GLM 4.6V Flash
GLM-4.6V Flash is a lightweight vision-language model from Z.ai in the GLM-4.6V series, built for fast, low-cost image and document understanding.
- Input / output price
- $0.00 / $0.00 per 1M
- Context
- 128K tokens
- Released
- Dec 8, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Z.ai zai/glm-4.6v-flash | $0.00/M | $0.00/M |
Pricing
USD per 1M tokens on Z.ai, after gateway discounts.
- Input
- $0.00 per 1M
- Output
- $0.00 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better45tokens/sacross providers
Time to first token
Lower is better6.9sacross providers
Response latency
Lower is better12sacross providers
Benchmarks
15 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Design2Codez.ai | 69.8% | z.ai | Dec 8, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| WebVoyagerz.ai | 71.8% | z.ai | Dec 8, 2025 |
| AndroidWorldz.ai | 42.7% | z.ai | Dec 8, 2025 |
| OSWorldz.ai | 21.1% | z.ai | Dec 8, 2025 |
| MMBrowseCompz.ai | 7.1% | z.ai | Dec 8, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMBench V1.1z.ai | 86.9% | z.ai | Dec 8, 2025 |
| OCRBenchz.ai | 84.7% | z.ai | Dec 8, 2025 |
| MathVistaz.ai | 82.7% | z.ai | Dec 8, 2025 |
| MMStarz.ai | 74.7% | z.ai | Dec 8, 2025 |
| MMMU (Val)z.ai | 71.1% | z.ai | Dec 8, 2025 |
| VideoMMMUz.ai | 70.1% | z.ai | Dec 8, 2025 |
| ChartQAProz.ai | 62.6% | z.ai | Dec 8, 2025 |
| MMMU_Proz.ai | 60.6% | z.ai | Dec 8, 2025 |
| CharXiv_Val-Reasoningz.ai | 59.6% | z.ai | Dec 8, 2025 |
| MMLongBench-Docz.ai | 53% | z.ai | Dec 8, 2025 |
Apps
Use GLM 4.6V Flash in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
GLM 4.6V Flash FAQ
Short answers, built from the data on this page.
GLM 4.6V Flash is a model from Z.ai, released on Dec 8, 2025. GLM-4.6V Flash is a lightweight vision-language model from Z.ai in the GLM-4.6V series, built for fast, low-cost image and document understanding.
On the Respan gateway, GLM 4.6V Flash costs $0.00 per 1M input tokens and $0.00 per 1M output tokens on Z.ai, after gateway discounts.
GLM 4.6V Flash is served by Z.ai.
GLM 4.6V Flash accepts up to 128K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "zai/glm-4.6v-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GLM 4.6V Flash has 15 published benchmark scores, including Design2Code 69.8%, WebVoyager 71.8%, and MMBench V1.1 86.9%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.