// Zhipu (Z.ai)
GLM 5
A Zhipu (Z.ai) model. 3 prices across 3 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (GMICloud)
- $0.6 / $1.92
- Context
- 203K
- AA index
- 27.9
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 | 203K (202,752 tokens) |
| Max output | 182K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 754B (from weight files) |
| Released | Feb 11, 2026 |
| Model IDs | z-ai/glm-5 |
02Prices on 3 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 |
|---|---|---|---|---|---|---|---|
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.6 | $1.92 | $0.12 | 0.93 | 203K | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.4); not checked against GMICloud's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.95 | $2.55 | $0.2 | 1.35 | 205K | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $1 | $3.2 | $0.2 | 1.55 | 203K | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); 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
GMICloud · SiliconFlow · 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-5 (Reasoning)
- 27.9
- Output speed (median)
- 75 tok/s
- Time to first token
- 1.57s
- AA index per $ (blended)
- 30.01
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1458 | official | 2026-10-08 |
| LMArena WebDev | 1434 | official | 2026-10-08 |
| GPQA Diamond | 87.8% | independent | 2026-02-12 |
| MMLU-Pro | 86.0% | vendor | 2026-03-11 |
| SWE-bench Verified | 72.8% | official | 2026-02-17 |
| AIME (OTIS Mock AIME 2024–2025) | 80.0% | independent | 2026-02-12 |
| τ²-bench | 86.8% | official | 2026-02-27 |
| Terminal-Bench 2.0 | 52.4% | official | 2026-02-11 |
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 5 API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.6 / $1.92 on GMICloud.
What is the context window of GLM 5?
203K tokens of context, up to 182K output tokens. Platforms may cap it lower – see the table.
Is GLM 5 open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-5). Licence: MIT.