Skip to content

GLM-5.3-Flash: Ox Alpha, named

The Ox Alpha preview is GLM-5.3-Flash: native multimodal, 1M context, MIT-licensed 320B-A18B. Same AnyRouter routes, catalog id z-ai/glm-5.3-flash.

Open GLM-5.3-Flash
Bar charts comparing GLM-5.3-Flash with GLM-5.2, DeepSeek-V4-Vision-Exp, Claude Opus 4.8, GPT-5.6 Terra and Gemini 3.7 Flash on six agent and coding benchmarks

The model AnyRouter listed as stealth/ox-alpha is GLM-5.3-Flash. Same routes, new public name, official launch. Call z-ai/glm-5.3-flash. The old id stays for history, ranking, and leaderboard. It is unlisted from GET /api/v1/models and the /models picker.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead. 320B-A18B, MIT License, 1M-token context. Z.ai ran the Ox Alpha preview entirely on Chinese AI chips.

Leading capabilities at a highly competitive price. Host routes keep the copied Ox Alpha $0/$0 rates. Z.ai's API docs list Coding Plan points, not a $/1M list we can copy. Announcement · weights · API.

Z.ai LLM Performance Evaluation bar chart comparing GLM-5.3-Flash with GLM-5.2, DeepSeek-V4-Vision-Exp, Claude Opus 4.8, GPT-5.6 Terra, and Gemini 3.7 Flash across six benchmarks.
Z.ai “LLM Performance Evaluation.” Scores copied from the chart. Not AnyRouter measurements.
BenchmarkGLM-5.3-FlashGLM-5.2DeepSeek-V4-Vision-ExpClaude Opus 4.8GPT-5.6 TerraGemini 3.7 Flash
Terminal Bench 2.184.381.083.985.087.485.8
DeepSWE v1.163.446.259.358.069.665.3
Agents' Last Exam26.320.427.327.028.0,
AutomationBench v1.0.648.826.238.841.037.252.3
HLE w/ Tools55.354.755.157.9, ,
GDPVal-AA v2177315041675158215711527

DeepSWE v1.1: Flash vs GLM-5.2

Z.ai chart. GLM-5.3-Flash 63.4, GLM-5.2 46.2.

GLM-5.3-Flash
63.4
GLM-5.3-Flash: 63.4
GLM-5.2
46.2
GLM-5.2: 46.2

AutomationBench v1.0.6: Flash vs GLM-5.2

Z.ai chart. GLM-5.3-Flash 48.8, GLM-5.2 26.2.

GLM-5.3-Flash
48.8
GLM-5.3-Flash: 48.8
GLM-5.2
26.2
GLM-5.2: 26.2
Z.ai Code Bench v1.0 agentic coding performance by effort level. GLM-5.3-Flash purple line versus GLM-5.3, GLM-5.2, Claude Fable 5, and Claude Opus 4.8.
Z.ai Code Bench v1.0 (Claude Code 2.1.207). Prefer the chart over token counts. Max accuracy is similar to Claude Opus 4.8; a step up from GLM-5.2.

Try it in the Vercel AI SDK. createAnyRouter() reads ANYROUTER_API_KEY:

generateText with the catalog id
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"

const anyrouter = createAnyRouter()

const { text } = await generateText({
  model: anyrouter("z-ai/glm-5.3-flash"),
  prompt: "Summarize this diff in three bullets.",
})
console.log(text)

Already on the OpenAI SDK? OpenAI SDK playbook:

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://anyrouter.dev/api/v1",
  apiKey: process.env.ANYROUTER_API_KEY,
})

const res = await client.chat.completions.create({
  model: "z-ai/glm-5.3-flash",
  messages: [{ role: "user", content: "Hello" }],
})
console.log(res.choices[0]?.message.content)
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-5.3-flash","messages":[{"role":"user","content":"Hello"}]}'

Or launch a coding agent through the anyr CLI:

curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr claude --model "z-ai/glm-5.3-flash"
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr opencode --model "z-ai/glm-5.3-flash"
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr codex --model "z-ai/glm-5.3-flash"

More: AI SDK · OpenAI SDK · coding agents.

No terminal? Open the playground and send a first message.

Try in playground

Related posts

Looking for the full catalog? Browse all models.