Multimodal model with strong image + text understanding.
| Specification | Price |
|---|---|
| Input | $0.3/ M tokens |
| Output | $0.9/ M tokens |
| Cache read | $0.055/ M tokens |
| Cache write | -- |
Paste and run the sample code below. The Gate.AI API is OpenAI-compatible—most SDKs only need a new base URL. To switch models, change the model ID.
Sign in to the Gate.AI console and create a new key under "API Keys". Keep it safe and send it via the Authorization header on every request.
Create a key in the consoleSend a POST request to the Chat Completions endpoint with a model ID and an array of messages to get a reply.
curl --location "https://api.gate.ai/openai/v1/chat/completions" \
--header "Authorization: Bearer {API_KEY}" \
--header "Content-Type: application/json" \
--data '{
"model": "glm-4.6v",
"messages": [
{"role": "user", "content": "Hello"}
]
}'By default a full JSON response is returned. Add "stream": true to the request body to receive incremental chunks over SSE.
curl --no-buffer --location "https://api.gate.ai/openai/v1/chat/completions" \
--header "Authorization: Bearer {API_KEY}" \
--header "Content-Type: application/json" \
--data '{
"model": "glm-4.6v",
"messages": [
{"role": "user", "content": "Hello"}
],
"stream": true
}'Base URL, method, and required headers are rendered from the active protocol template for this model.
GLM 5.3 FlashFlash tier of GLM-5.3: native multimodal inputs, suited for efficient coding and long-horizon agents with stable long-context behavior in production.
GLM 5.3Flagship-tier model for complex software engineering and long-horizon agent tasks, with stable execution across multi-turn tool calls and large-scale codebase refactoring.
GLM 5.2GLM 5.2 is a large-scale reasoning model with a 1M-token context window, suited for long-horizon agents, repo-level coding, and multi-step automation.
GLM 5.1Offers significantly improved coding and long-horizon task capabilities, autonomously planning, executing, and refining a single task for over eight hours to deliver complete, engineering-grade results.
GLM 5 TurboDesigned for agent-based workflows such as OpenClaw.
GLM 5Competitive general-purpose Chinese model.
GLM 4.7 FlashUltra-fast for Chinese. Very cheap.
GLM 4.7Balanced model with strong Chinese understanding.
GLM 4.6Text-only model in the GLM-4 family with improved coding benchmarks and tool calls during reasoning, suited for software development and agent workflows.