vlm.fyi by Ambient Get the data
Providers

Wafer via OpenRouter

1 model measured.

How Wafer via OpenRouter compares with other providers

Each dot is one or more of the model's other providers on that limit; the highlighted dot is Wafer via OpenRouter. The overall score ranks a model's providers: each limit as a percentage of the best provider's, averaged over the limits measured. 100 means it matches the best provider on every limit.

Kimi K3against its 11 other providers

Overall score?487th of 12 scored · 6 limitsbest 67 · Modal
Images724best ≥ 1,024 · Modal
768×432 frames≥ 384best, tied
Inline body≥ 32 MBbest, tied
Images by URL20 MBbest ≥ 128 MB · Baseten (fp8) via OpenRouter
Video fileNo videobest ≥ 512 MB · Decart (mxfp4) via OpenRouter
Video tok/minNobest 7,886 · Moonshot AI

Kimi K3

moonshotai/kimi-k3
Images
724 “This endpoint's maximum context length is 1048576 tokens. However, you requested about 1049347 tokens (1706 of text input, 1047625 of image input, 16 in the output). Please reduce the length of either one, or use the context-compression plugin to compress your prompt automatically.”
768×432 frames
≥ 384
Tokens / frame
457
Inline body
≥ 32 MB
Images by URL
20 MB “A remote image URL in the request could not be used. Remote images must be public http(s) URLs on the default port that answer quickly with a PNG, JPEG, GIF, WebP, BMP, TIFF, ICO, AVIF or HEIC image within the size limit. Send the image as a data: URI (base64) instead.”
Video file
No video “video and audio input is not supported for this model”
Video tok/min
No “video and audio input is not supported for this model”
Frames/min
—
Video input
No
Tool messages
Lenient
Extra fields
All accepted

Measured 2026-11-04