Models / Z.ai

GLM 5.3 Flash

Measured on 4 providers. The model card lists text, image, video input; what each provider accepts is below.

accounts/fireworks/models/glm-5p3-flash

Images: 120 “Invalid image or video input”
768×432 frames: 112 “Invalid image or video input”
Tokens / frame: 450
Inline body: ≥ 32 MB
Images by URL: 80 MB “Invalid image or video input”
Video file: No video “Cannot process videos: libGL.so.1: cannot open shared object file: No such file or directory”
Video tok/min: 46,994
Frames/min: —
Video input: Yes
Tool messages: Lenient
Extra fields: All accepted

Fireworks counts every image in the messages array ("per conversation"), not per message.

Measured 2026-10-31

glm-5.3-flash

Images: ≥ 1,024
768×432 frames: 128 “Model request failed.”
Tokens / frame: 450
Inline body: 12 MB “Request body exceeds the byte limit.”
Images by URL: ≥ 128 MB
Video file: 64 MB “The model rejected the request parameters.”
Video tok/min: ? “{"type":"<url>","title":"Error 502: Bad gateway","status":502,"detail":"The origin web server returned an invalid or incomplete response to Cloudflare. This typically indicates the origin is overloaded or misconfigured.","instance":"a533cd239918f13a","error_code":502,"error_name":"origin_bad_gate”
Frames/min: —
Video input: Yes
Tool messages: Lenient
Extra fields: All accepted

Measured 2026-10-31

zai-org/GLM-5.3-Flash

Images: 1,004 “Failed to start generation: At most 999 image(s) may be provided in one prompt. (parameter=image)”
768×432 frames: ≥ 384
Tokens / frame: 450
Inline body: ≥ 32 MB
Images by URL: ≥ 128 MB
Video file: 256 MB “Could not load the media in this request — video #1: video too large: 320000000 exceeds limit 268435456.”
Video tok/min: 952
Frames/min: —
Video input: Yes
Tool messages: Strict order
Extra fields: All accepted

Together caps the decoded media in one request at ≈1.43 GB (seen on DeepSeek V4.1 Flash; likely shared).

Measured 2026-10-31

z-ai/glm-5.3-flash

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: 450
Inline body: ≥ 32 MB
Images by URL: ≥ 128 MB
Video file: No video “{"error":{"message":"No endpoints found for z-ai/glm-5.3-flash. Every candidate endpoint was removed during routing: Filter by Regional Surcharge removed fireworks/us; Filter by Input Video Support removed relace/fp4, open-inference/fp4, wafer/us, near-ai/fp8, inference-net/us, inference-net/fp4, pa”
Video tok/min: No “{"error":{"message":"No endpoints found for z-ai/glm-5.3-flash. Every candidate endpoint was removed during routing: Filter by Regional Surcharge removed fireworks/us; Filter by Input Video Support removed relace/fp4, open-inference/fp4, wafer/us, near-ai/fp8, inference-net/us, inference-net/fp4, particle-ai/nvfp4, cohere, nebius/fp4, baseten/fp8/us, crusoe/fp4, baseten/fp8, deepinfra/fp4, z-ai/fp”
Frames/min: —
Video input: No
Tool messages: Lenient
Extra fields: Rejects response_format

This upstream doesn't accept video input for the model; OpenRouter answers a video request with 404 "No allowed providers".

Measured 2026-10-31