glm-5.3 API — per-token pricing and code examples
Price per 1M tokens
Cache rates apply when the provider reports cache tokens.
90% offAbout this model
glm-5.3 is served through OpenAI Chat Completions, OpenAI Responses, Anthropic Messages. You pay $0.14 per 1M input tokens and $0.44 per 1M output tokens. That is 90% below the official price of $1.40 and $4.40. Cache reads cost $0.014 per 1M tokens when the provider reports cached tokens. It is included in budget packs from $9.99 up.
Where GLM-5.3 fits
GLM-5.3 is a text model from Z.ai built for long, multi-step work. Z.ai lists a context of up to 1M tokens and up to 128K tokens of output in one answer. It accepts text input only, so screenshots, PDFs as images or audio need another model. Z.ai points it at complex coding, long-running agent tasks and security work, which is where a large context and a model that always reasons pay off.
Reasoning is always on
GLM-5.3 thinks before it answers on every request. Turning reasoning off is not supported: the thinking setting only accepts enabled. What you can change is how hard it thinks, with reasoning_effort set to low, high or max. The default is max, which Z.ai recommends for coding. For quick classification, extraction or short replies, low keeps answers faster and shorter.
Cent AI does not change your parameters silently. If your code still sends thinking.type: "disabled" from an older GLM model, the request fails, so switch it to enabled with reasoning_effort: "low" before you change the model name.
The example below uses the /v1/chat/completions format. On /v1/responses the same setting is reasoning.effort, and /v1/messages uses its own thinking block.
{
"model": "glm-5.3",
"reasoning_effort": "low",
"messages": [{ "role": "user", "content": "Summarise this diff" }]
}
What it costs on Cent AI
You pay per token from a prepaid USD balance, with four rates shown in the price box on this page: input, cache read, cache write and output. Reasoning tokens are billed as output, the same way the official price counts them, so a request at max effort can cost noticeably more than the visible answer suggests. If cost matters more than depth, lower the effort first.
Cache rates apply only when the model reports cached tokens in its usage. Cent AI never estimates cache hits on its own. Long agent sessions that resend the same system prompt and files are where the cache read rate helps most.
Using it from your tools
GLM-5.3 is served on all three Cent AI endpoints: /v1/chat/completions, /v1/responses and /v1/messages. That means OpenAI SDKs and Anthropic SDKs both work with only the base URL and key changed. Tool calling and JSON output are supported, which matters for coding agents and assistants that rely on function calls.
Specification
- Context window
- —
- Input and output
- Text
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
- Smallest pack
- $9.99
Latency and error rate per model are on the status page. status.cent-ai.dev
What a request costs
Open the full calculatorCost per request
Estimate
glm-5.3An estimate at price version 3. Your bill comes from the usage the provider reports for each request.
Save $0.3835Code
curl https://api.cent-ai.dev/v1/chat/completions \
-H "Authorization: Bearer $CENT_AI_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "glm-5.3", "messages": [{"role": "user", "content": "Hello"}]}'Set CENT_AI_KEY to a key from the dashboard. OpenAI SDKs use https://api.cent-ai.dev/v1; Anthropic SDKs use https://api.cent-ai.dev.
Price history
Version 3, in effect since Oct 30, 2026.
Effective
per 1M tokens
Inputold $0.07 new $0.14Cache readold $0.007 new $0.014Cache writeold $0.07 new $0.14Outputold $0.22 new $0.44Effective
per 1M tokens
Inputold $0.07 new $0.07Cache readold $0.013 new $0.007Cache writeold $0.07 new $0.07Outputold $0.22 new $0.22
Compare with
- hy4-previewInput$0.46704
- deepseek-v4-proInput$0.165
- gpt-6.1-solInput$0.58
- gpt-6.1-terraInput$0.15
Questions
How much does glm-5.3 cost on Cent AI?
$0.14 per 1M input tokens and $0.44 per 1M output tokens. Cache reads cost $0.014 and cache writes $0.14 per 1M tokens. Each request is rounded up once.
Is there a minimum charge?
A successful request costs at least $0.00002. A request that ends early, because the client left or the output was cut off, pays only for its tokens.
How do I pay?
Top up a prepaid USD balance with QRIS or USDT/USDC, or buy a budget pack once. Nothing renews automatically.
What if the provider does not report usage?
The request is billed from an estimate and marked estimated on the Requests page. An estimate never contains cache tokens.
Which endpoint do I call?
/v1/chat/completions, /v1/responses, /v1/messages. The OpenAI base URL is https://api.cent-ai.dev/v1.
Try glm-5.3 with one key
One prepaid balance for every model. Pay with QRIS or USDT/USDC.