Call GLM 5.3 Flash from Z.ai through an OpenAI-compatible API and pay per token from a prepaid balance, 60% under Z.ai's list price on OpenRouter. Model ID z-ai/glm-5.3-flash.

Pricing

Self-serve rates on our hosted open models, with the savings passed on to you and your users.

Self-serve · USD per 1M tokens
Model	Hours	Input	Output	Cached input
GLM 5.3 Flash60% under standard pricing		~~Standard price $0.15~~$0.06	~~Standard price $0.50~~$0.20	~~Standard price $0.03~~$0.012

Pricing details

Partners pay less. Talk to us

Performance

Model service data for the last hour, checked every 30 seconds.

GLM 5.3 FlashChecking sample time

Uptime: 100.00%
Time to first response: 1.32 s
Output speed: 69.0 tok/s
Cached input: 94.9%

Uptime history12h

2026-11-07 05:32:13 UTC2026-11-07 17:32:13 UTC

Quickstart

An OpenAI-compatible API: plug in your coding agent, router or app in minutes. Pay per token from one prepaid balance.

Direct API

Coding agents

and more

Routers

and more

Chat apps

Install the OpenAI Python SDK and set PARETO_API_KEY in your environment.

example.pyPython

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.paretoinference.com/v1",
    api_key=os.environ["PARETO_API_KEY"],
)

response = client.chat.completions.create(
    model="z-ai/glm-5.3-flash",
    messages=[{"role": "user", "content": "Hello, Pareto."}],
    stream=True,
)
for chunk in response:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Get started now

Install the OpenAI SDK and set PARETO_API_KEY in your server environment.

example.tsTypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PARETO_API_KEY,
  baseURL: "https://api.paretoinference.com/v1",
});

const response = await client.chat.completions.create({
  model: "z-ai/glm-5.3-flash",
  messages: [{ role: "user", content: "Hello, Pareto." }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Get started now

Set PARETO_API_KEY for OpenClaw and merge this into ~/.openclaw/openclaw.json. Start a new session.

openclaw.jsonJSON

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "pareto/z-ai/glm-5.3-flash"
      }
    }
  },
  "models": {
    "mode": "merge",
    "providers": {
      "pareto": {
        "baseUrl": "https://api.paretoinference.com/v1",
        "apiKey": "${PARETO_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "z-ai/glm-5.3-flash",
            "name": "GLM 5.3 Flash (Pareto)"
          }
        ]
      }
    }
  }
}

Get started now

Set PARETO_API_KEY and merge this into ~/.config/opencode/opencode.json. Keep your existing providers and settings, then start OpenCode.

opencode.jsonJSON

{
  "$schema": "https://opencode.ai/config.json",
  "model": "pareto/z-ai/glm-5.3-flash",
  "small_model": "pareto/z-ai/glm-5.3-flash",
  "provider": {
    "pareto": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Pareto Inference",
      "options": {
        "baseURL": "https://api.paretoinference.com/v1",
        "apiKey": "{env:PARETO_API_KEY}"
      },
      "models": {
        "z-ai/glm-5.3-flash": {
          "name": "GLM 5.3 Flash"
        }
      }
    }
  }
}

Get started now

Set PARETO_API_KEY, then start Claude Code with these variables. Use the base URL without /v1. Set all four model variables, or Claude Code requests Claude models and fails with a 401.

TerminalShell

export ANTHROPIC_BASE_URL=https://api.paretoinference.com
export ANTHROPIC_AUTH_TOKEN="$PARETO_API_KEY"
export ANTHROPIC_MODEL=z-ai/glm-5.3-flash
export ANTHROPIC_DEFAULT_HAIKU_MODEL=z-ai/glm-5.3-flash
export ANTHROPIC_DEFAULT_SONNET_MODEL=z-ai/glm-5.3-flash
export ANTHROPIC_DEFAULT_OPUS_MODEL=z-ai/glm-5.3-flash
claude

Get started now

Set PARETO_API_KEY and merge this provider into ~/.codex/config.toml, then start Codex.

config.tomlTOML

model = "z-ai/glm-5.3-flash"
model_provider = "pareto"

[model_providers.pareto]
name = "Pareto"
base_url = "https://api.paretoinference.com/v1"
env_key = "PARETO_API_KEY"
wire_api = "responses"

Get started now

Set PARETO_API_KEY and merge this provider into ~/.pi/agent/models.json. Select it with /model.

models.jsonJSON

{
  "providers": {
    "pareto": {
      "baseUrl": "https://api.paretoinference.com/v1",
      "api": "openai-completions",
      "apiKey": "$PARETO_API_KEY",
      "models": [
        {
          "id": "z-ai/glm-5.3-flash",
          "name": "GLM 5.3 Flash (Pareto)"
        }
      ]
    }
  }
}

Get started now

Set PARETO_API_KEY and save this as ~/.config/goose/custom_providers/pareto.json. Set GOOSE_PROVIDER=pareto and GOOSE_MODEL, then run Goose with the developer extension.

pareto.jsonJSON

{
  "name": "pareto",
  "engine": "openai",
  "display_name": "Pareto Inference",
  "api_key_env": "PARETO_API_KEY",
  "base_url": "https://api.paretoinference.com/v1/chat/completions",
  "models": [
    {
      "name": "z-ai/glm-5.3-flash"
    }
  ],
  "requires_auth": true,
  "supports_streaming": true
}

Get started now

Set PARETO_API_KEY, then start Aider in your repository. Keep the openai/ prefix and ignore the model names Aider suggests.

TerminalShell

export OPENAI_API_BASE=https://api.paretoinference.com/v1
export OPENAI_API_KEY="$PARETO_API_KEY"
aider --model openai/z-ai/glm-5.3-flash --no-show-model-warnings

Get started now

Put PARETO_API_KEY in ~/.continue/.env and merge this into ~/.continue/config.yaml. The editor extension does not read shell variables.

config.yamlYAML

name: Pareto Inference
version: 1.0.0
schema: v1
models:
  - name: GLM 5.3 Flash (Pareto)
    provider: openai
    model: z-ai/glm-5.3-flash
    apiBase: https://api.paretoinference.com/v1
    apiKey: ${{ secrets.PARETO_API_KEY }}
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use

Get started now

Set PARETO_API_KEY and merge this into ~/.omp/agent/models.yml. Start Oh My Pi with omp --model pareto/z-ai/glm-5.3-flash.

models.ymlYAML

providers:
  pareto:
    baseUrl: https://api.paretoinference.com/v1
    api: openai-completions
    apiKey: PARETO_API_KEY
    authHeader: true
    models:
      - id: z-ai/glm-5.3-flash
        name: GLM 5.3 Flash (Pareto)

Get started now

Set PARETO_API_KEY and add this to ~/.config/crush/crushrc. Select pareto/z-ai/glm-5.3-flash in Crush. Use openai-compat, not openai.

crushrcShell

provider add pareto --type openai-compat \
  --name "Pareto Inference" \
  --base-url "https://api.paretoinference.com/v1" \
  --api-key "$PARETO_API_KEY"

model add pareto/z-ai/glm-5.3-flash --name "GLM 5.3 Flash"

Get started now

Set PARETO_API_KEY, then start Qwen Code. Use --auth-type openai, not openai-responses.

TerminalShell

export OPENAI_API_KEY="$PARETO_API_KEY"
export OPENAI_BASE_URL=https://api.paretoinference.com/v1
export OPENAI_MODEL=z-ai/glm-5.3-flash
qwen --auth-type openai

Get started now

Settings → Model settings → Add provider → Create custom provider. Use Chat completions, the Pareto base URL, and model z-ai/glm-5.3-flash. Clear Image, Video and PDF, and paste this into the model's Reasoning parameter mapping. The default mapping sends fields Pareto rejects.

ZCodeMapping

{
  "reasoning_effort": reasoningLevel == "disabled" ? "none" : reasoningLevel == "enabled" ? "high" : reasoningLevel
}

Get started now

Add this model to your existing config. Keep your proxy access settings.

config.yamlYAML

model_list:
  - model_name: pareto-flash
    litellm_params:
      model: openai/z-ai/glm-5.3-flash
      api_base: https://api.paretoinference.com/v1
      api_key: os.environ/PARETO_API_KEY

Get started now

Add this entry to config.yaml and restart CLIProxyAPI. The base URL keeps /v1. Apps use a key from api-keys, not your Pareto key.

config.yamlYAML

openai-compatibility:
  - name: "pareto"
    base-url: "https://api.paretoinference.com/v1"
    api-key-entries:
      - api-key: "YOUR_PARETO_API_KEY"
    models:
      - name: "z-ai/glm-5.3-flash"

Get started now

Run the gateway from the Docker image; the npx build breaks streaming. Apps send your Pareto key and both x-portkey headers.

TerminalShell

docker run -d -p 127.0.0.1:8787:8787 portkeyai/gateway:latest

curl http://localhost:8787/v1/chat/completions \
  -H "Authorization: Bearer $PARETO_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-custom-host: https://api.paretoinference.com/v1" \
  -d '{"model": "z-ai/glm-5.3-flash", "messages": [{"role": "user", "content": "Say hello."}], "stream": true}'

Get started now

Set PARETO_API_KEY and save this as config.json in the Bifrost app directory. The base URL has no /v1. Apps use the model pareto/z-ai/glm-5.3-flash.

config.jsonJSON

{
  "providers": {
    "pareto": {
      "keys": [
        {
          "name": "pareto",
          "value": "env.PARETO_API_KEY",
          "models": [
            "*"
          ],
          "weight": 1
        }
      ],
      "network_config": {
        "base_url": "https://api.paretoinference.com",
        "default_request_timeout_in_seconds": 300
      },
      "custom_provider_config": {
        "base_provider_type": "openai",
        "allowed_requests": {
          "chat_completion": true,
          "chat_completion_stream": true,
          "list_models": true
        }
      }
    }
  }
}

Get started now

Run NextChat with your key on the server. BASE_URL has no /v1, and CUSTOM_MODELS adds the Pareto model.

TerminalShell

docker run -d -p 3000:3000 \
  -e OPENAI_API_KEY="$PARETO_API_KEY" \
  -e BASE_URL="https://api.paretoinference.com" \
  -e CUSTOM_MODELS="-all,+z-ai/glm-5.3-flash@OpenAI" \
  -e DEFAULT_MODEL="z-ai/glm-5.3-flash@OpenAI" \
  yidadaa/chatgpt-next-web:v2.16.1

Get started now

Run AnythingLLM with the Generic OpenAI provider. Keep Max Tokens at 8192 or more; reasoning counts toward it.

TerminalShell

docker run -d -p 3001:3001 --cap-add SYS_ADMIN \
  -v anythingllm_storage:/app/server/storage \
  -e STORAGE_DIR=/app/server/storage \
  -e LLM_PROVIDER=generic-openai \
  -e GENERIC_OPEN_AI_BASE_PATH=https://api.paretoinference.com/v1 \
  -e GENERIC_OPEN_AI_API_KEY="$PARETO_API_KEY" \
  -e GENERIC_OPEN_AI_MODEL_PREF=z-ai/glm-5.3-flash \
  -e GENERIC_OPEN_AI_MAX_TOKENS=8192 \
  mintplexlabs/anythingllm:1.16.2

Get started now

Add this endpoint to librechat.yaml, set PARETO_API_KEY in .env, and restart. Keep dropParams: Pareto rejects the user field.

librechat.yamlYAML

endpoints:
  custom:
    - name: "Pareto"
      apiKey: ${PARETO_API_KEY}
      baseURL: "https://api.paretoinference.com/v1"
      models:
        default: ["z-ai/glm-5.3-flash"]
        fetch: true
      titleConvo: true
      titleModel: "current_model"
      dropParams: ["user"]

Get started now

Compare

GLM 5.3 Flash API providers and pricesEvery provider's price, context, speed and uptime, cheapest first and checked hourly.

Models

DeepSeek V4.1 FlashOff-peak: $0.105 input, $0.42 output and $0.0021 cached input per 1M tokens MiMo V2.6 Flash$0.126 input, $0.252 output and $0.00252 cached input per 1M tokens

GLM 5.3 Flash API, served on Pareto GPUs.