vlm.fyi Get the data
Models / Qwen

Qwen3.8 27B

Measured on 22 providers. The model card lists text, image, video input; what each provider accepts is below.

AkashML (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Alibaba Cloud via OpenRouter

qwen/qwen3.8-27b
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
338
Inline body
20 MB “Downloaded image content cannot exceed 30MB”
Images by URL
28 MB “Downloaded image content cannot exceed 30MB”
Video file
≥ 512 MB
Video tok/min
35,640
Frames/min
60
Video input
Yes
Tool messages
Lenient
Extra fields
Rejects response_format
  • Inline images are capped at 250 data URIs per request; images sent by URL are capped at 30 MB of downloaded content instead.

Measured 2026-10-31

Cerebras (fp16) via OpenRouter

qwen/qwen3.8-27b
Images
2 “{"error":{"message":"Provider returned error","code":413,"metadata":{"raw":""Number of image inputs exceeds maximum of 2"","provider_name":"Cerebras","is_byok":false}},"user_id":"<redacted>"}”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “{"error":{"message":"No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Input Video Support removed modal, tenstorrent/fp4, cerebras/fp16; Filter by Fallback removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, dekallm, wafer/fp8, deepinfra/bf16, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, novita, alib”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Chutes (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
4.4 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Cloudflare via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “AiError: AiError: {\\”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

CoreWeave (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,274
Frames/min
—
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

DarkBloom (fp4) via OpenRouter

qwen/qwen3.8-27b
Images
64 “media input exceeds size limit”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
Rejected “a media file exceeds the maximum allowed size”
Frames/min
—
Video input
Unknown
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

DeepInfra (bf16) via OpenRouter

qwen/qwen3.8-27b
Images
30 “Too many images in request: 31 > 30”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

DekaLLM via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,330
Frames/min
4 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

IonStream (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
8 “litellm.BadRequestError: OpenAIException - Image count 9 exceeds limit 8 per request.\ \ LiteLLM: model group 'qwen/qwen3.8-27b-fp8' failed with the error above. No fallback was attempted.”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “litellm.BadRequestError: OpenAIException - Video count 1 exceeds limit 0 per request.\ \ LiteLLM: model group 'qwen/qwen3.8-27b-fp8' failed with the error above. No fallback was attempted.”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Jarvislabs

qwen-3.8-27b-fp8
Images
4 “The model rejected the request parameters.”
768×432 frames
4 “The model rejected the request parameters.”
Tokens / frame
355
Inline body
12 MB “Request body exceeds the byte limit.”
Images by URL
≥ 128 MB
Video file
256 MB “The model rejected the request parameters.”
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
Lenient
Extra fields
All accepted
  • The deployment accepts at most 4 images per request.

Measured 2026-10-31

Mancer (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
Rejected “Bad Parameters. \ (No credits charged.)”
Frames/min
—
Video input
Unknown
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Modal via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “{"error":{"message":"No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Input Video Support removed modal, tenstorrent/fp4, cerebras/fp16; Filter by Fallback removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, dekallm, wafer/fp8, deepinfra/bf16, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, novita, alib”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

ModelRun (fp4) via OpenRouter

qwen/qwen3.8-27b
Images
16 “failed to translate request: building multimodal request: too many media items in request: 17 exceeds the limit of 16”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “failed to translate request: building multimodal request: video must be H.264 (avc1) in an MP4 container (codec \\”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

NEAR AI (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “Content part type 'video_url' is not supported by this model.”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Novita via OpenRouter

qwen/qwen3.8-27b
Images
250 “invalid request error trace_id: <id>”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
35,640
Frames/min
—
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Parasail (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Phala via OpenRouter

qwen/qwen3.8-27b
Images
?
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Reka (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Tenstorrent (fp4) via OpenRouter

qwen/qwen3.8-27b
Images
?
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “{"error":{"message":"No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Input Video Support removed modal, tenstorrent/fp4, cerebras/fp16; Filter by Fallback removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, dekallm, wafer/fp8, deepinfra/bf16, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, novita, alib”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Venice (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
10 “At most 10 image(s) may be provided in one request.”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
2,499
Frames/min
6.3 ⁎
Video input
Yes
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31

Wafer (fp8) via OpenRouter

qwen/qwen3.8-27b
Images
170 “No endpoints found for qwen/qwen3.8-27b. Every candidate endpoint was removed during routing: Filter by Context Length removed darkbloom/fp4, chutes/fp8, near-ai/fp8, ionstream/fp8, reka/fp8, modal, dekallm, wafer/fp8, deepinfra/bf16, tenstorrent/fp4, mancer/fp8, modelrun/fp4, akashml/fp8, parasail/fp8, coreweave/fp8, cloudflare, venice/fp8, cerebras/fp16; Filter by Fallback removed novita, alibab”
768×432 frames
—
Tokens / frame
—
Inline body
—
Images by URL
—
Video file
—
Video tok/min
No “video and audio input is not supported for this model”
Frames/min
—
Video input
No
Tool messages
—
Extra fields
All accepted

Measured 2026-10-31