// Zhipu (Z.ai)
GLM 4.7
A Zhipu (Z.ai) model. 2 prices across 2 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.4 / $1.75
- Context
- 203K
- AA index
- 22.2
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 | 203K (202,752 tokens) |
| Max output | 131K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 358B (from weight files) |
| Released | Dec 22, 2025 |
| Model IDs | z-ai/glm-4.7 |
02Prices on 2 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 |
|---|---|---|---|---|---|---|---|
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.4 | $1.75 | $0.08 | 0.738 | 203K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against DeepInfra's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.54 | $1.98 | $0.099 | 0.9 | 205K | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.1); not checked against Novita'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.
- Via OpenRouter / provider listed there
DeepInfra · Novita - Self-host the open weights
GPU / VRAM sizing and build plans→
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-4.7 (Reasoning)
- 22.2
- Output speed (median)
- 45 tok/s
- Time to first tokenGLM-4.7 (Non-reasoning): 1.52s
- 1.87s
- AA index per $ (blended)
- 30.16
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1441 | official | 2026-10-08 |
| LMArena WebDev | 1435 | official | 2026-10-08 |
| GPQA Diamond | 83.3% | independent | 2026-01-29 |
| AIME (OTIS Mock AIME 2024–2025) | 83.3% | independent | 2026-01-29 |
| Terminal-Bench 2.0 | 33.4% | official | 2025-12-22 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from Zhipu (Z.ai)
FAQ
How much does the GLM 4.7 API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.4 / $1.75 on DeepInfra.
What is the context window of GLM 4.7?
203K tokens of context, up to 131K output tokens. Platforms may cap it lower – see the table.
Is GLM 4.7 open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-4.7). Licence: MIT.