glm-4.6v-flashx
Common Name: GLM-4.6V FlashX
ChatGLM
Released on Oct 8, 2025 12:00 AMKnowledge Cutoff Apr 1, 2025 12:00 AMSupportedTool InvocationSupportedReasoningLightweight, high-speed variant of GLM-4.6V with multimodal tool calling and long-context visual reasoning.
Specifications
Context
128K
Maximum Output
32K
Inputtext, image, video, pdf
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Pricing
< 32K
Input¥0.165/MTokens
Output¥1.65/MTokens
Cached Input¥0.033/MTokens
32K-128K
Input¥0.33/MTokens
Output¥3.30/MTokens
Cached Input¥0.033/MTokens
Performance Metrics (24h)
Similar Models
¥0.22/¥0.22/M
ctx131Kmax—avail—tps—
InOut
Zhipu AI's 0.9B document OCR model (94.62 on OmniDocBench V1.5). Converts images and PDFs to Markdown while preserving table, formula, and layout structure. Served through the layout parsing endpoint, not chat completions; a single call accepts one image (≤10MB) or PDF (≤50MB, ≤100 pages).
¥2.20/¥6.60/M
ctx64Kmax16Kavail—tps—
InOutCap
Zhipu AI's multimodal model with vision capabilities. Processes text, images, video, and files for analysis tasks.
¥4.40/¥13.20/M
ctx128Kmax—avail—tps—
InOutCap
Zhipu AI's GLM-4.5 AirX variant optimized for high-speed inference.
¥0.88/¥2.20/M
ctx131Kmax98Kavail—tps—
InOutCap
Zhipu AI's lightweight GLM-4.5 variant for cost-effective tasks.