// Zhipu (Z.ai)
GLM-5.3-Flash
A Zhipu (Z.ai) model. 14 prices across 13 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- ¥0.8 / ¥2.8
- Lowest (GMICloud)
- $0.075 / $0.25
- Context
- 1M
- AA index
- 41.8
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 · Image · Video |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 321B (from weight files) |
| Released | Aug 26, 2026 |
| Model IDs | glm-5.3-flash · z-ai/glm-5.3-flash · zai-org/GLM-5.3-Flash |
02Prices on 13 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 | ¥0.8 | ¥2.8 | ¥0.23 | 0.194 | 1M | Batch −50%Batch -50%; time-limited 50% off now: 0.4/1.4 |
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.075 | $0.25 | $0.015 | 0.119 | 1.05M | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.4); not checked against GMICloud's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.084 | $0.28 | $0.017 | 0.133 | 1.05M | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.44); not checked against Novita's own page |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥0.8 | ¥2.8 | ¥0.23 | 0.194 | — | SiliconFlow (硅基流动) own pricing page |
| Together Inference platform (own price page) | Platform 10-10 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | Together AI own pricing page |
| Fireworks Inference platform (own price page) | Platform 10-10 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | Batch −50%Fireworks AI own pricing page; batch -50% |
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0.5); not checked against DeepInfra's own page |
| BaseTen · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | BaseTen price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against BaseTen's own page |
| Crusoe · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | Crusoe price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Crusoe's own page |
| AtlasCloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against AtlasCloud's own page |
| Friendli · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | Friendli price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against Friendli's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
| Parasail · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 1.05M | Parasail price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Parasail's own page |
| Z.ai (via OpenRouter) · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.03 | 0.237 | 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
GMICloud · Novita · DeepInfra · BaseTen · Crusoe · AtlasCloud · Friendli · SiliconFlow · Parasail · Z.ai (via OpenRouter) - Inference platform (own price page)
SiliconFlow · Together · Fireworks - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
GLM-5.3-Flash→
04Performance
All results →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-Flash
- 41.8
- Output speed (median)
- 69 tok/s
- Time to first token
- 2.8s
- AA index per $ (blended)
- 215.47
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1475 | official | 2026-10-08 |
| LMArena WebDev | 1609 | official | 2026-10-08 |
| LMArena Vision | 1278 | official | 2026-10-02 |
| GPQA Diamond | 90.2% | independent | 2026-08-26 |
| AIME (OTIS Mock AIME 2024–2025) | 93.9% | independent | 2026-08-26 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-22 · DeepInfra · cache read0.012 → 0.024 USD (+100%)
- 2026-10-22 · DeepInfra · output0.2 → 0.4 USD (+100%)
- 2026-10-22 · DeepInfra · input0.06 → 0.12 USD (+100%)
- 2026-10-21 · DeepInfra · cache read0.015 → 0.03 USD (+100%)
- 2026-10-21 · DeepInfra · output0.25 → 0.5 USD (+100%)
- 2026-10-21 · DeepInfra · input0.075 → 0.15 USD (+100%)
- 2026-10-20 · GMICloud · cache read0.018 → 0.015 USD (-16.7%)
- 2026-10-20 · GMICloud · output0.3 → 0.25 USD (-16.7%)
- 2026-10-20 · GMICloud · input0.09 → 0.075 USD (-16.7%)
- 2026-10-14 · Z.ai (via OpenRouter) · new listing
06More from Zhipu (Z.ai)
FAQ
How much does the GLM-5.3-Flash API cost?
On the official pricing page: ¥0.8 / ¥2.8 per 1M input / output tokens, cached input ¥0.23 (checked 2026-10-10). The lowest price we found is $0.075 / $0.25 on GMICloud.
What is the context window of GLM-5.3-Flash?
1M tokens of context, up to 944K output tokens. Platforms may cap it lower – see the table.
Is GLM-5.3-Flash open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-5.3-Flash). Licence: MIT.