Inference platform that routes AI workloads across GPUs and serves open-source models through an OpenAI-compatible API.
Z.AI Developer Platform
Pay-per-token API for Z.AI's GLM models, plus a monthly GLM Coding Plan that powers coding agents such as Claude Code.
What is Z.AI Developer Platform?
The Z.AI Developer Platform is where developers get API access to the GLM family of models, with GLM-5.3 and GLM-5.3-Flash as the current main entries. Billing is by token: the pricing page lists input, cached input and output rates per million tokens for text, vision, image, video and audio models, plus a per-use charge for built-in web search. Some smaller models, including GLM-4.7-Flash and GLM-4.6V-Flash, are listed as free. For people who mostly want AI inside a coding tool, the separate GLM Coding Plan is a monthly subscription that works with more than 20 agent tools such as Claude Code, Codex, OpenCode and Cline, using a credit allowance that resets every five hours and every week. A Team Plan adds seats, a central admin view and spend controls. The documentation says the Coding Plan starts at 18 USD per month, and API prices are published in USD.
Use cases
- Call GLM models from your own application
- Power Claude Code or Codex with a flat coding plan
- Add web search to model calls
- Generate images and short videos through the API
- Transcribe audio with GLM-ASR-2512
- Read text from scans with the OCR model
- Give a dev team shared seats and spend limits
Who it's for
Why use Z.AI Developer Platform
- Per-token pricing is published for every model, so you can estimate API spend before building.
- A flat monthly Coding Plan lets one subscription cover several coding agents instead of paying per token.
- Cheaper Flash and free models are available when a task does not need the flagship model.
- Team Plan keeps billing and invoices in one place and excludes code and prompts from model training by default.
- Spend and quota progress can be checked in the console, so surprises are easier to avoid.
Z.AI Developer Platform features
- GLM-5.3 and GLM-5.3-Flash text models with cached-input pricing
- Vision, OCR, image, video and audio models priced per token, image or video
- Built-in web search billed per use
- GLM Coding Plan with Lite, Pro and Max tiers
- Works with 20+ agent tools including Claude Code, Codex and OpenCode
- Web Search, Web Reader and Zread MCP tools included in the Coding Plan
- Team Plan with seat management, usage insights and per-member spend limits
- Off-peak usage charged at 50% of the standard credit rate on coding plans
- Free models such as GLM-4.7-Flash and GLM-4.6V-Flash
Z.AI Developer Platform integrations
How to get started with Z.AI Developer Platform
- Register on the platform and create an API key.
- Choose a model such as GLM-5.3 or GLM-5.3-Flash from the pricing list.
- Call it through the HTTP API or an SDK, paying per million tokens used.
- Or subscribe to the GLM Coding Plan and connect it to a supported agent tool.
- Watch quota and token use on the usage pages and adjust the plan if needed.
Z.AI Developer Platform limitations
- Coding Plan quota can only be used in officially supported tools, not for general API calls
- Coding plans have both a 5-hour and a weekly credit limit
- Team Plan needs a minimum of 2 seats and mixed seat types are not supported
- Peak hours are Monday to Friday, 14:00 to 18:00 Singapore time, when standard credit rates apply
Z.AI Developer Platform pricing
Yes, Z.AI Developer Platform has a free plan. Paid plans start at $18 per month, according to the official pricing page on .
Z.AI Developer Platform plans
GLM-5.3 API
$1.4 input /$4.4 output per 1M tokens
Pay as you go; cached input $0.26 per 1M tokens
- Flagship text model
- Cached input discounted
- Prices listed in USD
GLM-5.3-Flash API
$0.15 input /$0.50 output per 1M tokens
Pay as you go; cached input $0.03 per 1M tokens
- Lower-cost Flash model
- Cached input discounted
GLM-5.3-FlashX API
$0.37 input /$1.25 output per 1M tokens
Pay as you go; cached input $0.075 per 1M tokens
- Middle tier between Flash and GLM-5.3
Free models
Free
GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash
- Input, cached input and output listed as free
GLM Coding Plan
From 18 USD per month
Lite, Pro and Max tiers
- Lite: 2,000 credits per 5 hours, 10,000 per week
- Pro: 12,000 credits per 5 hours, 60,000 per week
- Max: 28,000 credits per 5 hours, 140,000 per week
- Works with 20+ agent tools
GLM Coding Team Plan
Price on vendor site
Per seat, minimum 2 seats
- Standard Seat: 15,000 credits per 5 hours, 66,000 per week
- Premium Seat: 35,000 credits per 5 hours, 155,000 per week
- Central seat and spend management
Plans as listed on the official pricing page on . Prices can change and may vary by country or exclude tax. Check the official pricing page.
Z.AI Developer Platform alternatives
The main Z.AI Developer Platform alternatives listed on Debuly are OpenAI API, DeepSeek API, Alibaba Cloud Model Studio, OpenRouter, MiniMax and MiniMax API Platform. The table compares pricing and platforms; order is A–Z.
| Tool | Pricing | Starting price | Platforms |
|---|---|---|---|
| Z.AI Developer Platform | Freemium | $18/mo | API, Web |
| Alibaba Cloud Model Studio | Paid | $6/mo | Web, API |
| DeepSeek API | Paid | — | API |
| MiniMax | Paid | CN¥49/mo | Web, API, CLI |
| MiniMax API Platform | Paid | $22/mo | API, Web, CLI |
| OpenAI API | Paid | $0.1, usage-based | API, Web |
| OpenRouter | Freemium | — | Web, API |
Alibaba Cloud Model Studio
Alibaba Cloud platform giving developers API access to Qwen and partner models for text, image, video and speech, billed per token or by subscription.
DeepSeek API
Pay-per-token API for DeepSeek V4 models with a 1M-token context, thinking modes, tool calls and OpenAI or Anthropic formats.
MiniMax
AI company with M3 language models, H3 video, Speech 2.8 and agent products, sold by API pay-as-you-go or Token Plan subscription.
MiniMax API Platform
Developer platform to call MiniMax M3 language, H3 video, speech and image models by API, pay-as-you-go or with a Token Plan.
OpenAI API
Developer API for OpenAI's GPT models, image generation, realtime voice and transcription, priced per million tokens with batch and flex options.
OpenRouter
Unified OpenAI-compatible API for 500+ AI models with provider fallbacks, pay-as-you-go credits and a free tier
FreemiumVisit OpenRouter (official site)
Z.AI Developer Platform FAQ
What is the Z.AI Developer Platform?
It is the developer side of Z.AI, offering API access to the GLM models, a per-token pricing list, and the GLM Coding Plan subscription for coding agents.
How much does the Z.AI API cost?
Prices are per 1M tokens in USD. GLM-5.3 is $1.4 input and $4.4 output, GLM-5.3-Flash is $0.15 input and $0.50 output, and GLM-5.3-FlashX is $0.37 input and $1.25 output. Web search costs $0.01 per use.
Is there a free plan or free models?
Yes, some models are listed as free, including GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash. Other models are billed per token.
How much is the GLM Coding Plan?
The documentation says plans start at 18 USD per month, with Lite, Pro and Max tiers. Lite gives 2,000 credits per 5 hours and 10,000 per week; Pro gives 12,000 and 60,000; Max gives 28,000 and 140,000.
Which tools work with the GLM Coding Plan?
The plan is documented for ZCode, Claude Code, Codex, OpenCode, AutoClaw, OpenClaw and Cline, among more than 20 supported agent tools. Use outside supported tools is not allowed.
Does Z.AI offer a team plan?
Yes. The GLM Coding Team Plan is sold by seat with a two-seat minimum, in Standard and Premium seat types, and adds seat management, usage insights, overage billing and centralized invoicing.
What are alternatives to the Z.AI Developer Platform?
Other model API platforms include the OpenAI API, Anthropic API, DeepSeek API, Kimi API and Alibaba Cloud Model Studio.
Sources & verification
Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.
| Source | Type | Accessed |
|---|---|---|
| docs.z.ai/guides/overview/quick-start | official | |
| docs.z.ai/guides/overview/pricing | pricing | |
| docs.z.ai/devpack/overview | pricing | |
| docs.z.ai/devpack/teamplan | docs | |
| docs.z.ai/devpack/faq | docs |
Image credits
- Logo: from docs.z.ai · fetched · Vendor trademark, used only to identify the product; removed on request
- Cover: none collected yet, so a generated tile is shown.
Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.
More in Developer platforms 4
All developer platforms toolsPlatform for testing, tracing and governing AI systems, with CI/CD evals, production monitoring and guardrails.
FreemiumBackend platform for apps and AI agents with a JSON document database, vector search, identity, storage and scoped agent keys.
PaidGovernance layer between AI agents and company systems that connects MCP servers, filters risky data, scopes access by role and logs every tool call.
Paid
