Alla modellerchatGLM 5.3

GLM 5.3

av Z-AIPremium

Testa på Kunya
Z
chat

GLM 5.3

Z.ai reasoning flagship — complex software engineering and long-horizon agent tasks with 1M context (reasoning always on)

Modell-ID:glm-5.3

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "max_tokens": 4096
}
cURL-exempel
curl -X POST https://kunya.ai/api/v1/chat/completions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"glm-5.3","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'

Anteckningar

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
  • •Supports tool calling via the `tools` parameter.

Priser

Indata$1.82 per 1M tokens
Utdata$5.72 per 1M tokens
Kontextfönster1049K

Kunya benchmark

Updated 2026-10-06 · #6 performance · #15 value

Performance
96.5
Value (KVI)
73.6
Literary writing
82.8
SWE Verified
95.4%
Cost
$8.12/1k tasks
Full benchmark report →

Funktioner

Streaming Ja
Vision Nej
Resonemang Ja
Verktyg Ja
LeverantörZ-AI
Testa på Kunya

Rankningar

Programming#2
Tool Use#2

Liknande modeller

Hy3

Tencent

295B MoE reasoning model (21B active) — agentic workflows, 256K context, configurable chain-of-thought for coding, analysis, and tool use

API-dokumentation

Qwen 3.7 Max

Qwen

Flagship Qwen3.7 — 1M context, agentic coding, office productivity, long-horizon execution, prompt caching

API-dokumentation

DeepSeek V4 Pro

DeepSeek

Flagship model — 1M context, thinking + non-thinking modes

API-dokumentation

GLM 5.2

Z-AI

Z.ai GLM 5.2 via EvoLink — long-horizon coding agents, repo Q&A, tool-using engineering workflows, 1M context with thinking + prompt caching

API-dokumentation