Z.ai
GLM 5.3
Released 2026-08-18
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
You send / 1M
$0.070
tokens in
It replies / 1M
$1.40
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0008
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 |
|---|---|---|---|---|
| Wafer · fp4 | $0.070 | $1.40 | 100% | Read |
| Wafer · fp4 | $0.179 | $1.40 | 100% | Read |
| Novita · fp8 | $0.630 | $1.98 | 100% | Read |
| Sail Research · fp8 | $0.500 | $2.00 | 100% | Read |
| Sail Research · fp8 | $0.500 | $2.00 | 100% | Read |
| Reka | $0.140 | $2.10 | 100% | Read |
| SiliconFlow · fp8 | $0.700 | $2.20 | 100% | Read |
| Tenstorrent · fp8 | $0.600 | $2.50 | 100% | Read |
| DeepInfra · fp4 | $0.563 | $2.50 | 99% | Read |
| Phala | $0.840 | $2.64 | 100% | Read |
| Decart · fp4 | $0.840 | $2.69 | 100% | Read |
| DigitalOcean | $0.910 | $2.86 | 100% | Read |
| DekaLLM | $0.250 | $2.95 | 100% | Read |
| Fireworks | $0.980 | $3.08 | 100% | Read |
| PrimeIntellect | $0.980 | $3.08 | 100% | n/a |
| Inceptron · fp4 | $1.20 | $3.50 | 100% | Read |
| InferenceNet · fp4 | $0.080 | $3.60 | 100% | Read |
| InferenceNet · fp4 | $0.080 | $3.60 | 100% | Read |
| CoreWeave · fp8 | $1.20 | $4.00 | 99% | Read |
| Relace | $0.070 | $4.38 | 100% | Read |
| Mistral · nvfp4 | $1.40 | $4.40 | 100% | Read |
| BaseTen · fp4 | $1.40 | $4.40 | 100% | Read |
| Nebius · fp4 | $1.40 | $4.40 | 100% | Read |
| Crusoe · fp4 | $1.40 | $4.40 | 100% | Read |
| Venice | $1.40 | $4.40 | 100% | Read |
| Makora · fp4 | $0.140 | $4.40 | 99% | n/a |
| Together | $1.40 | $4.40 | 100% | Read |
| Parasail · fp8 | $1.40 | $4.40 | 100% | Read |
| Modal | $1.40 | $4.40 | 100% | Read |
| AkashML · fp8 | $0.190 | $4.40 | 100% | Read |
| BaseTen · fp4 | $1.40 | $4.40 | 100% | Read |
| Fireworks | $1.40 | $4.40 | 100% | Read |
| Cloudflare | $1.40 | $4.40 | 100% | Read |
| Z.AI · fp8 | $1.40 | $4.40 | 100% | Read |
| Mistral · nvfp4 | $1.54 | $4.84 | 100% | Read |
| Amazon Bedrock | $1.68 | $5.28 | 93% | Read |
| Morph · fp8 | $1.05 | $5.88 | 100% | Read |
| ModelRun · fp4 | $2.10 | $6.60 | 92% | Read |
| Fireworks | $2.10 | $6.60 | 98% | Read |
| BaseTen · fp8 | $2.10 | $6.60 | 98% | Read |
| BaseTen · fp8 | $2.10 | $6.60 | 99% | 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 $0.069 per 1M (prompt caching)
- Intelligence score: 44.8 / 100 (Artificial Analysis)
Similar models
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