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 |
|---|---|---|---|---|---|---|
| — | — | — | ||||
| — | — | — | — | |||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
| — | — | — | — | — | ||
38 deals · page 1 of 4
Current offers
Free
OpenCode Go adds stealth model Iceman, free and unlimited for now
OpenCode Go just added Iceman Contributor Free, a stealth model that's free for a limited time with no request limits, and it doesn't count against your Go plan's monthly usage. It has a 262K-token context and tool calling. You need an OpenCode Go subscription and must allow the model to learn from your requests.
Flint 40B is free on OpenCode, a new open coding-agent model at no cost!
OpenCode Zen added Flint 40B Free, the free version of Recursive's open-source coding model Flint. Input, output, and cache reads cost nothing. Flint is a mixture-of-experts model with about 40B total and 2.5B active parameters and about 262K tokens of context. It's also free on OpenRouter and Kilo, and no end date has been announced.
NVIDIA API Catalog lets you call 40+ models for free, no per-token billing
Join the free NVIDIA Developer Program and call 40+ hosted models on build.nvidia.com for free, including DeepSeek V4.1 Flash, MiniMax M3.1 Flash and Nemotron 3.5. Most models allow up to 40 requests per minute with no per-token billing, for prototyping and testing.
Nscale gives new users $5 in free credit to try GLM-5.3
UK AI cloud provider Nscale gives every new user $5 of free credit. Claim it in the console after signing up and call the newly added GLM-5.3 through an OpenAI-compatible API, at $1.40 per million input tokens and $4.40 per million output tokens.
Free for a limited time · includes voice cloning
Xiaomi MiMo text-to-speech API is free for now, voice cloning included
Xiaomi made its three MiMo TTS models free for a limited time: standard speech, voice cloning, and voice design. Calls don't charge your pay-as-you-go balance or use Token Plan credits. Sign up, create an API key, and call them through an OpenAI-compatible endpoint.
$0.0425/s at 720p (list $0.17)
FLUX 3 Max video model is 75% off on fal.ai until November 7, now $0.0425 per second at 720p
FLUX 3 Max, the new video model on fal.ai, is 75% off until November 7: 720p video costs $0.0425 per second instead of $0.17. Billing is per second of output, with no minimums and no subscription, and text-to-video and image-to-video cost the same.
100M free tokens for new accounts
Inception gives new accounts 100M free tokens to try Mercury 3, no card needed
Every new Inception Platform account gets 100 million free tokens with no payment details required, so you can call the newly released Mercury 3 right away. Mercury 3 is also 50% off at launch: $0.10 per 1M input tokens and $0.35 per 1M output tokens.
Free until Nov 1 (then $0.75/1K)
DeepSeek API web search and fetch are free in Claude Code and Codex until November 1
When you run Claude Code, Codex, or DeepSeek Harness on the DeepSeek API, the web search and page fetch calls the model makes are free for now. Billing starts at 00:00 Beijing time on November 1, 2026, at $0.75 per 1,000 successful requests.
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.