GLM 4.6V FlashX API

About GLM 4.6V FlashX

High-speed GLM-4.6V vision model for image, video, file, and text understanding, with 128K context and native function calling.

Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled. Supports text, image, video, and file input plus function tools, tool_choice auto, JSON response_format, thinking controls, tool_stream, temperature, top_p, do_sample, max_tokens, stop, and streaming.

Also known as Z.ai GLM 4.6V FlashX

GLM 4.6V FlashX specs

Model ID

glm-4-6v-flashx

Author

Z.ai

Category

Text Generation

Released

-

Context window

128K tokens

Max output

32,768 tokens

Input

TextImageVideoFile

Output

Text

Structured output

JSON Mode

Region

Singapore

Endpoints

POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/glm-4-6v-flashx:generateContent

Alternate model IDs

glm-4.6v-flashxzai/glm-4.6v-flashxzhipu/glm-4.6v-flashx

GLM 4.6V FlashX API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

How to call the GLM 4.6V FlashX API

GLM 4.6V FlashX 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-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-flashx",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="glm-4-6v-flashx",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)

GLM 4.6V FlashX API parameters

Request parameters supported by the GLM 4.6V FlashX API on EmpirioLabs. Defaults apply when a field is omitted.

Good to know

Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled.

GLM 4.6V FlashX API: common questions

How much does the GLM 4.6V FlashX API cost?

On EmpirioLabs, GLM 4.6V FlashX is billed pay as you go: Input $0.04 per 1M prompt tokens; Output $0.40 per 1M generated tokens; Implicit cache read $0.036 per 1M cached input tokens; Web search $0.033 per request when enabled. The live rate card on this page always matches what the API charges.

What is the context window of GLM 4.6V FlashX?

GLM 4.6V FlashX supports a 128K-token context window with up to 32,768 output tokens per response.

Is the GLM 4.6V FlashX API OpenAI-compatible?

Yes. GLM 4.6V FlashX serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to glm-4-6v-flashx.

Can I try GLM 4.6V FlashX in the browser before integrating?

Yes. The EmpirioLabs playground runs GLM 4.6V FlashX in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a GLM 4.6V FlashX API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.