GLM 5V Turbo
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.
- Input / output price
- $1.20 / $4.00 per 1M
- Context
- 203K tokens
- Released
- Apr 1, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Z.ai zai/glm-5v-turbo | $1.20/M | $4.00/M |
OpenRouter openrouter/glm-5v-turbo | $1.20/M | $4.00/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $1.20 per 1M
- Average output
- $4.00 per 1M
- Average cache read
- $0.24 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 better28tokens/sacross providers
Response latency
Lower is better7.5sacross providers
Benchmarks
18 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Design2Codedocs.z.ai | 94.8% | docs.z.ai | Apr 2, 2026 |
| Flame-VLM-Codedocs.z.ai | 93.8% | docs.z.ai | Apr 2, 2026 |
| CC-Repo-Explorationdocs.z.ai | 72.2% | docs.z.ai | Apr 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| WebVoyagerdocs.z.ai | 88.5% | docs.z.ai | Apr 2, 2026 |
| AndroidWorlddocs.z.ai | 75.7% | docs.z.ai | Apr 2, 2026 |
| OSWorlddocs.z.ai | 62.3% | docs.z.ai | Apr 2, 2026 |
| BrowseComp-VLdocs.z.ai | 51.9% | docs.z.ai | Apr 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| V*docs.z.ai | 89% | docs.z.ai | Apr 2, 2026 |
| SimpleVQAdocs.z.ai | 78.2% | docs.z.ai | Apr 2, 2026 |
| Vision2Webdocs.z.ai | 31% | docs.z.ai | Apr 2, 2026 |
| ImageMiningdocs.z.ai | 30.7% | docs.z.ai | Apr 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1434 Elo · #87 of 191 | LMArena | Nov 9, 2026 |
| LMArena WebDevLMArena | 1399 Elo · #89 of 124 | LMArena | Nov 10, 2026 |
| LMArena VisionLMArena | 1232 Elo · #59 of 91 | LMArena | Nov 9, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMSearchdocs.z.ai | 72.9% | docs.z.ai | Apr 2, 2026 |
| CC-Frontenddocs.z.ai | 68.4% | docs.z.ai | Apr 2, 2026 |
| MMSearch-Plusdocs.z.ai | 30% | docs.z.ai | Apr 2, 2026 |
| CC-Backenddocs.z.ai | 22.8% | docs.z.ai | Apr 2, 2026 |
Apps
Use GLM 5V Turbo 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 5V Turbo FAQ
Short answers, built from the data on this page.
GLM 5V Turbo is a model from Z.ai, released on Apr 1, 2026. GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.
On the Respan gateway, GLM 5V Turbo costs $1.20 per 1M input tokens and $4.00 per 1M output tokens on every provider, after gateway discounts.
GLM 5V Turbo is available through 2 providers: Z.ai and OpenRouter.
GLM 5V Turbo accepts up to 203K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "zai/glm-5v-turbo". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GLM 5V Turbo has 18 published benchmark scores, including Design2Code 94.8%, WebVoyager 88.5%, and V* 89%. 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.