mlx-optiq
← Models

GLM 5.3 Flash

GLM 5.3 Flash on OptiQ Cloud, billed per token.

cloud

GLM 5.3 Flash is a model from Z.ai served by OptiQ Cloud, billed per token, with a context window of about 1 million tokens. Boost in OptiQ Code runs on it by default. All OptiQ Cloud models are served at full precision, and your requests are never used for training.

Input$0.15 / M
Cached input$0.03 / M
Output$0.50 / M
Context1M tokens
Typical speed—

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.

DeepSWE v1.1

DeepSWE v1.1, as each maker published itDeepSeek V4.1 Flash 77.0; GLM 5.3 Flash 63.4; MiniMax M3.1 Flash 73.7; GLM 5.3 66.9DeepSeek V4.1 Flash77.0GLM 5.3 Flash63.4MiniMax M3.1 Flash73.7GLM 5.366.9

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

Output price, $ per million tokens

Output price, $ per million tokensDeepSeek V4.1 Flash $0.50; GLM 5.3 Flash $0.50; MiniMax M3.1 Flash $0.60; Qwen3.8 27B $2.00; MiMo V2.6 Flash $0.65; MiniMax M3 $2.00; GLM 5.3 $4.40; DeepSeek V4 Pro $6.60DeepSeek V4.1 Flash$0.50GLM 5.3 Flash$0.50MiniMax M3.1 Flash$0.60Qwen3.8 27B$2.00MiMo V2.6 Flash$0.65MiniMax M3$2.00GLM 5.3$4.40DeepSeek V4 Pro$6.60

Input price, $ per million tokens

Input price, $ per million tokensDeepSeek V4.1 Flash $0.10; GLM 5.3 Flash $0.15; MiniMax M3.1 Flash $0.15; Qwen3.8 27B $0.15; MiMo V2.6 Flash $0.22; MiniMax M3 $0.50; GLM 5.3 $1.40; DeepSeek V4 Pro $2.20DeepSeek V4.1 Flash$0.10GLM 5.3 Flash$0.15MiniMax M3.1 Flash$0.15Qwen3.8 27B$0.15MiMo V2.6 Flash$0.22MiniMax M3$0.50GLM 5.3$1.40DeepSeek V4 Pro$2.20

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-flash

Codex

optiq run codex --cloud glm-5.3-flash

OpenCode

optiq run opencode --cloud glm-5.3-flash

Mistral Vibe

optiq run vibe --cloud glm-5.3-flash

Hermes Agent

optiq run hermes --cloud glm-5.3-flash

OpenClaw

optiq run openclaw --cloud glm-5.3-flash

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-flash

OptiQ Lab, and any app that talks to optiq serve

Pick optiq-cloud/glm-5.3-flash 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_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-flash",
       "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-flash",
    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-Flash).

Terminal-Bench 2.184.3
DeepSWE v1.163.4

Details

Input$0.15 per million tokens
Cached input$0.03 per million tokens
Output, including reasoning$0.50 per million tokens
Context window1M tokens
Longest reply128,000 tokens
Model idglm-5.3-flash on the API, optiq-cloud/glm-5.3-flash in optiq serve