Newshot

Itsfree.ai – Every model you can use for free

Original text(via HN AI)
题图
题图
  • Qwen 3Alibaba’s family, from 0.6B you can run on a laptop to MoE giants. Hosted APIs name the exact weight; this page is the family.17 freeopen
  • Llama 3.3 70BMeta’s classic open model. Nearly every free provider here serves it, which makes it the safest default.15 freeopen
  • GPT-OSS 120BOpenAI’s open-weights release. Runs on your own hardware, or free on Groq. Cerebras still serves it on a $5 signup credit.12 freeopen
  • DeepSeek V4The current DeepSeek family: V4 Flash and V4 Pro, 1M of context, thinking as a switch rather than a second model.8 freeopen
  • Nemotron 3 UltraNVIDIA’s 550B Ultra, tuned for agents and function calling. Free on NIM, OpenRouter (:free) and Requesty.6 freeopen
  • DeepSeek V4 FlashThe current DeepSeek workhorse: 1M of context, thinking as a switch. Official id deepseek-v4-flash; AMD serves DeepSeek-V4-Flash-0731.5 freeopen
  • GLM 5.2Z.ai’s current flagship. Excellent at coding and tool calling. Free on OpenRouter (z-ai/glm-5.2:free); on Z.ai itself GLM-5 bills per token.5 freeopen
  • Qwen 3.8 27BAlibaba’s current 27B: thinking or instruct in one id, images in. Groq serves it at 131K; Cloudflare’s free window reaches 262K.5 freeopen
  • Qwen CoderThe coding branch of Qwen. Small enough to run locally, good enough to power editor autocomplete.5 freeopen
  • Mixtral 8x7BThe mixture-of-experts model that proved MoE works in the open. Retired from Mistral’s own API; still a great local pick.4 freeopen
  • Laguna XSPoolside’s small coding model. OpenRouter’s free id is poolside/laguna-xs-2.1; Requesty serves poolside/laguna-xs.2 at 33K.4 free
  • Gemini 3.7 FlashGoogle’s current Flash workhorse — coding, agents and multimodal input, 1M of context, free to try in AI Studio.2 free
  • Kimi K3Moonshot’s current open MoE. Strong at agentic tool use and coding. Free on NVIDIA NIM; Groq retired the old K2 ids.2 freeopen
  • DeepSeek R1The 2025 reasoner that made chain-of-thought open. Gone from DeepSeek’s own API; still free on a few hosts and as local weights.2 freeopen
  • Qwen3.8-Flash-NextThe Flash-Next 3.8 checkpoint. AMD Radeon Cloud serves this exact id on the $10/day Token Factory quota.2 freeopen
  • Gemma 4 31BGoogle’s open 31B. Cerebras serves gemma-4-31b on a $5 signup credit; Requesty lists google/gemma-4-31b-it at $0.2 freeopen
  • Nemotron 3 SuperThe 120B Super. Requesty’s docs example and a $0 id on that gateway; also :free on OpenRouter.2 freeopen
  • Gemini 3.5 Flash LiteThe cheapest current Gemini. Built for classification, extraction and anything you run thousands of times a day.1 free
  • GPT-OSS 20BThe smaller open-weights GPT-OSS. Faster than 120B on Groq, same 131K window and 1,000 requests a day.1 freeopen
  • GPT-OSS Safeguard 20BThe safety classifier in the GPT-OSS line. Groq serves it on the same free chat quota as the other 20B.1 freeopen
  • DeepSeek V3.1The previous DeepSeek generation. Retired from the official API; SambaNova still hosts V3.1 on the free tier.1 freeopen
  • GLM 4.7 FlashThe permanent free line on Z.ai. 200K of context. glm-4.7, glm-5 and glm-5.2 on that host bill per token.1 freeopen
  • Qwen 3.6 27BThe previous 27B Qwen still on Groq’s free list. Same 131K window and 30 requests a minute as 3.8.1 freeopen
  • Qwen 3.7 PlusThe current plus id on Alibaba Model Studio (Singapore / intl). 1M of context, 1M free tokens for 90 days. qwen3-plus is not a current id.1 free
  • Qwen 3 30B-A3BThe 30B MoE (3B active). Cloudflare serves @cf/qwen/qwen3-30b-a3b-fp8 on the free Workers AI pool.1 freeopen
  • Qwen 3.5 397BThe 397B-A17B Qwen 3.5. Ollama Cloud’s current Qwen id is qwen3.5:397b.1 freeopen
  • Qwen 3 8BThe 8B Qwen 3 instruct. SiliconFlow’s free-tier example id; small enough to run locally too.1 freeopen
  • Mistral SmallMistral’s current small line. Free mode on La Plateforme uses this id; Labs models (labs- prefix) are also free of charge.1 free
  • Command ACohere’s enterprise model, built around RAG and citations. The trial key never expires.1 free
  • Jamba 1.5 LargeA hybrid Mamba-Transformer. Unusually cheap on long documents thanks to its architecture.1 freeopen
  • Groq CompoundNot one model but a system: Groq routes your request across models and built-in tools like web search.1 free
  • Groq Compound MiniThe lighter Compound system on Groq. Same tool-routing idea, smaller default stack.1 free
  • Mistral Medium 3.5Mistral’s balanced model: European hosting and 256K of context. Paid on La Plateforme; not the free-tier chip.0 free
  • Phi-4Microsoft’s small model that punches far above its size on reasoning benchmarks.0 freeopen

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by HN AI
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗