Z.ai models in Big-AGI

GLM for code and agents at Z.ai's own rates - on a curated catalog that survives Z.ai's broken listing and hides models Z.ai advertises but doesn't serve.

GLM-5.3 FlashX (1M)GLM-5.3 Flash (1M)GLM-5.2 (1M)GLM-4.7 Flash (Free)GLM-5.3 (1M)

Z.ai setup guide Z.ai models

All supported Z.ai models

ModelContextInputOutputReleased

GLM-5.3 FlashX (1M)NEWFast GLM-5.3 Flash variant served at ~200 tokens/s. Image inputs, thinking always on with low/high/max effort. 1M context, 128K output.1M$0.37$1.25Sep 2026 GLM-5.3 Flash (1M)Multimodal Flash on a new 320B MoE base (18B activated, hybrid sparse+linear attention). Image inputs, thinking always on with low/high/max effort. 1M context,…1M$0.15$0.50Aug 2026 GLM-5.3 (1M)Z.ai 1M-context flagship, post-trained on the GLM-5.2 base for coding, cybersecurity and agentic work. Thinking always on, with low/high/max effort. 1M context…1M$1.40$4.40Aug 2026 GLM-5.2 (1M)Z.ai 1M-context flagship (744B MoE, 40B activated). Agentic coding with reasoning_effort control (high/max). 1M context, 128K output.1M$1.40$4.40Jun 2026 GLM-5.1Z.ai flagship (744B MoE, 40B activated). Post-training upgrade over GLM-5 with stronger coding and long-horizon task autonomy. 200K context, thinking mode.205K$1.40$4.40Apr 2026 GLM-5V TurboFirst multimodal GLM-5 model. Vision-based coding agent with image/video/file inputs. 200K context, 128K output, thinking mode.205K$1.20$4.00Apr 2026 GLM-5 TurboSpeed-optimized GLM-5 variant for agent workflows. Enhanced tool invocation and long-chain execution. 200K context, thinking mode.205K$1.20$4.00Mar 2026 GLM-5Z.ai flagship foundation model (744B MoE, 40B activated). Designed for Agentic Engineering with SOTA coding and agent capabilities. 200K context, thinking mode.205K$1.00$3.20Feb 2026 GLM-OCR (Vision, OCR)Specialized OCR model for text extraction from images and documents.131K$0.03$0.03Feb 2026 GLM-4.7 Flash (Free)Free GLM-4.7 variant. Same model as FlashX but with limited concurrency (1 concurrent request) and lower priority.205KFreeFreeJan 2026 GLM-4.7 FlashXFast GLM-4.7 variant with priority routing and higher concurrency. Same model as Flash, better infrastructure.205K$0.07$0.40Jan 2026 GLM-4.7Latest-gen GLM model with 200K context. Thinking mode activated by default.205K$0.60$2.20Dec 2025 AutoGLM PhoneMobile phone automation agent. Understands phone screens via multimodal perception and executes automated operations.131KFreeFreeDec 2025 GLM-4.6 VVision-enabled GLM-4.6 model. Supports image/video/file inputs, 32K output, hybrid thinking.131K$0.30$0.90Dec 2025 GLM-4.6 V Flash (Free)Free vision GLM-4.6. Same model as FlashX but with limited concurrency (1 concurrent request). Image/video/file inputs, 32K output.131KFreeFreeDec 2025 GLM-4.6 V FlashXFast vision GLM-4.6 with priority routing and higher concurrency. Image/video/file inputs, 32K output.131K$0.04$0.40Dec 2025 GLM-4.6GLM-4.6 model with 200K context, 128K output. Hybrid thinking: auto-determines whether to engage deep reasoning.205K$0.60$2.20Sep 2025 GLM-4.5 VVision-enabled GLM-4.5 model. 64K context, 16K output, interleaved thinking.66K$0.60$1.80Aug 2025 GLM-4.5Prior-gen GLM-4.5 model with 128K context, 96K output. Interleaved thinking.131K$0.60$2.20Jul 2025 GLM-4.5 AirLightweight GLM-4.5 variant. Interleaved thinking.131K$0.20$1.10Jul 2025 GLM-4.5 AirXExtended lightweight GLM-4.5 variant. Interleaved thinking.131K$1.10$4.50Jul 2025 GLM-4.5 Flash (Free)Free GLM-4.5 variant with limited concurrency. Prior-gen, superseded by GLM-4.7 Flash.131KFreeFreeJul 2025 GLM-4.5 XExtended GLM-4.5 model. Interleaved thinking.131K$2.20$8.90Jul 2025 GLM-4 32B (0414) 128KGLM-4 32B model with 128K context, 16K output.131K$0.10$0.10Apr 2025

24 models · sorted by release date · prices in USD per 1M tokens · refreshed hourlyCompare every model across vendors ->

Get started in 3 steps

Create an API key at the Z.ai console.

Paste it into Big-AGI's model settings.

Start chatting, or Beam it against other models and fuse the answers.

Running Z.ai in Big-AGI

Add your Z.ai API key and run the GLM models at Z.ai's own API rates. Big-AGI adds no markup and no intermediary: billing runs directly between you and Z.ai, and your keys stay in your browser.

Your key, your billing. Usage is billed by Z.ai to your account. Big-AGI does not meter or charge for model usage.
Strong at code and agents. GLM is tuned for coding and tool use, a capable and cost-effective pick for daily work.
A catalog that doesn't break. Z.ai's own model-list endpoint is unreliable, so Big-AGI runs from a hand-curated list of GLM models and layers a live check on top just to catch brand-new releases. A broken listing never takes the catalog down, and a model Z.ai advertises but doesn't actually serve gets hidden so you never pick something that would just fail.

Why run GLM here?

Z.ai's own chat product is a reasonable way to try GLM, but it only ever shows you GLM's take on a prompt. Beam sends the same prompt to GLM and to GPT, Claude, or Gemini at once, so a code review or a debugging session gets more than one model's opinion before you act on it. You also get parameters a consumer chat interface does not surface (temperature, system prompt, per-turn model swaps), and a key that stays in your browser instead of sitting on Z.ai's servers.

Your keys and your data

Turn on Direct Connection and the browser calls Z.ai directly, bypassing the Big-AGI server, whenever your key is client-side and Z.ai allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector opens on any message to show the exact request sent to Z.ai, the token counts, and a cost estimate for that call.

GLM in Beam

Run GLM in parallel with Claude, GPT, and Gemini on the same prompt, then reach for Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the single best one. Parallel runs use more tokens than a single chat.

Bring your Z.ai key. Keep control.

Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how Z.ai is called.

Launch Big-AGI

<- All Models

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq