Free AI Model APIs
| Model / Platform | Cloudflare Workers AI64 models | NVIDIA API Catalog36 models | OpenCode Zen / Console13 models | Vercel AI Gateway10 models |  OpenRouter6 models |  Respan3 models |
|---|---|---|---|---|---|---|
| — | — | — | ||||
| — | — | — | — | |||
| — | — | — | — | |||
| — | — | — | — | |||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
43 deals · page 2 of 4
Current offers
Beam Free on OpenCode, use Reflection's open Beam model at no cost with 1M context
OpenCode added Beam Free, the free version of Reflection's open-source Beam 1.0, to both Zen and Go. Input, output, and cache reads cost nothing, and it doesn't use Go plan quota. It offers about 1M tokens of context and up to about 131K output tokens, with reasoning and tool calling, and no end date has been announced.
Free
Reflection's open 501B Beam model is free on Vercel AI Gateway with 1M context
Reflection open-sourced Beam 1.0, a 501B-parameter model, on October 16, and Vercel AI Gateway added a free version as reflection/beam-free with $0 input and output. It has about 1M tokens of context and up to about 131K output tokens, is built for coding and agentic tasks, and has no published usage cap or end date.
Free
OpenCode Zen adds LL Alpha Free, a limited-time $0 text reasoning model (~262k context)
OpenCode Zen just added LL Alpha Free, an anonymous text model billed at $0 for input, output, and cached reads. It offers about 262k tokens of context and up to ~65k output tokens, with reasoning and tool use. It is free for a limited time with no end date announced yet.
Free (rate limits vary by route)
Free AI decision models from Jev to Liquid d1
Jev is free for a limited time on OpenCode Zen. Mercury Decide and Span-01 Lite offer free API access, while new Liquid organizations receive $2 in trial credits. Kev and Laya can be hosted on your own hardware.
Free (rate limited)
NVIDIA Nemotron 3.5 Super VL is free on OpenRouter with 1M context and multimodal input
OpenRouter added a free version of NVIDIA Nemotron 3.5 Super VL. Input and output cost nothing, with rate limits on the free endpoint. It reads images, document screenshots, and video, has about 1M tokens of context, and supports tool calls and structured outputs.
Full amount of last 7 days' spend
DeepSeek API outage gift credit matches your last 7 days of spend
After the DeepSeek API outage on Oct 15, 2026 (08:11–13:04 Beijing time), DeepSeek is returning gift credit equal to your account spend from Oct 8–14. Credit lands automatically, and later API charges draw from the gift balance first.
$10 per 1M characters (list $50)
Fish Audio Drama 3 text-to-speech is 80% off on Vercel AI Gateway at $10 per million characters through November 12
Fish Audio’s new Drama 3 text-to-speech model is now on Vercel AI Gateway, and it is 80% off for its first 30 days. Through November 12, it costs $10 per million characters instead of $50. Call fish-audio/drama-3 with your AI Gateway API key for voiceovers, character dialogue, and audiobooks.
Free
Nemotron 3.5 Lightning free API on Vercel AI Gateway and OpenRouter at $0
NVIDIA's open Nemotron 3.5 Lightning has free versions on Vercel AI Gateway and OpenRouter, with $0 input and output. It has a 1M-token context, up to about 65K output tokens and tool calling. No end date has been announced, and the provider may keep prompts and responses from the free version for training.
100M free input tokens (worth $5) for the first 10,000 signups
SubQ Snap gives the first 10,000 signups 100M free input tokens, worth $5 in API credit
Subquadratic just released its SubQ Snap decision model in public preview, and the first 10,000 people to sign up get 100 million free input tokens, worth $5 in API credit. Snap only bills input at $0.05 per million tokens, output is free, and a single request can take up to 384K tokens of text and images.
Free
Alibaba Cloud Model Studio decision-model-preview is free for a limited time
Alibaba Cloud Model Studio's new decision model, decision-model-preview, is free to call for a limited time in both the Singapore and China (Beijing) regions. One request runs classification, yes/no checks, and scoring in parallel and returns probabilities with confidence scores.
Go: $8 first month, up to $120/month in credits
OpenDesign Go is $8 for the first month with up to $120 a month in DeepSeek V4.1 Flash credits
OpenDesign doubled DeepSeek V4.1 Flash credits on every paid plan. Go is $8 for your first month on a new monthly subscription, then $10 a month, and includes up to $120 a month of DeepSeek V4.1 Flash usage plus an API key you can use in OpenCode and other tools.
$25 signup credit (valid 3 months)
Nace.AI gives new signups $25 in API credit for three months, usable on Drex and document tools
New Nace.AI accounts get $25 in API credit at signup, valid for three months and shared between the Drex decision model and the Document Intelligence tools. After that you get $5 every month, plus $5 for each friend you refer once they make a paid call.