mlx-optiq
← Models

GLM 5.3

GLM 5.3 on OptiQ Cloud, billed per token.

cloud

GLM 5.3 on OptiQ Cloud: $1.40 input, $4.40 output per million tokens. Requests go only to providers that serve the model at fp8 or better and do not train on your data.

Input$1.40 / M
Cached input$0.26 / M
Output$4.40 / M
Context1M tokens

Next to the other OptiQ Cloud models

Scores are from each maker's model card, for benchmarks that more than one card reports; OptiQ did not run them. Prices are what OptiQ Cloud charges.

Terminal-Bench 2.1

Terminal-Bench 2.1, as each maker published itGLM 5.3 Flash 84.3; GLM 5.3 88.2GLM 5.3 Flash84.3GLM 5.388.2

DeepSWE v1.1

DeepSWE v1.1, as each maker published itGLM 5.3 Flash 63.4; DeepSeek V4.1 Flash 77.0; GLM 5.3 66.9GLM 5.3 Flash63.4DeepSeek V4.1 Flash77.0GLM 5.366.9

Output price, $ per million tokens

Output price, $ per million tokensGLM 5.3 Flash $0.50; DeepSeek V4.1 Flash $0.50; GLM 5.3 $4.40GLM 5.3 Flash$0.50DeepSeek V4.1 Flash$0.50GLM 5.3$4.40

Input price, $ per million tokens

Input price, $ per million tokensGLM 5.3 Flash $0.15; DeepSeek V4.1 Flash $0.10; GLM 5.3 $1.40GLM 5.3 Flash$0.15DeepSeek V4.1 Flash$0.10GLM 5.3$1.40

How Z.ai compares it

Scores published by Z.ai for GLM-5.3 and other models, taken from the comparison table on Z.ai's model card. Higher is better; OptiQ did not run these benchmarks.

Terminal-Bench 2.1

Terminal-Bench 2.1, as published by Z.aiGLM-5.3 88.2; GLM-5.2 81.0; Kimi K3 88.3; DeepSeek-V4 Pro-0813 87.9; Qwen3.8-Max 86.6; Opus 4.8 85.0; Fable 5 (w/ fallback) 88.0; GPT-5.6 Sol 88.8GLM-5.388.2GLM-5.281.0Kimi K388.3DeepSeek-V4 Pro-081387.9Qwen3.8-Max86.6Opus 4.885.0Fable 5 (w/ fallback)88.0GPT-5.6 Sol88.8

DeepSWE v1.1

DeepSWE v1.1, as published by Z.aiGLM-5.3 66.9; GLM-5.2 46.2; Kimi K3 67.5; DeepSeek-V4 Pro-0813 62.7; Qwen3.8-Max 56.6; Opus 4.8 58.0; Fable 5 (w/ fallback) 69.7; GPT-5.6 Sol 72.7GLM-5.366.9GLM-5.246.2Kimi K367.5DeepSeek-V4 Pro-081362.7Qwen3.8-Max56.6Opus 4.858.0Fable 5 (w/ fallback)69.7GPT-5.6 Sol72.7

Terminal-Bench 3.0

Terminal-Bench 3.0, as published by Z.aiGLM-5.3 28.3; GLM-5.2 4.6; Kimi K3 17.4; Opus 4.8 21.1; Fable 5 (w/ fallback) 33.7; GPT-5.6 Sol 34.6GLM-5.328.3GLM-5.24.6Kimi K317.4Opus 4.821.1Fable 5 (w/ fallback)33.7GPT-5.6 Sol34.6

Source: zai-org/GLM-5.3

Use it

Connect this Mac

Sign in once. New accounts get $2 of credit. See OptiQ Cloud.

pip install mlx-optiq
optiq cloud login

Claude Code

optiq run claude --cloud glm-5.3

Codex

optiq run codex --cloud glm-5.3

OpenCode

optiq run opencode --cloud glm-5.3

Mistral Vibe

optiq run vibe --cloud glm-5.3

Hermes Agent

optiq run hermes --cloud glm-5.3

OpenClaw

optiq run openclaw --cloud glm-5.3

No local model is loaded. optiq run starts optiq serve --cloud-only, sets the agent up for this session only, and stops the server when the agent exits.

OptiQ Code

Boost: this model leads the task and your local model is its helper.

/boost glm-5.3

OptiQ Lab, and any app that talks to optiq serve

Pick optiq-cloud/glm-5.3 in the model list. With no local model:

optiq serve --cloud-only

The API, from anywhere

Create a key on the dashboard.

curl https://cloud.mlx-optiq.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPTIQ_CLOUD_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3",
       "messages": [{"role": "user", "content": "Hello"}]}'
from openai import OpenAI

client = OpenAI(
    base_url="https://cloud.mlx-optiq.com/api/v1",
    api_key="<your key>")
reply = client.chat.completions.create(
    model="glm-5.3",
    messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)

Published benchmarks

These coding and agent benchmark figures were published by Z.ai on its official model card (zai-org/GLM-5.3).

Terminal-Bench 2.188.2
DeepSWE v1.166.9
Terminal-Bench 3.028.3

Details

Input$1.40 per million tokens
Cached input$0.26 per million tokens
Output, including reasoning$4.40 per million tokens
Context window1M tokens
Longest reply131,072 tokens
Model idglm-5.3 on the API, optiq-cloud/glm-5.3 in optiq serve