.1mistralai/mistral-7b-instruct-v0.3nvidiauntestedDOWN—✗✗✗
0.1mistralai/mistral-large-2-instructnvidiauntestedDOWN—✗✗✗
0.1mistralai/mistral-largenvidiauntestedDOWN—✗✗✗
0.1mistralai/mixtral-8x22b-v0.1nvidiauntestedDOWN—✗✗✗
0.1moonshotai/kimi-k2.6nvidiauntestedDOWN—✗✗✗
49.3moonshotai/kimi-k3nvidiayesFREE3/5✓✓✗
0.1nv-mistralai/mistral-nemo-12b-instructnvidiauntestedDOWN—✗✗✗
0.2nvidia/ai-synthetic-video-detectornvidiauntestedDOWN—✗✗✗
0.1nvidia/cosmos-reason2-8bnvidiauntestedDOWN—✗✗✗
0.4nvidia/ising-calibration-1.5-31bnvidiayesFREE3/5✓✓✓
0.1nvidia/llama-3.1-nemotron-51b-instructnvidiauntestedDOWN—✗✗✗
0.1nvidia/llama-3.1-nemotron-70b-instructnvidiauntestedDOWN—✗✗✗
0.1nvidia/llama-3.1-nemotron-ultra-253b-v1nvidiauntestedDOWN—✗✗✗
0.1nvidia/llama3-chatqa-1.5-70bnvidiauntestedDOWN—✗✗✗
0.1nvidia/mistral-nemo-minitron-8b-8k-instructnvidiauntestedDOWN—✗✗✗
4.2nvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidiayesFREE3/5✓✗✓
2.3nvidia/nemotron-3-super-120b-a12bnvidiayesFREE3/5✓✓✓
4.4nvidia/nemotron-3-ultra-550b-a55bnvidiayesFREE3/5✓✓✗
0.1nvidia/nemotron-3.5-content-safetynvidiauntestedDOWN—✗✗✗
1.6nvidia/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-parse-2.0nvidiauntestedDOWN—✗✗✗
0.2nvidia/nemotron-parsenvidiauntestedDOWN—✗✗✗
0.1nvidia/neva-22bnvidiauntestedDOWN—✗✗✗
0.1nvidia/nvclipnvidiauntestedDOWN—✗✗✗
60.1nvidia/riva-translate-4b-instruct-v2nvidiauntestedDOWN—✗✗✗
0.1nvidia/riva-translate-4b-instructnvidiauntestedDOWN—✗✗✗
0.1nvidia/vilanvidiauntestedDOWN—✗✗✗

41 made a tool call, 0 answered in text only, of 122 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.