Every model you can run for free right now — limits, expiry and catches included. One table, no accounts. Click a model to get it: its provider page, key and API.
01 — Models
| Model | Type | Released | Provider | Context | Free limits | Until | Catch | Score |
|---|---|---|---|---|---|---|---|---|
| stealth/crouton-alpha | omni | 2026-11 | 03OpenRouter (:free) | 1.04858M | 20 rpm · 50 req/day | ongoing | 429strains | |
| nvidia/nemotron-3.5-super-vl:free | vision | 2026-10 | 03OpenRouter (:free) | 1M | 20 rpm · 50 req/day | ongoing | 429strains | |
| xingchen-agi/xing4.0-29b-a4b:free | 2026-10 | 03OpenRouter (:free) | 256k | 20 rpm · 50 req/day | ongoing | 429strains | ||
| recursive/flint-v1.0:free | 2026-10 | 03OpenRouter (:free) | 256k | 20 rpm · 50 req/day | ongoing | 429strains | ||
| nemotron-3.5-super-vl-120b-a12b | vision | 2026-10 | 05NVIDIA NIM | — | unpublished | ongoing | eval | |
| mistral-large-4 | vision | 2026-10 | 06Mistral La Plateforme | — | per-model (see docs) | ongoing | ||
| nvidia/nemotron-3.5-lightning-free | 2026-10 | 07Vercel AI Gateway | 1M | $5 credit / month | ongoing | |||
| reflection/beam-free | 2026-10 | 07Vercel AI Gateway | 1.04858M | $5 credit / month | ongoing | |||
| stealth/glyph-cluster | 2026-10 | 07Vercel AI Gateway | 250k | $5 credit / month | ongoing | |||
| reflection/beam | 2026-10 | 07Vercel AI Gateway | 1.04858M | $5 credit / month | ongoing | |||
| Gemini 3.8 Flash | vision | 2026-09 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| deepseek-v4.1-flash | 2026-09 | 05NVIDIA NIM | — | unpublished | ongoing | eval | ||
| qwen3.8-27b | 2026-08 | 02Groq | 131k | 1k req/day · 8k tok/min | ongoing | slow | ||
| nvidia/nemotron-3.5-lightning:free | 2026-08 | 03OpenRouter (:free) | 1M | 20 rpm · 50 req/day | ongoing | 429strains | ||
| dots-studio/dots-3-note-preview:free | vision | 2026-08 | 03OpenRouter (:free) | 500k | 20 rpm · 50 req/day | ongoing | 429strains | |
| liquid/lfm-2.5-2.6b:free | 2026-08 | 03OpenRouter (:free) | 64k | 20 rpm · 50 req/day | ongoing | 429strains | ||
| qwen3.8-27b | 2026-08 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | |||
| nemotron-3.5-lightning-30b-a3b | 2026-08 | 05NVIDIA NIM | — | unpublished | ongoing | eval | ||
| glm-5.3-flash (3rd-party) | 2026-08 | 06Mistral La Plateforme | 1M | per-model (see docs) | ongoing | |||
| qwen-3.8-27b | 2026-08 | 08Cerebras | 64k | $5 trial credits | trial | cardcredits | ||
| Gemini 3.6 Flash | vision | 2026-07 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| Gemini 3.5 Flash-Lite | vision | 2026-07 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| nvidia/nemotron-3-ultra-550b-a55b:free | 2026-06 | 03OpenRouter (:free) | 1M | 20 rpm · 50 req/day | ongoing | 429strains | ||
| cohere/north-mini-code:free | code | 2026-06 | 03OpenRouter (:free) | 250k | 20 rpm · 50 req/day | ongoing | 429strains | |
| nvidia/nemotron-3.5-content-safety:free | vision | 2026-06 | 03OpenRouter (:free) | 125k | 20 rpm · 50 req/day | ongoing | 429strains | |
| nemotron-3-ultra-550b-a55b | 2026-06 | 05NVIDIA NIM | — | unpublished | ongoing | eval | ||
| north-mini-code-1.0 | code | 2026-06 | 09Cohere | 256k | 1k calls / month | ongoing | eval | |
| Gemini 3.1 Flash-Lite | vision | 2026-05 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| command-a-plus-05-2026 | 2026-05 | 09Cohere | 128k | 1k calls / month | ongoing | eval | ||
| google/gemma-4-31b-it:free | vision | 2026-04 | 03OpenRouter (:free) | 256k | 20 rpm · 50 req/day | ongoing | 429strains | |
| google/gemma-4-26b-a4b-it:free | vision | 2026-04 | 03OpenRouter (:free) | 256k | 20 rpm · 50 req/day | ongoing | 429strains | |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | omni+reasoning | 2026-04 | 03OpenRouter (:free) | 250k | 20 rpm · 50 req/day | ongoing | 429strains | |
| gemma-4-26b-a4b-it | vision | 2026-04 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| google/lyria-3-pro-preview | vision | 2026-03 | 03OpenRouter (:free) | 1.04858M | 20 rpm · 50 req/day | ongoing | 429strains | |
| google/lyria-3-clip-preview | vision | 2026-03 | 03OpenRouter (:free) | 1.04858M | 20 rpm · 50 req/day | ongoing | 429strains | |
| mistral-small-4 | reasoning | 2026-03 | 06Mistral La Plateforme | — | per-model (see docs) | ongoing | ||
| openrouter/free (auto-router) | vision | 2026-02 | 03OpenRouter (:free) | 195k | 20 rpm · 50 req/day | ongoing | 429strains | |
| glm-4.7-flash | 2026-01 | 04Cloudflare Workers AI | 131k | 10k neurons/day | ongoing | |||
| ministral-3-14b | 2025-12 | 06Mistral La Plateforme | — | per-model (see docs) | ongoing | |||
| gpt-oss-120b | reasoning | 2025-08 | 02Groq | 131k | 1k req/day · 8k tok/min | ongoing | slow | |
| gpt-oss-20b | reasoning | 2025-08 | 02Groq | 131k | 1k req/day · 8k tok/min | ongoing | slow | |
| gpt-oss-120b | reasoning | 2025-08 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| gpt-oss-20b | reasoning | 2025-08 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| codestral (v25.08) | code | 2025-08 | 06Mistral La Plateforme | — | per-model (see docs) | ongoing | ||
| gpt-oss-120b | reasoning | 2025-08 | 08Cerebras | 65k | $5 trial credits | trial | cardcredits | |
| command-a-reasoning-08-2025 | reasoning | 2025-08 | 09Cohere | 256k | 1k calls / month | ongoing | eval | |
| Gemini 2.5 Pro | vision | 2025-06 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| Gemini 2.5 Flash | vision | 2025-06 | 01Google AI Studio | 1M | ~1,500 req/day (Flash) | ongoing | trains | |
| llama-4-scout-17b-16e-instruct | vision | 2025-04 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| qwen3-30b-a3b-fp8 | 2025-04 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | |||
| mistral-small-3.1-24b-instruct | vision | 2025-03 | 04Cloudflare Workers AI | 128k | 10k neurons/day | ongoing | ||
| command-a-03-2025 | 2025-03 | 09Cohere | 256k | 1k calls / month | ongoing | eval | ||
| deepseek-r1-distill-qwen-32b | reasoning | 2025-01 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| llama-3.3-70b-instruct-fp8-fast | 2024-12 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | |||
| command-r7b-12-2024 | 2024-12 | 09Cohere | 128k | 1k calls / month | ongoing | eval | ||
| qwen2.5-coder-32b-instruct | code | 2024-11 | 04Cloudflare Workers AI | — | 10k neurons/day | ongoing | ||
| whisper-large-v3 (audio) | audio | 2023-11 | 02Groq | — | 1k req/day · 8k tok/min | ongoing | slow |