Z.ai: GLM 5.2
The Z.ai: GLM 5.2 is a language model designed for processing text input within an extremely high context length of 1048576 tokens and generating output up to 131072 completion tokens per interaction. It accepts only text-based input modalities and supports tools, reasoning capabilities, but does not have structured output or open weights. This model may be worth considering for those prioritizing its price point and performance on benchmark tasks, given a blended score of 76.2 across two independent benchmarks. With an input cost of $0.6832 per million tokens and an output cost of $2.1472 per million tokens, it offers a relatively affordable option with some robust capabilities.
Benchmark results
Independent, published benchmarks. Blended score 73.3 across 2 benchmarks, last refreshed 2026-10-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 55.6 |
| EQ-Bench | emotional understanding in dialogue | 78.7 |
- Model ID
- z-ai/glm-5.2
- Vendor
- z-ai
- Released
- June 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 943,718 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.06/M input and $7.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.38 |
| A month of a busy support chatbot | 5M in / 2M out | $14.30 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-10-10 | $0.06 | $7.00 | 1,048,576 |
| 2026-10-09 | $0.08 | $4.30 | 1,048,576 |
| 2026-10-08 | $0.17 | $12.00 | 1,048,576 |
| 2026-10-07 | $0.06 | $12.00 | 1,048,576 |
| 2026-10-06 | $0.01 | $12.00 | 1,048,576 |
| 2026-10-05 | $0.02 | $16.00 | 1,048,576 |
| 2026-10-04 | $0.38 | $3.49 | 1,048,576 |
| 2026-10-02 | $0.41 | $3.99 | 1,048,576 |
| 2026-10-01 | $1.40 | $4.40 | 1,048,576 |
| 2026-09-30 | $0.21 | $3.99 | 1,048,576 |
| 2026-09-29 | $0.32 | $4.40 | 1,048,576 |
| 2026-09-20 | $0.65 | $2.04 | 1,048,576 |
| 2026-09-19 | $0.55 | $1.74 | 1,048,576 |
| 2026-09-18 | $0.49 | $1.56 | 1,048,576 |
| 2026-09-15 | $1.40 | $4.40 | 1,048,576 |
| 2026-09-14 | $0.68 | $2.15 | 1,048,576 |
| 2026-09-12 | $0.60 | $2.00 | 1,048,576 |
| 2026-09-02 | $0.97 | $3.04 | 1,048,576 |
| 2026-08-25 | $1.19 | $3.74 | 1,048,576 |
| 2026-08-19 | $0.97 | $3.04 | 1,048,576 |
| 2026-08-18 | $0.50 | $3.15 | 1,048,576 |
| 2026-08-17 | $1.19 | $3.74 | 1,048,576 |
| 2026-08-16 | $0.32 | $1.02 | 1,048,576 |
| 2026-08-15 | $0.49 | $1.54 | 1,048,576 |
| 2026-08-14 | $0.63 | $1.98 | 1,048,576 |
| 2026-08-13 | $0.50 | $3.15 | 1,048,576 |
| 2026-08-12 | $0.42 | $1.40 | 1,048,576 |
| 2026-08-10 | $0.76 | $2.42 | 1,048,576 |
| 2026-08-09 | $0.10 | $0.31 | 1,048,576 |
| 2026-08-08 | $0.36 | $1.14 | 1,048,576 |
| 2026-08-07 | $0.70 | $2.19 | 1,048,576 |
| 2026-08-04 | $0.76 | $2.42 | 1,048,576 |
| 2026-08-03 | $1.19 | $3.74 | 1,048,576 |
| 2026-08-02 | $0.39 | $1.21 | 1,048,576 |
| 2026-08-01 | $0.76 | $2.39 | 1,048,576 |
| 2026-07-31 | $1.19 | $3.74 | 1,048,576 |
| 2026-07-30 | $0.68 | $2.13 | 1,048,576 |
| 2026-07-28 | $0.73 | $2.28 | 1,048,576 |
| 2026-07-27 | $0.82 | $2.59 | 1,048,576 |
| 2026-07-26 | $0.72 | $2.25 | 1,048,576 |
| 2026-07-25 | $0.77 | $2.42 | 1,048,576 |
| 2026-07-24 | $0.77 | $2.43 | 1,048,576 |
| 2026-07-23 | $0.83 | $2.60 | 1,048,576 |
| 2026-07-22 | $0.82 | $2.57 | 1,048,576 |
| 2026-07-21 | $0.97 | $3.04 | 1,048,576 |
| 2026-07-20 | $0.97 | $3.06 | 1,048,576 |
| 2026-07-19 | $0.25 | $0.80 | 1,048,576 |
| 2026-07-18 | $0.41 | $1.29 | 1,048,576 |
| 2026-07-17 | $0.93 | $2.93 | 1,048,576 |
Category rankings
Where Z.ai: GLM 5.2 places across the 14 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #19 | Long-Document SummarizationWriting · of 25 ranked | 152 |
| #19 | Meeting NotesBusiness · of 25 ranked | 142 |
| #20 | Legal ResearchProfessional · of 25 ranked | 156 |
| #20 | Scientific ResearchProfessional · of 25 ranked | 156 |
| #20 | Fiction CollaboratorPersonal · of 25 ranked | 156 |
| #20 | Literature ReviewResearch · of 25 ranked | 156 |
| #21 | Code RefactoringCode · of 25 ranked | 151 |
| #21 | RAG PipelinesAgents · of 25 ranked | 151 |
| #21 | Long-Context Q&AAgents · of 25 ranked | 147 |
| #22 | Transcript CleanupWriting · of 25 ranked | 141 |
| #23 | RFP ResponseBusiness · of 25 ranked | 155 |
| #24 | Code DocumentationCode · of 25 ranked | 138 |
| #24 | Contract ReviewProfessional · of 25 ranked | 160 |
| #25 | Character RoleplayPersonal · of 25 ranked | 141 |
Similar models
Z.ai: GLM 5 Turbo
Z.ai: GLM 5.3
Z.ai: GLM 5.1
Z.ai: GLM 4.7
Z.ai: GLM 5
Z.ai: GLM 5.3 (batch)
Quick answers
- How much does Z.ai: GLM 5.2 cost?
- $0.06 per million input tokens and $7.00 per million output tokens.
- What is Z.ai: GLM 5.2's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does Z.ai: GLM 5.2 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Z.ai: GLM 5.2 process images?
- No, it is text-only on the input side.