Z.AI Open Platform free tier: limits and models

What Z.AI Open Platform's free tier allows

GLM-4.7-Flash and GLM-4.5-Flash are listed at $0 for input, cached input and output on the official pricing table, making them free to call rather than merely discounted. Z.AI does not publish per-model RPM or TPM for these models on the pricing page; the rate limit reference is a separate page and the console is authoritative.

Published limits: Selected models priced at zero
Free access type: Provider free tier
Credit card: Not required
Protocol: OpenAI-compatible at https://api.z.ai/api/paas/v4
Lifecycle: Active
Sources reviewed: 2026-07-25

The free Flash models sit alongside paid GLM models on the same key, so watch which model ID you send to avoid unintended charges.

Where Z.AI Open Platform sits in this catalog

Z.AI Open Platform is one of 15 provider free tier entries among the 25 providers detailed here. It asks for no credit card, which is true of 23 of the 25. It publishes no fixed request count, as 16 of the 25 do not.

Compared with	Published limits	Card	Endpoint
Z.AI Open Platform (this page)	Selected models priced at zero	Not required	`api.z.ai`
Novita AI	Selected models priced at zero	Not required	`api.novita.ai`
Mistral La Plateforme	Enforced but not published	Not required	`api.mistral.ai`
Alibaba Cloud Model Studio	Published per model	Not required	`dashscope-intl.aliyuncs.com`

Models Z.AI Open Platform lists as free

GLM-4.7-Flash — GLM, also free at 3 other providers here
GLM-4.5-Flash — GLM, also free at 3 other providers here

3 other providers here also host the GLM family on free terms, and the terms are not the same: SiliconFlow, Cerebras Inference, Chutes.

Checking a Z.AI Open Platform key

The CORS preflight echoes the requesting origin and allows an Authorization header, so a browser can call this endpoint directly. That was measured against https://api.z.ai on 2026-07-25.

So a key can be checked in the browser checker without installing anything. If you would rather not paste a key into a web page, this does the same thing:

#!/usr/bin/env sh
set -eu

: "${ZAI_API_KEY:?Set ZAI_API_KEY to a key you created yourself at the provider console}"

# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
  --write-out '\nHTTP %{http_code}\n' \
  --header "Authorization: Bearer $ZAI_API_KEY" \
  'https://api.z.ai/api/paas/v4/models'

Using a Z.AI Open Platform key

Z.AI Open Platform serves the OpenAI chat completions protocol at https://api.z.ai/api/paas/v4. Point any client that accepts a custom base URL at it, and let the client read the key from ZAI_API_KEY so the value never lands in a config file:

# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "GLM-4.7-Flash"
model_provider = "zai"

[model_providers.zai]
name = "Z.AI Open Platform OpenAI-compatible gateway"
base_url = "https://api.z.ai/api/paas/v4"
env_key = "ZAI_API_KEY"
wire_api = "responses"

Questions about the Z.AI Open Platform free tier

Does Z.AI Open Platform ask for a credit card?

No. Z.AI Open Platform is one of 23 providers here that hand out free access without a card, so the only cost of trying it is the signup.

What are Z.AI Open Platform's free-tier rate limits?

Z.AI Open Platform publishes no single free-tier number: its limits are selected models priced at zero. This catalog leaves that blank rather than guessing a figure.

What happens when a Z.AI Open Platform key hits the limit?

The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.

Is the Z.AI Open Platform free tier going away?

Nothing in Z.AI Open Platform's own documentation says so as of 2026-07-25. The free Flash models sit alongside paid GLM models on the same key, so watch which model ID you send to avoid unintended charges.

Can Z.AI Open Platform be used with Codex, Cline, or Continue?

Yes. Z.AI Open Platform serves the OpenAI chat completions protocol at https://api.z.ai/api/paas/v4, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.

Official sources

Z.AI pricinghttps://docs.z.ai/guides/overview/pricing
Z.AI rate limitshttps://docs.z.ai/api-reference/rate-limit
OpenAI Python SDK with Z.AIhttps://docs.z.ai/guides/develop/openai/python

Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.