Kimi K3.1 Pro

Alibaba Cloud via OpenRouter

Images

250 “Exceeded limit on max number of data-uri items : 250”

768×432 frames

224 “Exceeded limit on max number of data-uri items : 250”

Tokens / frame

457

Inline body

20 MB “Downloaded image content cannot exceed 30MB”

Images by URL

28 MB “Downloaded image content cannot exceed 30MB”

Video file

No video “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Video tok/min

No “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Frames/min

—

Video input

No

Tool messages

Lenient

Extra fields

All accepted

Measured 2026-11-05

DeepInfra (bf16) via OpenRouter

Images

30 “Too many images in request: 31 > 30”

768×432 frames

28 “Too many images in request: 32 > 30”

Tokens / frame

461

Inline body

≥ 32 MB

Images by URL

≥ 128 MB

Video file

No video “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Video tok/min

No “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Frames/min

—

Video input

No

Tool messages

Lenient

Extra fields

All accepted

Measured 2026-11-05

Fireworks

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

457

Inline body

≥ 32 MB

Images by URL

80 MB (10 MB/image) “Image <url> download size exceeded maximum size limit of 10.0 MB”

Video file

96 MB “Video <url> download size exceeded maximum size limit of 100.0 MB”

Video tok/min

324,240

Frames/min

480

Video input

Yes

Tool messages

Lenient

Extra fields

Rejects usage, reasoning

• Video is sampled at 8 frames per second, in groups of 4 at full resolution (~2,700 tokens per group, ~324k tokens per minute). On Nov 5 the full 5-minute clip timed out at 300 s and one minute took ~7 minutes to process. Density was measured on the first minute of the reference clip.

Measured 2026-11-05

Fireworks via OpenRouter

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

457

Inline body

≥ 32 MB

Images by URL

80 MB (10 MB/image) “Image <url> download size exceeded maximum size limit of 10.0 MB”

Video file

96 MB “Video <url> download size exceeded maximum size limit of 100.0 MB”

Video tok/min

324,240

Frames/min

480

Video input

Yes

Tool messages

Lenient

Extra fields

All accepted

• Same sampling as Fireworks direct: 8 frames per second, in groups of 4. The first minute of video took 58 s on Nov 8; on Nov 5 the same request hit OpenRouter's 300 s limit.

Measured 2026-11-08

Modal (mxfp4) via OpenRouter

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

≥ 128 MB

Video file

No video “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Video tok/min

No “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Frames/min

—

Video input

No

Tool messages

Lenient

Extra fields

All accepted

Measured 2026-11-08

Moonshot AI

Images

≥ 488 “488 images passed and 496 failed with HTTP 429 "request reached organization TPM", reproducibly, each request after a full minute's cooldown.”

768×432 frames

≥ 384

Tokens / frame

457

Inline body

≥ 32 MB

Images by URL

No “{"error":{"message":"Invalid request: unsupported image url: <url>”

Video file

≥ 96 MB

Video tok/min

7,886

Frames/min

11.7 ⁎

Video input

Yes

Tool messages

Strict order

Extra fields

All accepted

• Takes video only inline (base64): video URLs are refused. Video density and file size were measured with the video sent inline.

Measured 2026-11-08

Moonshot AI (highspeed) via OpenRouter

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

20 MB “Downloaded image content cannot exceed 30MB”

Images by URL

28 MB “Downloaded image content cannot exceed 30MB”

Video file

≥ 96 MB

Video tok/min

7,886

Frames/min

11.7 ⁎

Video input

Yes

Tool messages

Strict order

Extra fields

All accepted

• Takes video only inline (base64): video URLs are refused. Video density and file size were measured with the video sent inline.

Measured 2026-11-08

Moonshot AI (mxfp4) via OpenRouter

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

20 MB “Downloaded image content cannot exceed 30MB”

Images by URL

28 MB “Downloaded image content cannot exceed 30MB”

Video file

≥ 96 MB

Video tok/min

7,886

Frames/min

11.7 ⁎

Video input

Yes

Tool messages

Strict order

Extra fields

All accepted

• Takes video only inline (base64): video URLs are refused. Video density and file size were measured with the video sent inline.

Measured 2026-11-08

Nebius (fp4) via OpenRouter

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

458

Inline body

≥ 32 MB

Images by URL

≥ 128 MB

Video file

No video “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Video tok/min

No “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Frames/min

—

Video input

No

Tool messages

Lenient

Extra fields

All accepted

Measured 2026-11-05

Together AI

Images

999 “Multimodal processing failed: At most 999 image(s) may be provided in one request, got 1000”

768×432 frames

≥ 384

Tokens / frame

457

Inline body

≥ 32 MB

Images by URL

64 MB “Failed to start generation: Failed to generate completions: CannotConnect (a request carrying 128 MB of images by URL)”

Video file

≥ 512 MB

Video tok/min

Ignored

Frames/min

—

Video input

Ignored

Tool messages

Strict order

Extra fields

All accepted

• Accepts a video_url with HTTP 200, but the video adds no tokens: the model never sees it.

Measured 2026-11-08

Together AI via OpenRouter

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

64 MB “Failed to start generation: Failed to generate completions: CannotConnect (a request carrying 128 MB of images by URL)”

Video file

No video “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Video tok/min

No “OpenRouter had no endpoint to route this to (removed by its Input Video Support filter).”

Frames/min

—

Video input

No

Tool messages

Strict order

Extra fields

All accepted

Measured 2026-11-08