GLM-4.6Z.ai
- api
- chat
- hosting
- Singapore
- model lab
- Z.AI
- weights
- open
- added
- September 2025
- model id
- zai/GLM-4.6
capabilities 2/8
2 providers serve glm-4.6. This page is one of them. Compare all endpoints
- input
- $0.60
- output
- $2.20
- cache write
- -
- cache read
- -
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0820 |
| 1M in + 100K out | $0.82 |
| 10M in + 1M out | $8.20 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| eval | Score as a share of 100 | /100 |
|---|---|---|
| Math Index | 86.0 | |
| AIME 2025 | 86.0 | |
| MMLU Pro | 82.9 | |
| GPQA Diamond | 78.0 | |
| τ²-Bench | 70.5 | |
| LiveCodeBench | 69.5 | |
| Coding Index | 45.8 | |
| Terminal-Bench Hard | 25.0 | |
| Intelligence Index | 18.5 | |
| Humanity's Last Exam | 14.5 | |
| 10 evals | mean | 57.7 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-09-30.
- retention
- none
- trains on prompts
- no
- hosted in
- Singapore
Terms are the provider's, not Requesty's: routing a request here puts it under them. Z AI Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
zai/GLM-4.6this id pins the z.ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="zai/GLM-4.6", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
GLM-4.6 is Z AI’s latest flagship model, designed to push agentic and coding performance further. It expands the context window from 128K to 200K tokens, improves reasoning and tool-use capabilities, and delivers stronger results in coding benchmarks and real-world development workflows. GLM-4.6 demonstrates refined writing quality, more capable agent behavior, and higher token efficiency (≈15% fewer tokens vs. GLM-4.5). Evaluations show clear gains over GLM-4.5 across reasoning, agents, and coding, reaching near parity with Claude Sonnet 4 in practical tasks while outperforming other open-source baselines. GLM-4.6 is available through the Z.ai API platform, OpenRouter, coding agents (Claude Code, Roo Code, Cline, Kilo Code), and soon as downloadable weights on HuggingFace and ModelScope.
questions 6
How much does GLM-4.6 cost?
What is the context window of GLM-4.6?
How does GLM-4.6 perform on benchmarks?
What can GLM-4.6 do?
How do I use GLM-4.6 with the OpenAI SDK?
Can I run GLM-4.6 through Requesty?
more from z.ai 7
| endpoint | ctx | in /M |
|---|---|---|
| glm-5.3-flash | 1M | $0.15 |
| glm-5.3 | 1M | $1.40 |
| glm-5.2 | 1M | $1.40 |
| glm-5.1 | 200K | $1.40 |
| GLM-5 | 200K | $1.00 |
| GLM-4.7 | 200K | $0.60 |
| GLM-4.5 | 131K | $0.60 |
call glm-4.6 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology