GLM-5.3
glm-5.3
GLM penuh dengan konteks 1M untuk dokumen sangat panjang, agent, dan penalaran kompleks. Input teks.
Context window1,048,576input + output
Max output128,000native generation limit
Input rate$1.12per 1M tokens
Output rate$3.52per 1M tokens
Input cache$0.21per 1M tokens
Advantages GLM-5.3
Konteks 1.048.576 token
Muat dokumen, riwayat, dan instruksi panjang dalam satu jendela.
GLM penuh
Tier penuh di atas Flash untuk tugas yang membutuhkan penalaran lebih dalam.
Output 128.000 token
Jawaban panjang dan dokumen terstruktur dalam satu request.
Capability
Per-capability verification status is in capability matrix. Capabilities follow the model's native limits.
Text inputStreamingReasoningFunction calling
Plans for this model
Integration example
Replace RINS_API_KEY with an active key from the dashboard.
cURLPOST /v1/chat/completions
curl https://api.rinsdev.cloud/v1/chat/completions \
-H "Authorization: Bearer $RINS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Halo"}]
}'
See examples for Python, JavaScript, streaming, tool calling, and image input