glm-4-6v-flashx
Visual understanding, information extraction, and tool calling.
Pricing: Input 9.6 credits / 1M tokens (≈ $0.05), Output 96 credits / 1M tokens (≈ $0.48).
Prices updated
How can I help you today?
This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.
More AI models from Z.ai
GLM-4.6V-FlashX API
Call GLM-4.6V-FlashX on ModelFold with model id glm-4-6v-flashx.
What this model is for
Context window
131,072 tokens of context for longer conversations, document analysis, and code.
Visual understanding
Accepts text and images, returning text. Use it to understand screenshots, charts, and documents.
Reasoning and tools
Supports reasoning and function calling. Pass tools and tool_choice; your application executes the requested tools.
Pricing
Billing follows token usage. At current prices, input is 9.6 credits per 1M tokens (about $0.048) and output is 96 credits per 1M tokens (about $0.48). Final charges follow actual token usage. Failed calls are not charged.
FAQ
What model id do I send?⌄
Send model glm-4-6v-flashx to POST https://modelfold.ai/v1/chat/completions with Authorization: Bearer YOUR_API_KEY and an OpenAI-style messages array. stream: true returns server-sent events.
Does it support tools?⌄
Yes. Pass tools and tool_choice as in OpenAI Chat Completions. The model returns tool arguments; your application runs the tool and sends back its result.
| Input | 9.6 credits 1M tokens≈ $0.05 |
| Cached input | 0.96 credits 1M tokens≈ $0.00 |
| Output | 96 credits 1M tokens≈ $0.48 |
Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.
Read API docs →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-4-6v-flashx","messages":[{"role":"user","content":"Hello"}]}'