// Zhipu (Z.ai)
GLM-5.2
A Zhipu (Z.ai) model. 12 prices across 11 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 (DeepInfra)
- $0.563 / $1.8
- Context
- 1.05M
- AA index
- 33.7
Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →
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 | 1.05M (1,048,576 tokens) |
| Max output | 944K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 753B (from weight files) |
| Released | Jun 16, 2026 |
| Model IDs | glm-5.2 · z-ai/glm-5.2 · zai-org/GLM-5.2 |
02Prices on 11 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 | 1.05M | Batch −50%Batch -50% |
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.563 | $1.8 | $0.105 | 0.872 | 1.05M | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0.25); not checked against DeepInfra's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.65 | $2.04 | $0.121 | 0.998 | 1.05M | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.536); not checked against Novita'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=0.15); not checked against SiliconFlow's own page |
| AtlasCloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.938 | $2.95 | $0.174 | 1.44 | 1.05M | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.33); not checked against AtlasCloud's own page |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥8 | ¥28 | ¥2 | 1.94 | — | SiliconFlow (硅基流动) own pricing page |
| Together Inference platform (own price page) | Platform 10-10 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Together AI own pricing page |
| Nebius · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.14 | 2.15 | 1.05M | Nebius price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Nebius's own page |
| BaseTen · fp8 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=fp8; discount field=0); not checked against BaseTen's own page |
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against GMICloud's own page |
| Parasail · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 262K | Parasail price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Parasail's own page |
| Friendli · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $1.4 | $4.4 | $0.26 | 2.15 | 1.05M | Friendli price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against Friendli'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
DeepInfra · Novita · SiliconFlow · AtlasCloud · Nebius · BaseTen · GMICloud · Parasail · Friendli - Inference platform (own price page)
SiliconFlow · Together - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
GLM-5.2→
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-5.2 (Max)
- 33.7
- Output speed (median)
- 88 tok/s
- Time to first tokenGLM-5.2 (Non-reasoning): 1.11s
- 3.5s
- AA index per $ (blended)
- 17.37
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| GPQA Diamond | 71.2% | independent | 2026-08-10 |
| SWE-bench Verified | 78.7% | independent | 2026-06-25 |
| AIME (OTIS Mock AIME 2024–2025) | 28.9% | independent | 2026-08-10 |
| τ²-bench | 37.1% | official | 2026-07-24 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-22 · Nebius · cache read— → 0.14 USD
- 2026-10-14 · SiliconFlow · cache read0.221 → 0.13 USD (-41.2%)
- 2026-10-14 · SiliconFlow · output3.74 → 2.2 USD (-41.2%)
- 2026-10-14 · SiliconFlow · input1.19 → 0.7 USD (-41.2%)
06More from Zhipu (Z.ai)
FAQ
How much does the GLM-5.2 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 $0.563 / $1.8 on DeepInfra.
What is the context window of GLM-5.2?
1.05M tokens of context, up to 944K output tokens. Platforms may cap it lower – see the table.
Is GLM-5.2 open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-5.2). Licence: MIT.