Looking for a Flim.ai alternative?

Where FrameThrower goes deeper

• —Cinema-first catalog. Features, documentaries and animation across 5,000+ films — curated frame sets picked and reviewed with working cinematographers, not a mixed archive of ads and everything else.
• —Craft-level indexing. Every frame carries lighting key and quality, lens character, shot size and framing, color, mood, film stock look and time of day — searchable alone or combined, in plain language.
• —Credits you can follow. Every result links to its film, director and cinematographer pages, so a found frame becomes a study of who made it and how.
• —Moodboards & lookbooks built in. Canvas moodboards, shot boards and exportable lookbooks in the same app — reference to deliverable in one place.
• —Developer friendly. Built by filmmakers who are also developers — designed to plug into modern, AI-assisted and agentic production workflows.
• —See it free before you commit. A free account includes full search. Paid plans add exports and higher limits. No card required.

Reachable by machines, not just by browser

Flim is a browser tab; this is infrastructure. FrameThrower is the reference app for the future creative: the library is callable from a REST API, an MCP server and an npm SDK, so an agent can pull references into a moodboard, a lookbook, a shot board or a production pipeline without a human in the loop.

npm install framethrower-ai

curl -X POST https://framethrower.ai/api/v1/search \
  -H "Authorization: Bearer ft_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "neon-lit rainy street at night", "limit": 5}'

Free tier included. $2 of credits on signup, no card, and they work through the API from the first call — no plan to buy first. After that it is usage-based: $1 = 1,000 credits, a search costs 2, so $1 buys 500 searches. Credits never expire.

Built by filmmakers and ads creatives, for film professionals. People who have shot, cut and pitched for a living — which is why the index is organised around lighting, lens and framing rather than keywords.

API documentation · machine-readable spec · npm package

Frequently asked questions

Does FrameThrower have an API?

Yes — a REST API with 11 endpoints and no rate limits, an MCP server with four tools (search_frames, find_by_craft, find_similar, get_frame_details), and an npm SDK (npm install framethrower-ai). A free account gets $2 of credits that work through the API from the first call, no card and no plan required; after that it is usage-based at $1 = 1,000 credits, and a search costs 2, so $1 buys 500 searches. Docs at framethrower.ai/developers.

How is FrameThrower different from Flim.ai?

Both are AI-powered image search tools, but they aim at different jobs. Flim spans movies, ads, music videos and archives for broad creative inspiration. FrameThrower goes deep on cinema: filmmaker-curated frame sets from 5,000+ films, indexed per frame by lighting key and quality, lens character, shot size, framing, color, mood and film stock look — the vocabulary DPs and directors actually brief in.

Is FrameThrower free to try?

Yes — a free account includes plain-language search across the full library, no card required. Paid plans add exports and higher usage limits.

Can I search by a reference image like on Flim?

Yes. Drop in any image and FrameThrower returns frames matching its light, color and composition, alongside plain-language search that can combine craft terms: "wide anamorphic desert at golden hour", "silhouette against a window, low-key".

Does FrameThrower do moodboards?

Built in: canvas moodboards, shot boards and exportable lookbooks live in the same app as search, so a reference hunt turns into a deliverable without export-import loops.