Type
Spec
Rate
Input
per 1M prompt tokens
Free
Output
per 1M generated tokens
Free
Implicit cache read
per 1M cached input tokens
Free
Web search
per request when enabled
$0.033
GLM 4.6V Flash and GLM 4.6V FlashX side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Z.ai Text GenerationGLM 4.6V Flash and GLM 4.6V FlashX are both Z.ai models in the Text Generation category, available through the EmpirioLabs API.
| Spec | GLM 4.6V Flash | GLM 4.6V FlashX |
|---|---|---|
| Model ID | glm-4-6v-flash | glm-4-6v-flashx |
| Author | Z.ai | Z.ai |
| Released | Dec 8, 2025 | - |
| Context window | 128K tokens | 128K tokens |
| Max output | 32,768 tokens | 32,768 tokens |
| Input | Text Image Video File | Text Image Video File |
| Output | Text | Text |
| Structured output | JSON Mode | JSON Mode |
| Region | Singapore | Singapore |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/glm-4-6v-flash:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/glm-4-6v-flashx:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | GLM 4.6V Flash | GLM 4.6V FlashX |
|---|---|---|
| temperature | 0 to 1 Default: 1 | 0 to 1 Default: 1 |
| top_p | 0.01 to 1 Default: 0.95 | 0.01 to 1 Default: 0.95 |
| max_tokens | 1 to 32768 Default: 4096 | 1 to 32768 Default: 4096 |
| stop | array | array |
| do_sample | boolean Default: true | boolean Default: true |
| enable_thinking | boolean Default: true | boolean Default: true |
| thinking | object | object |
| tools | array | array |
| tool_choice | auto Default: auto | auto Default: auto |
| tool_stream | boolean Default: false | boolean Default: false |
| tool_web_search | boolean Default: false | boolean Default: false |
| search_result | boolean Default: true | boolean Default: true |
| search_prompt | string | string |
| count | 1 to 50 Default: 10 | 1 to 50 Default: 10 |
| search_domain_filter | string | string |
| search_recency_filter | oneDay, oneWeek, oneMonth, oneYear, noLimit Default: noLimit | oneDay, oneWeek, oneMonth, oneYear, noLimit Default: noLimit |
Base token use is free. Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled.
Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled.
GLM 4.6V Flash serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id glm-4-6v-flash. Both models are called through the same endpoint. Set model to glm-4-6v-flash or glm-4-6v-flashx. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-4-6v-flash",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Both models have a context window of 128K tokens. Capabilities listed only for GLM 4.6V FlashX: cache. Both models list the same rate for Web search (per request when enabled). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Both models list the same rate for Web search (per request when enabled). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.