Z.ai models

Access 30 Z.ai models through the Oxyy unified API including GLM-5.2, GLM-5.3, GLM-5.3-Flash. Compare pricing, context windows and capabilities between Z.ai models.

Z.ai tokens processed on Oxyy· daily, UTC

Models 30

Z.ai: GLM-5.2TextText-60%1.8B tokens

reasoningcodingagenticlong-contextopen-weights

Long-context reasoning and coding model. The GLM release that expanded the context window from 200K to 1M tokens.

by Z.aiJun 16, 20261.05M context$1.40/M input$4.40/M output19.3s latency70 t/s

Z.ai: GLM-5.3TextText-60%1.1M tokens

reasoningcodingagenticlong-contextopen-weights

Z.ai's flagship model for complex software engineering and long-horizon agent tasks. Uses the same base model as GLM-5.2, with all gains driven by post-training.

by Z.aiAug 14, 20261.05M context$1.40/M input$4.40/M output11.9s latency63 t/s

Z.ai: GLM-5.3-FlashTextImageText-60%281.7K tokens

codingmultimodallow-costopen-weightsvisual-coding

The first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at very low cost.

by Z.ai— context$0.150/M input$0.500/M output14.8s latency63 t/s

Z.ai: GLM-4.7-FlashTextTextFree83.4K tokens

freeopen-weights

Free tier text model from the GLM-4.7 generation.

by Z.ai— context$0/M input$0/M output6507ms latency65 t/s

Z.ai: GLM-5TextText-60%51.3K tokens

reasoningcodingagenticopen-weights

Z.ai's new-generation flagship foundation model for agentic engineering, targeting complex system engineering and long-range agent tasks.

by Z.aiFeb 11, 2026200K context$1.00/M input$3.20/M output2558ms latency443 t/s

Z.ai: GLM-5.1TextText-60%51.2K tokens

reasoningcodingagenticopen-weights

Leading open-source coding model with significant gains on long-horizon tasks. Predecessor to GLM-5.2.

by Z.ai200K context$1.40/M input$4.40/M output4566ms latency53 t/s

Z.ai: CogVideoX-3TextImageVideo-60%—

video-generationopen-weights

Z.ai's video generation model.

by Z.ai— context—/M input—/M output

Z.ai: CogView-4TextImage-60%—

image-generationtext-to-imageopen-weightslow-cost

Z.ai's CogView image generation model.

by Z.ai— context—/M input—/M output

Z.ai: GLM-4-32B-0414-128KTextText-60%—

low-costopen-weightslong-context

32-billion-parameter GLM-4 model with a 128K context window, flat-priced on input and output.

by Z.ai128K context$0.100/M input$0.100/M output

Z.ai: GLM-4.5TextText-60%—

codingagenticopen-weights

GLM-4.5 base text model. The release that introduced interleaved reasoning to the GLM line.

by Z.ai— context$0.600/M input$2.20/M output

Z.ai: GLM-4.5-AirTextText-60%—

low-costopen-weights

Lightweight, low-cost variant of GLM-4.5.

by Z.ai— context$0.200/M input$1.10/M output

Z.ai: GLM-4.5-AirXTextText-60%—

high-throughput

High-throughput variant of GLM-4.5-Air.

by Z.ai— context$1.10/M input$4.50/M output

Z.ai: GLM-4.5-FlashTextTextFree—

freeopen-weights

Free tier text model from the GLM-4.5 generation.

by Z.ai— context$0/M input$0/M output

Z.ai: GLM-4.5VTextImageText-60%—

visionmultimodalopen-weights

Previous-generation GLM vision-language model.

by Z.ai— context$0.600/M input$1.80/M output

Z.ai: GLM-4.5-XTextText-60%—

reasoninghigh-performance

Highest-performance variant of GLM-4.5, and the most expensive model in Z.ai's published catalog.

by Z.ai— context$2.20/M input$8.90/M output

Z.ai: GLM-4.6TextText-60%—

codingagenticopen-weights

Prior-generation GLM-4 text model.

by Z.ai— context$0.600/M input$2.20/M output

Z.ai: GLM-4.6VTextImageText-60%—

visionmultimodaldocument-understandingui-reconstruction

Multimodal model for high-fidelity visual understanding and long-context reasoning across images, documents and mixed media. Handles complex page layouts and charts as visual input.

by Z.ai128K context$0.300/M input$0.900/M output

Z.ai: GLM-4.6V-FlashTextImageTextFree—

visionfree

Free tier vision-language model.

by Z.ai— context$0/M input$0/M output

Z.ai: GLM-4.6V-FlashXTextImageText-60%—

visionlow-costhigh-throughput

High-throughput, low-cost vision variant of GLM-4.6V.

by Z.ai— context$0.040/M input$0.400/M output

Z.ai: GLM-4.7TextText-60%—

reasoningcodingagenticopen-weights

Previous flagship focused on task completion rather than single-point code generation, with interleaved, retained and round-level reasoning.

by Z.ai200K context$0.600/M input$2.20/M output

Z.ai: GLM-4.7-FlashXTextText-60%—

low-costhigh-throughput

High-throughput, very low cost variant of GLM-4.7.

by Z.ai— context$0.070/M input$0.400/M output

Z.ai: GLM-5.3-FlashXTextText-60%—

codinglow-costhigh-throughput

Higher-throughput FlashX variant of the GLM-5.3 generation.

by Z.ai— context$0.370/M input$1.25/M output

Z.ai: GLM-5-CodeTextText-60%—

codingagentic

Coding-specialized variant of GLM-5.

by Z.ai— context$1.20/M input$5.00/M output

Z.ai: GLM-5-TurboTextText-60%—

reasoningcodingfast

Speed-optimized variant of GLM-5.

by Z.ai— context$1.20/M input$4.00/M output

Z.ai: GLM-ASR-2512AudioText-60%—

speech-to-texttranscriptionlow-cost

Z.ai's automatic speech recognition model.

by Z.ai— context$0.030/M input—/M output

Z.ai: GLM-ImageTextImage-60%—

image-generationtext-to-imageopen-weights

Text-to-image generation model, described by Z.ai as achieving open-source state of the art in complex scenarios.

by Z.ai— context—/M input—/M output

Z.ai: GLM-OCRImageFileText-60%—

ocrdocument-understandinglow-cost

Z.ai's OCR model for extracting text from images and documents.

by Z.ai— context$0.030/M input$0.030/M output

Z.ai: GLM Slide/Poster Agent (beta)TextTextImage-60%—

agentslidesposterbeta

Z.ai agent that generates slides and posters.

by Z.ai— context$0.700/M input—/M output

Z.ai: General-Purpose TranslationTextText-60%—

agenttranslation

Z.ai's translation agent.

by Z.ai— context$3.00/M input—/M output

Z.ai: Popular Special Effects Video TemplatesTextImageVideoVideo-60%—

agentvideoeffects

Z.ai agent that applies popular special-effects templates to video.

by Z.ai— context—/M input—/M output

Models 30

Z.ai: GLM-5.2TextText-60%1.8B tokens

reasoningcodingagenticlong-contextopen-weights

Long-context reasoning and coding model. The GLM release that expanded the context window from 200K to 1M tokens.

by Z.aiJun 16, 20261.05M context$1.40/M input$4.40/M output19.3s latency70 t/s

Z.ai: GLM-5.3TextText-60%1.1M tokens

reasoningcodingagenticlong-contextopen-weights

Z.ai's flagship model for complex software engineering and long-horizon agent tasks. Uses the same base model as GLM-5.2, with all gains driven by post-training.

by Z.aiAug 14, 20261.05M context$1.40/M input$4.40/M output11.9s latency63 t/s

Z.ai: GLM-5.3-FlashTextImageText-60%281.7K tokens

codingmultimodallow-costopen-weightsvisual-coding

The first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at very low cost.

by Z.ai— context$0.150/M input$0.500/M output14.8s latency63 t/s

Z.ai: GLM-4.7-FlashTextTextFree83.4K tokens

freeopen-weights

Free tier text model from the GLM-4.7 generation.

by Z.ai— context$0/M input$0/M output6507ms latency65 t/s

Z.ai: GLM-5TextText-60%51.3K tokens

reasoningcodingagenticopen-weights

Z.ai's new-generation flagship foundation model for agentic engineering, targeting complex system engineering and long-range agent tasks.

by Z.aiFeb 11, 2026200K context$1.00/M input$3.20/M output2558ms latency443 t/s

Z.ai: GLM-5.1TextText-60%51.2K tokens

reasoningcodingagenticopen-weights

Leading open-source coding model with significant gains on long-horizon tasks. Predecessor to GLM-5.2.

by Z.ai200K context$1.40/M input$4.40/M output4566ms latency53 t/s

Z.ai: CogVideoX-3TextImageVideo-60%—

video-generationopen-weights

Z.ai's video generation model.

by Z.ai— context—/M input—/M output

Z.ai: CogView-4TextImage-60%—

image-generationtext-to-imageopen-weightslow-cost

Z.ai's CogView image generation model.

by Z.ai— context—/M input—/M output

Z.ai: GLM-4-32B-0414-128KTextText-60%—

low-costopen-weightslong-context

32-billion-parameter GLM-4 model with a 128K context window, flat-priced on input and output.

by Z.ai128K context$0.100/M input$0.100/M output

Z.ai: GLM-4.5TextText-60%—

codingagenticopen-weights

GLM-4.5 base text model. The release that introduced interleaved reasoning to the GLM line.

by Z.ai— context$0.600/M input$2.20/M output

Z.ai: GLM-4.5-AirTextText-60%—

low-costopen-weights

Lightweight, low-cost variant of GLM-4.5.

by Z.ai— context$0.200/M input$1.10/M output

Z.ai: GLM-4.5-AirXTextText-60%—

high-throughput

High-throughput variant of GLM-4.5-Air.

by Z.ai— context$1.10/M input$4.50/M output

Z.ai: GLM-4.5-FlashTextTextFree—

freeopen-weights

Free tier text model from the GLM-4.5 generation.

by Z.ai— context$0/M input$0/M output

Z.ai: GLM-4.5VTextImageText-60%—

visionmultimodalopen-weights

Previous-generation GLM vision-language model.

by Z.ai— context$0.600/M input$1.80/M output

Z.ai: GLM-4.5-XTextText-60%—

reasoninghigh-performance

Highest-performance variant of GLM-4.5, and the most expensive model in Z.ai's published catalog.

by Z.ai— context$2.20/M input$8.90/M output

Z.ai: GLM-4.6TextText-60%—

codingagenticopen-weights

Prior-generation GLM-4 text model.

by Z.ai— context$0.600/M input$2.20/M output

Z.ai: GLM-4.6VTextImageText-60%—

visionmultimodaldocument-understandingui-reconstruction

Multimodal model for high-fidelity visual understanding and long-context reasoning across images, documents and mixed media. Handles complex page layouts and charts as visual input.

by Z.ai128K context$0.300/M input$0.900/M output