vlm.fyi Get the data
Models / DeepSeek

DeepSeek V4.1 Flash (1017)

Measured on 5 providers. The model card lists text, image input; what each provider accepts is below.

Fireworks via OpenRouter

deepseek/deepseek-v4.1-flash-1017
Images
120 “Too many images were provided, we currently limit the number of images per conversation to 120”
768×432 frames
112 “Too many images were provided, we currently limit the number of images per conversation to 120”
Tokens / frame
223
Inline body
≥ 32 MB
Images by URL
64 MB “Invalid image or video input”
Video file
No video “No endpoints found that support input video”
Video tok/min
No “No endpoints found that support input video”
Frames/min
—
Video input
No
Tool messages
Lenient
Extra fields
All accepted

Measured 2026-10-31

Fireworks

accounts/fireworks/models/deepseek-v4p1-flash-1017
Images
120 “Invalid image or video input”
768×432 frames
112 “Invalid image or video input”
Tokens / frame
223
Inline body
≥ 32 MB
Images by URL
80 MB “Invalid image or video input”
Video file
No video “Invalid image or video input”
Video tok/min
No “Invalid image or video input”
Frames/min
—
Video input
No
Tool messages
Lenient
Extra fields
All accepted
  • Fireworks counts every image in the messages array ("per conversation"), not per message.

Measured 2026-10-31

Jarvislabs

deepseek-v4.1-flash-1017
Images
999 “The model rejected the request parameters.”
768×432 frames
≥ 384
Tokens / frame
223
Inline body
12 MB “Request body exceeds the byte limit.”
Images by URL
≥ 128 MB
Video file
No video “The model rejected the request parameters.”
Video tok/min
No “The model rejected the request parameters.”
Frames/min
—
Video input
No
Tool messages
Lenient
Extra fields
All accepted
  • Inline bodies above ~5–8 MB fail with "Request body timed out" (about a 10 s window to receive the body), so the usable inline size depends on upload speed. Hard limit: HTTP 413 at 16 MB. Images by URL avoid both.

Measured 2026-10-31

Modal

deepseek-ai/DeepSeek-V4.1-Flash-1017
Images
999 “At most 999 image(s) may be provided in one prompt. (parameter=image)”
768×432 frames
≥ 384
Tokens / frame
223
Inline body
≥ 32 MB
Images by URL
≥ 128 MB
Video file
No video “At most 0 video(s) may be provided in one prompt. (parameter=video)”
Video tok/min
No “At most 0 video(s) may be provided in one prompt. (parameter=video)”
Frames/min
—
Video input
No
Tool messages
Lenient
Extra fields
All accepted

Measured 2026-10-31

Together AI

deepseek-ai/DeepSeek-V4.1-Flash-1017
Images
839 “Multimodal payload is 1503781440 bytes (1434.1 MiB) which exceeds the gRPC single-message ceiling of 1502189977 bytes (1432.6 MiB). Reduce the number of images, lower their resolution (e.g. `detail=”
768×432 frames
≥ 384
Tokens / frame
223
Inline body
≥ 32 MB
Images by URL
≥ 128 MB
Video file
No video “Invalid multimodal request: invalid media request for model deepseek_v41: modality video is not supported by model spec deepseek_v41”
Video tok/min
No “Invalid multimodal request: invalid media request for model deepseek_v41: modality video is not supported by model spec deepseek_v41”
Frames/min
—
Video input
No
Tool messages
Strict order
Extra fields
All accepted
  • Together caps the decoded media in one request at 1,502,189,977 bytes (≈1.43 GB). Images are decoded to tensors before this check, so pixel count matters, not file size.

Measured 2026-10-31