Z.ai GLM 5.2
Z.ai (Zhipu AI)docs.mistral.ai/models/zai-glm-5-2
A third-party open source text model from Z.ai with a 1M-token context window.
Updated 38 min ago · first seen 11 Sept 2026
model_01M2943ZSHC4RGJCVFH2K0A6B2
- Parameters
- 753.3B
- T2 · 41 min ago
- Context
- 1M tokens
- T1 · 55 min ago
- Released
- 16 Jun 2026
- T2 · 43 min ago
Specification
- Version
- 5.2
Source:Mistral AI docsT1observed 56 min agohigh
- Release date
- 16 Jun 2026
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Parameters
- 753.3B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Context window
- 1M tokens
Source:Mistral AI docsT1observed 55 min agohigh
- Max output
- 182.5K tokens
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Hugging Face repo
- zai-org/GLM-5.2
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Official page
Source:Mistral AI docsT1observed 56 min agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Downloads
- 933,052
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 38 min agomedium
- Likes
- 5,078
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 38 min agomedium
- Last modified
- 2026-09-01T11:36:01+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Openrouter id
- z-ai/glm-5.2
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
22
Source tiers
T1T26 / 16
Freshest observation
38 min ago
Conflicts
1 flagged
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
Mistral AI docs · T1
Structured output
Yes
Mistral AI docs · T1
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1M tokens
Source:Mistral AI docsT1observed 55 min agohigh
- Max output
- 182.5K tokens
Source:OpenRouter public model & pricing listingT2observed 43 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Z.ai APIz-ai/glm-5.2 | $0.60 | $2 | $0.15 | — | 202.8K | 43 min ago | openrouter.aiT2 |
| Z.ai APIz-ai/glm-5.2:batch | $0.70 | $2.2 | $0.07 | — | 1.05M | 43 min ago | openrouter.aiT2 |
| Mistral AI La Plateforme | $1.4 | $4.4 | — | — | — | 55 min ago | docs.mistral.aiT1 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 2
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Mistral AI La Plateforme
- Z.ai API
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 433.7 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 433.7 GB | No |
| AMD Instinct MI300X | 4bit | 192 GB | 433.7 GB | No |
| Apple M2 Ultra | 4bit | — | 433.7 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 433.7 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 433.7 GB | No |
| Apple M1 Ultra | 4bit | — | 433.7 GB | No |
| Apple M3 Max | 4bit | — | 433.7 GB | No |
| Apple M4 Max | 4bit | — | 433.7 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 433.7 GB | No |
| Apple M2 Max | 4bit | — | 433.7 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 433.7 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 433.7 GB | No |
| Apple M1 Max | 4bit | — | 433.7 GB | No |
| Apple M4 Pro | 4bit | — | 433.7 GB | No |
| Apple M3 Pro | 4bit | — | 433.7 GB | No |
| Apple M1 Pro | 4bit | — | 433.7 GB | No |
| Apple M2 Pro | 4bit | — | 433.7 GB | No |
| Apple M4 | 4bit | — | 433.7 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 433.7 GB | No |
| Apple M2 | 4bit | — | 433.7 GB | No |
| Apple M3 | 4bit | — | 433.7 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 433.7 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 433.7 GB | No |
| Apple M1 | 4bit | — | 433.7 GB | No |
Ancestors 0
None recorded.
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Last modified
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2026-09-01T11:36:01+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Z.ai API lists Z.ai GLM 5.2 at $0.7 in / $2.2 out per 1M tokens
openrouterZ.ai API lists Z.ai GLM 5.2 at $0.6 in / $2 out per 1M tokens
openrouterMistral AI La Plateforme lists Z.ai GLM 5.2 at $1.4 in / $4.4 out per 1M tokens
mistral
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Mistral AI docs | docs.mistral.ai/models | model_docs | T1· Official | 50 min ago | 1 |
| Mistral AI docs | docs.mistral.ai/models/zai-glm-5-2 | model_page | T1· Official | 55 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/amd/GLM-5.2-MXFP4 | model_page | T2· Quality secondary | 33 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=zai-org&p=0&sort=downloads | listing | T2· Quality secondary | 38 min ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 43 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.