GLM models

Messages and Responses APIs add GLM-5.3 and DeepSeek-V4.1-Flash models

Together AI · GLM-5.3 Flash · GLM 5.3

GLM-5.3-Flash available for LoRA post-training on B200-SXM

Together AI · GLM-5.3 Flash

Kimi K3, GLM 5.3 Flash and three more models added to Dedicated catalog

Cerebras · GLM-5.3 Flash

Z.ai GLM 5.3 Flash available, with a 1M-token context windowGA

Mistral · GLM-5.3 Flash

GLM 5.3 by Z.ai is now generally available on Amazon BedrockGA

AWS · GLM 5.3

GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash on provisioned throughput

Together AI · GLM 5.3 · GLM-5.3 Flash

OCR 4.0 and Leanstral 1.5 retire September 30, 2026; GLM 5.2 deprecatedDeprecation

Mistral · GLM-5.2 · Was due Sep 30, 2026

Z.ai GLM 5.3 is generally availableGA

Mistral · GLM 5.3

Serverless deprecation takes effect for DeepSeek V4, Kimi K2 and GLM 5.2 models

Fireworks AI · GLM-5.2

GLM 5.3 Flash available for LoRA on Serverless Training, with 200K context

Fireworks AI · GLM-5.3 Flash

GLM 5.3 available for LoRA on Serverless Training, with up to 262K context

Fireworks AI · GLM 5.3

GLM 5.3 Flash available for LoRA on Dedicated Training API, with vision

Fireworks AI · GLM-5.3 Flash

Fireworks serverless decommissions DeepSeek V4, GLM 5.2 and Kimi K2 models on Sept 25

Fireworks AI · GLM-5.2

Fine-tuning now supports zai-org/GLM-5.3

Together AI · GLM 5.3

GLM 5.3 available for LoRA training on Dedicated Training API, up to 204K context

Fireworks AI · GLM 5.3

AI Search now supports GLM-5.3 Flash

Cloudflare · GLM-5.3 Flash

GLM-5.3 on serverless with 1M context, at $1.40 input / $4.40 output per 1M tokens

Together AI · GLM 5.3

Workers AI - Z.ai GLM-5.3 now available on Workers AIGA

Cloudflare · GLM 5.3

GLM-5.3-Flash on serverless, with 1M context and function calling

Together AI · GLM-5.3 Flash

Workers AI - Z.ai GLM-5.3 Flash now available on Workers AI

Cloudflare · GLM-5.3 Flash

GLM-5.2 on serverless raises context length to 1,000,000 tokens

Together AI · GLM-5.2

GLM-5.3 released, with 50% coding gain over GLM-5.2 on Z.ai Code Bench

Z.ai · GLM 5.3

GLM-5.2 now available for fine-tuning

Together AI · GLM-5.2

GLM-5.2 FP8, NVIDIA-Nemotron-Nano-12B-v2 and GLM-OCR models now available on Amazon SageMaker JumpStart

AWS · GLM-5.2 FP8 · GLM-OCR

GLM-5.2 on serverless context length raised to 512,000 tokens, price unchanged

Together AI · GLM-5.2

Many Qwen, Kimi, GLM, DeepSeek and Llama models deprecated for fine-tuning

Together AI · GLM 5

Workers AI - Select models now require the Workers Paid planPrice

Cloudflare · GLM-5.2

zai-glm-4.7 deprecated August 17, 2026, keeps default logprobs shape until then

Cerebras · GLM zai-glm-4.7

API version 2 is now the default, with stricter validation and reasoning_logprobs

Cerebras · GLM 4.7

Fine-tuning now supports GLM-5.1 and GLM-5

Together AI · GLM-5.1 · GLM 5

Qwen3-235B-A22B-Instruct-2507-tput, Llama-3-8B-Instruct-Lite and GLM-5.1 deprecated on serverless

Together AI · GLM-5.1

Provisioned throughput available for MiniMax-M3 and GLM-5.2, one-month minimum term

Together AI · GLM-5.2

GLM-5.1 and four other models deprecated on serverless

Together AI · GLM-5.1

GLM-5 deprecated on serverless, replaced by GLM-5.2

Together AI · GLM 5

GLM-5.2 available on serverless with 262K context at $1.40 input per 1M tokens

Together AI · GLM-5.2

Workers, Agents, Workers AI - Introducing GLM-5.2 on Workers AIGA

Cloudflare · GLM-5.2

GLM 5.2 available in the Model Library

Fireworks AI · GLM-5.2

Cached input pricing for GLM-5.1 and Qwen3.5-397B-A17B, DeepSeek-V4-Pro price cut

Together AI · GLM-5.1

Two new models for agentic coding and efficient AI are now available in Amazon SageMaker JumpStart

AWS · GLM-5.1-FP8

Eight legacy serverless models deprecated, decommissioned May 14, 2026

Fireworks AI · GLM 4.7 · GLM 5

GLM 5, GLM 5.1 and Kimi K2.6 supported on Cerebras Dedicated Endpoints

Cerebras · GLM 5 · GLM-5.1

Gemma 4 31B-it and GLM-5.1 available on serverless

Together AI · GLM-5.1

AI Search - New Workers AI models for text generation and embedding in AI Search

Cloudflare · GLM 4.7 Flash

GLM-5.1 released, working independently for up to 8 hours in a single run

Z.ai · GLM-5.1

GLM-4.5-Air-FP8 and GLM-4.7 deprecated, along with Qwen3-Next-80B-A3B-Instruct

Together AI · GLM-4.5-Air-FP8 · GLM 4.7

Minimax M2.5 and GLM 5 models now available on Amazon BedrockGA

AWS · GLM 5

zai-glm-4.7 accepts reasoning_effort; set to none to disable reasoning

Cerebras · GLM 4.7

GLM-5 now available on serverless

Together AI · GLM 5

Workers, Agents, Workers AI - Introducing GLM-4.7-Flash on Workers AI, @cloudflare/tanstack-ai, and workers-ai-provider v3.1.1

Cloudflare · GLM 4.7 Flash

GLM-5 released for complex system engineering and long-range Agent tasks

Z.ai · GLM 5

Amazon Bedrock adds support for six fully-managed open weights models

AWS · GLM 4.7 · GLM 4.7 Flash

Mistral-7B-Instruct-v0.3 and GLM-4.6 now redirect to Ministral-3-14B and GLM-4.7

Together AI · GLM-4.6 · GLM 4.7

GLM-Image image generation model released, with improved text rendering

Z.ai · GLM-Image

GLM-4.7 now available on serverless

Together AI · GLM 4.7

Z.ai GLM 4.7 (zai-glm-4.7) available in preview

Cerebras · GLM 4.7

GLM-4.7 released, with improved coding, reasoning and agentic capabilities

Z.ai · GLM 4.7

GLM-4.6 and Kimi-K2-Thinking now available on serverless

Together AI · GLM-4.6

Z.ai GLM 4.6 (zai-glm-4.6) available in preview on Cerebras Inference

Cerebras · GLM Z.ai GLM 4.6

GLM-4.6 released, with context window expanded to 200K

Z.ai · GLM-4.6