中文读者：直达中文部分 · 中文 Top 15 · 中文评分说明　|　English: Top 15 · How the score works

Tokenation

Tokenation collects free LLM API offers and checks every entry against the provider's own pages. Offers are split into two kinds:

Evergreen free tiers: standing free quotas with no announced end date, plus new-account trial allowances.
Each row records the provider, the model ID, a one-line overview, the free quota, the deadline and the score.

Limited-time offers: announced by the provider as free for a limited time, either with a fixed end date
or with no published deadline (the entry says so). Offers whose announced deadline has already passed are removed.

Top 9 by Tokenation score

The 9 best deals on the site right now, ranked by the Tokenation score.

Provider	Type	Model ID	Overview	Free quota	AA	Free until	Score	Link
Qoder	Limited-time	qwen3.8-flash	Qwen3.8-Flash uses no Credits within daily allowance	Qwen3.8-Flash daily free allowance…	39.8	No deadline announced	86.53	→
OpenCode Zen	Limited-time	deepseek-v4.1-flash-free	DeepSeek V4.1 Flash free for a limited time	10 limited-time free models; app-only	32.5	No deadline announced	81.66	→
OpenCode Go	Limited-time	beam-free	Beam model free for a limited time in OpenCode Go	Beam + Iceman limited-time free; both…	30.3	No deadline announced	80.20	→
Vercel AI Gateway	Limited-time	reflection/beam-free	Beam open-weight model with ~501B total parameters	3 visible models at $0 input/output (37…	30.3	No deadline announced	80.20	→
Google Gemini API	Evergreen	gemini-3.8-flash	Google's strongest Flash model for coding, agents and multi-step reasoning.	Gemini 3.8 Flash free-tier input/output…	30.5	Ongoing	68.35	→
AutoClaw (Z.ai / Zhipu)	Limited-time	glm-5.3	Z.ai reasoning model for software engineering and long-horizon agent tasks.	40M tokens; expires Nov 8 at 23:59 (UTC…	31.7	2026-11-08 (in 3 days)	57.15	→
AiHubMix	Limited-time	xiaomi-mimo-v2.6-pro-free	Xiaomi MiMo V2.6 Pro flagship.	71 models at $0; after top-up, 100 req/…	46.3	No deadline announced	53.47	→
AiHubMix	Limited-time	coding-glm-5.3-free	Z.ai GLM 5.3 coding variant.	71 models at $0; after top-up, 100 req/…	44.8	No deadline announced	52.47	→
AiHubMix	Limited-time	coding-glm-5.3-flash-free	Z.ai GLM 5.3 Flash coding variant.	71 models at $0; after top-up, 100 req/…	41.8	No deadline announced	50.47	→

Top 9 of 66 scored model rows. Scoring rule below. Full lists below.

How the score works

Every offer here carries one number from 0 to 100, so an offer you have never touched can be compared against one you already pay for. Free API tiers change every week, and signing up to test each one costs a weekend, so the score compresses that decision into a single number. It measures how much usable inference you get for free right now. It is not a ranking of model quality.

• Intelligence, 40%: the model's Artificial Analysis index.

• Free quota, 60%: how much you can actually run before you hit a wall.

• Every score traces back to the provider's own page, rechecked daily.

• Out of scope, so never scored: decision models that return typed answers instead of text, routing endpoints (an "auto" model selection), and models under 20B total parameters.

• Chinese: Evergreen free tiers

• Chinese: Limited-time offers

• English: Evergreen free tiers

• English: Limited-time offers

↑ Back to top · Chinese version

---

Tokenation（中文）

Tokenation 每日搜集免费 LLM API，并逐条回到厂商官方页面核实。条目分两类：

常态免费（Evergreen），官方定价页长期挂着、无公告结束时间的免费额度，含新用户免费额度。
每行记录平台、模型 ID、一段简介、免费额度、截止日与推荐指数。

限时免费（Limit-time），官方明示的限时免费 offer，含两类：写明固定截止日的，以及只写「限时」
未公布截止日的（会在日期字段注明）。已过公布截止日的条目一律移除。

推荐指数榜 · Top 9

本站此刻最值的 9 单，按推荐指数从高到低。

平台	类型	模型 ID	介绍	免费额度	AA	截止	推荐指数	链接
Qoder	限时	qwen3.8-flash	Qwen3.8-Flash 每日限额内不扣 Credits	Qwen3.8-Flash 每日额度免费；另每日领 100 Credits	39.8	未公布截止日	86.53	→
OpenCode Zen	限时	deepseek-v4.1-flash-free	DeepSeek V4.1 Flash 限时免费模型	10 个限时免费模型；仅限应用内使用	32.5	未公布截止日	81.66	→
OpenCode Go	限时	beam-free	OpenCode Go 内限时免费的 Beam 模型	Beam 与 Iceman 限时免费；均标 Unlimited	30.3	未公布截止日	80.20	→
Vercel AI Gateway	限时	reflection/beam-free	Beam 开放权重模型，约 501B 总参数	3 个可读模型输入输出 $0（共 37 个促销位）	30.3	未公布截止日	80.20	→
Google Gemini API	常态	gemini-3.8-flash	谷歌最强 Flash，擅长编码、Agent 与多步推理	Gemini 3.8 Flash 免费层输入输出免费；按项目限流	30.5	长期有效	68.35	→
AutoClaw（智谱）	限时	glm-5.3	智谱推理模型，面向软件工程与长周期 Agent 任务	4,000 万 Tokens；11/8 23:59 到期	31.7	2026-11-08（剩余 3 天）	57.15	→
AiHubMix	限时	xiaomi-mimo-v2.6-pro-free	小米 MiMo V2.6 Pro 旗舰版	71 款模型 $0；充值后每日 100 请求、1M tokens	46.3	未公布截止日	53.47	→
AiHubMix	限时	coding-glm-5.3-free	智谱 GLM 5.3 编码专用版	71 款模型 $0；充值后每日 100 请求、1M tokens	44.8	未公布截止日	52.47	→
AiHubMix	限时	coding-glm-5.3-flash-free	智谱 GLM 5.3 Flash 编码快速版	71 款模型 $0；充值后每日 100 请求、1M tokens	41.8	未公布截止日	50.47	→

上表从 66 行已评分条目中取前 9 行，评分口径见下节。完整清单见下方四个列表。

评分怎么看

本站每个条目都带一个 0 到 100 的分数，让你能拿一个没试过的免费额度，和一个已经在用的放在一起比。免费额度每周都在变，逐个注册去试要花掉一个周末，这个分数把这件事压缩成一个数字。它量的是此刻免费能拿到多少可用推理，不是模型强弱排名。

• 智能占 40%：取模型在 Artificial Analysis 智能指数上的位置。

• 免费额度占 60%：真跑起来撞墙之前能用多少。

• 每个分数都能追回厂商自己的页面，每天重新核实一次。

• 不参与评分：只返回类型化结果的决策模型、路由端点（auto 自动选模），以及总参数低于 20B 的模型。

• 中文：常态免费

• 中文：限时免费

• 英文：常态免费

• 英文：限时免费

↑ 回到顶部 · English version