Models · Z.ai

GLM-5.3 API, 1.8x less than the official price

GLM-5.3 costs $0.77 per million input tokens and $2.42 per million output tokens on Kontinent AI. Z.ai's official price is $1.40 and $4.40, so you pay 1.8x less (45% less).

1.8x less chat messages glm-5.3
Get an API key Try Claude Haiku 4.5 first No top-up needed
  • No subscription
  • Pay only for requests that get an answer
  • Your balance does not expire
  • Sign in with Google or email

Price per million tokens

Tokens Official price Kontinent AI
Input Official price $1.40 $0.77
Output Official price $4.40 $2.42
Cached input Official price $0.26 $0.143

USD per million tokens. The official price is Z.ai's, on its price page. Ours is that price times 0.55, for every kind of token. This model thinks before it answers. The thinking is billed as output tokens, at the same multiple.

What jobs cost with GLM-5.3

Job Official price, then ours
1,000 support-bot replies 1,500 tokens in and 500 out, each Official price $4.30 , Kontinent AI $2.37
One coding-agent session 200,000 tokens in and 20,000 out, uncached Official price $0.37 , Kontinent AI $0.20
1,000 document summaries 4,000 tokens in and 300 out, each Official price $6.92 , Kontinent AI $3.81

Each job is priced the way the API bills it. Work out your monthly bill.

Run GLM-5.3 for $0.20 a session, not $0.37

The same GLM-5.3, through one API key. Change the base URL and the key, and keep your code. You see what every request cost and what you saved.

Get an API key Try Claude Haiku 4.5 first No top-up needed
  • No subscription
  • Pay only for requests that get an answer
  • Your balance does not expire
  • Sign in with Google or email

Your monthly bill

Enter what you spend at the official price and see it on Kontinent AI, in your currency.

1.8x less than the official price

At the official price
$100.00
With Kontinent AI
$55.00
You keep
$45.00

The model

Maker
Z.ai
Model id
glm-5.3
Context window
1,000,000 tokens
Weights
Open weights
Beyond plain chat
Tool calling, Structured output (JSON schema)
Speed, measured by us
not measured yet

Use GLM-5.3

  • POST /v1/chat/completions: the OpenAI SDKs, OpenCode, most OpenAI-compatible tools.
  • POST /v1/messages: Claude Code, the Anthropic SDKs.
terminal 
curl https://api.kontinentai.com/v1/chat/completions \
  -H "Authorization: Bearer $KONTINENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3", "messages": [{"role": "user", "content": "Hello"}]}'
Claude Code 
export ANTHROPIC_BASE_URL=https://api.kontinentai.com
export ANTHROPIC_AUTH_TOKEN=$KONTINENT_API_KEY
claude --model glm-5.3

Setup for each tool: Claude Code, Codex, OpenCode, OpenAI SDK, Anthropic SDK.

Questions

How much does the GLM-5.3 API cost?

GLM-5.3 costs $0.77 per million input tokens and $2.42 per million output tokens on Kontinent AI. Z.ai's official price is $1.40 and $4.40, so you pay 1.8x less (45% less). Cached input is $0.143 per million tokens, against $0.26 official.

Is it the same GLM-5.3?

Yes. We send your request to the model you name, and nothing else. We check the name of the model that answered on each response.

What does a coding-agent session cost with GLM-5.3?

A session of 200,000 input tokens and 20,000 output tokens, uncached, costs $0.20 on Kontinent AI and $0.37 at Z.ai's official price.

Can I use GLM-5.3 with OpenCode or Claude Code?

Yes. Point OpenCode, Claude Code at Kontinent AI by changing the base URL and the key. The setup pages in the docs show each one.

What is the context window of GLM-5.3?

1M tokens (1,000,000), as Z.ai publishes it.

Compare GLM-5.3

Other models

Start with GLM-5.3 today

GLM-5.3 is 45% less than Z.ai's official price on every token. Top up a prepaid balance and call it from the tools you already use.

Get an API key Try Claude Haiku 4.5 first No top-up needed
  • No subscription
  • Pay only for requests that get an answer
  • Your balance does not expire
  • Sign in with Google or email