// Zhipu (Z.ai)
GLM-5.3
A Zhipu (Z.ai) model. 18 prices across 17 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- ¥8 / ¥28
- Lowest (Novita)
- $0.63 / $1.98
- Context
- 1M
- AA index
- 44.8
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Zhipu (Z.ai) |
|---|---|
| Context window | 1M (1,000,000 tokens) |
| Max output | 944K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · glm-5.3 (custom) · Hugging Face |
| Parameters | 753B (from weight files) |
| Released | Aug 18, 2026 |
| Model IDs | glm-5.3 · z-ai/glm-5.3 · glm-5.3@bailian · zai-org/GLM-5.3 |
02Prices on 17 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Official Vendor’s China site, billed in CNY | Official 10-10 | ¥8 | ¥28 | ¥2 | 1.94 | 1M | Batch −50%Batch -50% |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.63 | $1.98 | $0.117 | 0.968 | 1.05M | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.5); not checked against Novita's own page |
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.563 | $2.5 | $0.125 | 1.05 | 1.05M | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0.375); not checked against DeepInfra's own page |
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.7 | $2.2 | $0.13 | 1.07 | 1.05M | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.3); not checked against GMICloud's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.7 | $2.2 | $0.13 | 1.07 | 1.05M | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.2); not checked against SiliconFlow's own page |
| Alibaba Cloud · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.19 | $3.74 | $0.238 | 1.83 | 1M | Alibaba price as listed on OpenRouter (pass-through; quantization=unknown); Alibaba Cloud; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| Friendli · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.26 | $3.96 | $0.234 | 1.94 | 1.05M | Friendli price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0.1); not checked against Friendli's own page |
| 阿里云百炼 Inference platform (own price page) | Platform 10-10 | ¥8 | ¥28 | — | 1.94 | — | Third-party model hosted on 阿里云百炼 (Beijing) |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥8 | ¥28 | ¥2 | 1.94 | — | SiliconFlow (硅基流动) own pricing page |
| Mistral Inference platform (own price page) | Platform 10-10 | $1.4 | $4.4 | $0.14 | 2.15 | — | Batch −50%Batch -50% (pricing FAQ); Third-party model on La Plateforme |
| Together Inference platform (own price page) | Platform 10-10 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Together AI own pricing page |
| Fireworks Inference platform (own price page) | Platform 10-10 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Batch −50%Fireworks AI own pricing page; batch -50% |
| BaseTen · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.14 | 2.15 | 1.05M | BaseTen price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against BaseTen's own page |
| Crusoe · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Crusoe price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Crusoe's own page |
| Parasail · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page |
| AtlasCloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against AtlasCloud's own page |
| Cloudflare · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Cloudflare price as listed on OpenRouter (pass-through; quantization=unknown); Cloudflare; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| Z.ai (via OpenRouter) · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Z.AI price as listed on OpenRouter (pass-through; quantization=fp8); Z.ai (maker); promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Vendor’s China site, billed in CNY
Official - Via OpenRouter / provider listed there
Novita · DeepInfra · GMICloud · SiliconFlow · Alibaba Cloud · Friendli · BaseTen · Crusoe · Parasail · AtlasCloud · Cloudflare · Z.ai (via OpenRouter) - Inference platform (own price page)
阿里云百炼 · SiliconFlow · Mistral · Together · Fireworks - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
GLM-5.3→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexGLM-5.3 (Max)
- 44.8
- Output speed (median)
- 74 tok/s
- Time to first tokenGLM-5.3 (Low): 3.18s
- 2.84s
- AA index per $ (blended)
- 23.08
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| GPQA Diamond | 90.9% | independent | 2026-08-24 |
| AIME (OTIS Mock AIME 2024–2025) | 91.1% | independent | 2026-08-24 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-21 · Novita · cache read0.13 → 0.117 USD (-10%)
- 2026-10-21 · Novita · output2.2 → 1.98 USD (-10%)
- 2026-10-21 · Novita · input0.7 → 0.63 USD (-10%)
- 2026-10-20 · Crusoe · cache read0.13 → 0.26 USD (+100%)
- 2026-10-20 · GMICloud · cache read0.182 → 0.13 USD (-28.6%)
- 2026-10-20 · GMICloud · output3.08 → 2.2 USD (-28.6%)
- 2026-10-20 · GMICloud · input0.98 → 0.7 USD (-28.6%)
- 2026-10-16 · Crusoe · cache read0.26 → 0.13 USD (-50%)
- 2026-10-14 · Z.ai (via OpenRouter) · new listing
- 2026-10-14 · Cloudflare · new listing
- 2026-10-14 · Alibaba Cloud · new listing
- 2026-10-14 · SiliconFlow · cache read0.208 → 0.13 USD (-37.5%)
- 2026-10-14 · SiliconFlow · output3.52 → 2.2 USD (-37.5%)
- 2026-10-14 · SiliconFlow · input1.12 → 0.7 USD (-37.5%)
06More from Zhipu (Z.ai)
FAQ
How much does the GLM-5.3 API cost?
On the official pricing page: ¥8 / ¥28 per 1M input / output tokens, cached input ¥2 (checked 2026-10-10). The lowest price we found is $0.63 / $1.98 on Novita.
What is the context window of GLM-5.3?
1M tokens of context, up to 944K output tokens. Platforms may cap it lower – see the table.
Is GLM-5.3 open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-5.3). Licence: glm-5.3 (custom).