🪙 Free Token

### Aion Labs 🇮🇱 Permanent free tier, no credit card required. 15 RPM, 20K tokens/day. Specialized for roleplay and storytelling. Base URL: ` [...] ### Groq 🇺🇸 Free tier, no credit card. Ultra-fast LPU inference. 5 B

OpenRouter, Groq, Cerebras, Cloudflare Workers AI, Mistral, and GitHub Models all offer free access with no credit card. Google AI Studio requires only a Google account. SambaNova is the main exception that asks for paym

By provider (31): AI21 Labs · Aion Labs · Cerebras · Cerebrium · Cloudflare Workers AI · Cohere · Coze · Fireworks AI · Friendli AI · Google AI Studio · Groq · Hetzner Inference API · LLM7.io · Mistral (La Plateforme) ·

If you are building anything with LLMs in 2026, you should not be paying for inference yet. Between Google's Gemini free tier, Groq, Cerebras, OpenRouter, and a dozen smaller providers, you can run real production worklo

In this article, we have compiled a list of LLM API providers that offer free tiers without requiring credit card registration, as well as practical knowledge on how to combine them to build robust systems. Note: The fr

DEV Community ## DEV Community tokenmixai Posted on Apr 10 • Originally published at tokenmix.ai # 12 Free LLM APIs You Can Use Right Now (No Credit Card, Real Limits Tested) "Free LLM API" results are full of outda

[1:57] in mind to use it just for learning and practice in our list. The third provider is GitHub models. Microsoft owns GitHub. [2:07] Microsoft also partner heavily with Open AI. So guess what? If you have a GitHub acc

Fortunately, as of 2026, LLM APIs with free tiers that require no credit card are no longer rare. But if you stop at "apparently there's a free tier," the moment you actually run something you'll get smacked with `429 To

Copilot tier） 做 MVP、教学演示、个人脚本再也不用到处找 Key 了。 仓库地址： [...] Key 了。 仓库地址：github.com/cheahjs/free-l… [...] Key 了。 仓库地址：github.com/cheahjs/free-l…

#### 鸿枫 #### 鸿枫 # 告别 API 焦虑！我整理了一份全网最全的《免费 Token / 超值套餐》薅羊毛指南 头像 ## 💡 写在前面 进入 AI 时代，大模型能力越来越强，但随之而来的“Token 焦虑”也成了很多开发者和 AI 爱好者的痛点。无论是日常写代码、做 Agent 开发，还是单纯想体验最新的顶尖模型，动辄按量计费的 API 账单总是让人肉疼。 为了解决这个痛点，我最近肝出了一个飞书知识库 —— 《

导航站： TG反馈交流群： 【闪电狐家宽机场(8.8折优惠码：EOOCE】: 【超值香港长期保号号码+无限流量esim】 【Eskimo免费1G全球esim家宽e流量，有效期2年】 【ESTK让国航手机支持esim,10%抵扣码: UPTHFAOQT4】: 【KAST免费两张u卡】 【Pokepay香港实体卡,可注册甲骨文】 【B2proxy住宅代理, 专属9折优惠码：MrWang9（如遇到优惠码无效,可联系在线客服返还余额)】

### Cursor 配置 1. 打开 `Settings` → `Models` → `Add Model` 2. Model name: `llama-3.3-70b-versatile` 3. Base URL: ` 4. API key: 填入你的 Groq 免费 Key ### Claude Code 配置 如果你想在终端里用 Claude Code，又不想花官方 Anthropic 的高昂 API 费，

## 2026 大模型 API 免费额度汇总 原创 腾讯云 开发者社区 文档建议反馈控制台 首页 学习 活动 专区 圈层 工具 MCP广场 文章/答案/技术大牛 发布 云煮鱼 社区首页 >专栏 >2026 大模型 API 免费额度汇总 # 2026 大模型 API 免费额度汇总 作者头像 云煮鱼 修改于 2026-03-17 17:19:07 修改于 2026-03-17 17:19:07 65.

> | 输入范围 | 输入价格 | 输出价格 | > --- > | 0 - 128K | 0.00084 CA/1K Tokens | 0.00504 CA/1K Tokens | > | > 128K | 0.0021 CA/1K Tokens | 0.0126 CA/1K Tokens | > | 输入范围 | 输入价格 | 输出价格 | > --- > | 0 - 128K | 0.00056 CA/1K Tokens

常见原因： 使用的模型已经没有免费额度。 免费额度不支持抵扣OpenAI兼容-Batch（文件输入）产生的费用。 控制台的免费额度数据为分钟级更新且需手动刷新。若未及时刷新，页面显示仍有额度但实际已耗尽，导致产生调用费用。操作前刷新页面，以最新显示为准。 IDE 插件自动补全导致 Token 快速消耗。使用 Cline、CodeBuddy 等 IDE 插件调用模型时，插件会自动携带完整的代码上下文和对话历史，单次对话可能消耗数

免费额度已到期或耗尽：免费额度的有效期为 90 天，从开通阿里云百炼、模型发布或模型申请通过之日起计算（以较晚者为准），到期或耗尽后将不再显示，继续调用模型将产生计费。 该模型所在地域或服务部署范围不享有免费额度：仅华北2（北京）地域的模型享有免费额度，其他地域和部署范围无免费额度。 该模型本身不提供免费额度：部分模型不参与新人免费额度发放。判断某模型是否享有免费额度，可在控制台模型广场进入该模型详情页，查看免费额度区域是否有余量显

| Poolside: Laguna M.1 (free) | OpenRouter | 262K | 768B tokens | | NVIDIA: Nemotron 3 Super (free) | OpenRouter | 262K | 750B tokens | | Dots Studio: Dots3-Note Preview (free) | OpenRouter | 512K | 704B tokens | | Apode

## The repo with the clearest free-tier details If the goal is to find concrete free-tier information instead of vague "free AI" claims, mnfst/awesome-free-llm-apis stands out. Its public listing names direct provider

beeper/aibot - A ChatGPT bot for Matrix vossenwout/free-llm-apis - Scripts showing how to connect to a variety of llm providers with a free thier ConsistentlyInconsistentYT/Pixeltovoxelprojector - Projects motion of pi

| | | | | --- --- | | Google Google | Groq | Cerebras Cerebras | OpenCode Zen | | Mistral Mistral | OpenRouter OpenRouter | Cloudflare Cloudflare | Cohere Cohere | | Z.ai (Zhipu) Z.ai (Zhipu) | NVIDIA NVIDIA | Hugg

Star 3 ⚡ Curated directory of 180+ Free AI APIs & Models: LLMs, Multi-Modal Vision, Image Gen, Voice, Embeddings & RAG with Free Tiers (No Credit Card Required). machine-learning awesome artificial-intelligence develo

## Key Features Tool Selection - LLMs intelligently select tools based on descriptions Type Safety - Strong typing throughout the execution pipeline Reliability - Circuit breakers, retry policies, and error handling

OpenRouter’s free plan is real: 25+ free models, 50 requests per day, 20 RPM, and `openrouter/free` as a single router across a rotating pool. Good for experimentation, model comparison, and rough production fallback. [.

Which models are free on OpenRouter? As of June 2026, OpenRouter has 28+ free models. Standouts: Qwen3 Coder 480B (free) - strongest free coding model with 262K context. DeepSeek R1 (free) - top reasoning model. DeepSeek

The first is the free-model cap: 20 per minute, 50 or 1,000 per day, applied to any model ID ending in `:free`. That one is published and predictable. The second is the capacity of whichever provider is actually serving

by mistralaiApr 30, 2026262K context$1.50/M input tokens$7.50/M output tokens Mistral: Mistral Medium 3.5 (batch)Mistral Medium 3.5 (batch) 1.01M tokens [...] by mistralaiFeb 17, 202533K context$0.20/M input tokens$0

As of October 31, 2026: Free - rate-limited GroqCloud API access; Developer - pay-as-you-go per token with higher rate limits, Batch and Flex processing, billed monthly; e.g. GPT OSS 120B $0.15/M input, $0.60/M output; G

1fr));gap:0 1.75rem}"}],"page":{"pagePath":"api\_reference/limits","slug":"/api\_reference/limits","pageMetadata":{"publish":true,"title":"Limits","description":"Credit Limits and Rate Limits","seoTitle":"API Credit \u00

by meta-llamaJul 23, 2024131K context$0.05/M input tokens$0.08/M output tokens [...] by openaiOct 29, 2025$0.075/M input tokens$0.30/M output tokens OpenAI: gpt-oss-120bgpt-oss-120b [...] by openaiAug 5, 2025131K contex

OpenAI and Google also offer free tiers for developers to test their AI models, which both have lower rate limits than their pricier tiers. Mistral's new tier is available through its API-serving platform, la Plateforme