Z.ai
GLM 5.2
Released 2026-06-16
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
You send / 1M
$0.034
tokens in
It replies / 1M
$7.00
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0035
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp4 | $0.450 | $1.44 | 100% | Read |
| DeepInfra · fp4 | $0.563 | $1.80 | 100% | Read |
| Novita · fp8 | $0.650 | $2.04 | 100% | Read |
| DigitalOcean | $0.700 | $2.20 | 100% | Read |
| SiliconFlow · fp8 | $0.700 | $2.20 | 100% | Read |
| CoreWeave · fp4 | $0.620 | $2.42 | 100% | Read |
| Inceptron · fp4 | $0.990 | $4.32 | 100% | Read |
| Nebius · fp4 | $1.40 | $4.40 | 88% | Read |
| Mistral · nvfp4 | $1.40 | $4.40 | 99% | Read |
| BaseTen · fp8 | $1.40 | $4.40 | 100% | Read |
| Together | $1.40 | $4.40 | 98% | Read |
| BaseTen · fp8 | $1.40 | $4.40 | 100% | Read |
| Venice · fp8 | $1.40 | $4.40 | 100% | Read |
| Parasail · fp4 | $1.40 | $4.40 | 100% | Read |
| Z.AI · fp8 | $1.40 | $4.40 | 100% | Read |
| Mistral | $1.54 | $4.84 | 100% | Read |
| Morph · fp8 | $1.05 | $5.88 | 100% | Read |
| BaseTen · fp8 | $2.10 | $6.60 | 100% | Read |
| BaseTen · fp8 | $2.10 | $6.60 | 100% | Read |
| Wafer · fp4 | $0.034 | $7.00 | 100% | Read |
| Relace | $0.030 | $7.22 | 100% | Read |
| Decart · fp4 | $1.20 | $8.00 | 100% | Read |
| Wafer · fp4 | $0.190 | $8.00 | 100% | Read |
| Cloudflare | $0.190 | $8.00 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 944K tokens
- Repeated text is billed at $0.033 per 1M (prompt caching)
- Intelligence score: 33.7 / 100 (Artificial Analysis)
Similar models
- DeepSeek Pro Latest~deepseek · $0.254 in / $8.00 out per 1M
- Sonar Deep ResearchPerplexity · $2.00 in / $8.00 out per 1M
- Aion 3.5Aion Labs · $3.00 in / $6.00 out per 1M
- Qwen3.8 2.4T A95BQwen · $2.00 in / $6.00 out per 1M
- Aion-3.0Aion Labs · $3.00 in / $6.00 out per 1M
- GLM 5.3 PrimeZ.ai · $2.80 in / $8.80 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Reasoning AI ModelsTop No-Training Reasoning Tool-Calling AI ModelsTop No-Training Reasoning Long-Context AI Models