Worked examples
Code refactoring in a single file
A 20,000 token input prompt asking for a refactor of a Python module, resulting in a 2,000 token response. Calculation: (20,000 / 1,000,000 * $0.15) + (2,000 / 1,000,000 * $0.50) = $0.003 + $0.001 = $0.004.
Long-context document summarization
Processing a 60,000 token document (near the context limit) to generate a 4,000 token summary. Calculation: (60,000 / 1,000,000 * $0.15) + (4,000 / 1,000,000 * $0.50) = $0.009 + $0.002 = $0.011.
High-volume classification task
Batch processing 100 short requests, each with 500 input tokens and 100 output tokens. Per request cost: (500 / 1,000,000 * $0.15) + (100 / 1,000,000 * $0.50) = $0.000075 + $0.00005 = $0.000125. Total for 100 requests: $0.0125.
Token Pricing
Our glm api uses straightforward per-token pricing. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You pay strictly for the tokens processed in each request.
Prepaid Credit
Load credit once and use it as needed. Your balance decreases only when tokens are successfully processed. Errors and refusals do not consume credit. Credits never expire, so you can top up when convenient.
Crypto Top Up
We accept top-ups by crypto (USDT on TRC20, USDC on Base). Minimum top-up is $20, maximum is $500. You receive a +5% bonus from $50, +10% from $100, and +15% from $200. No PayPal required.
Billing & Refunds
Credit is non-refundable but lasts indefinitely. If you experience a double charge or billing error, contact Support. Your trial credit is $0.50 for 7 days. Claim this credit with one click on your API key page.
Limits and what is included
Same price for every feature — function calling and JSON mode cost nothing extra.
| Spec | Value |
|---|---|
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Structured output | JSON object mode via response_format json_object |
| Completion length | prompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap |
| Context window | 100,000 tokens, input and output combined |
| Parallel requests | up to 8 in parallel per key |
| Rate limit | 300/min per key |
| Credit expiry | paid credit never expires, no subscription |
| Volume bonus | +5% from $50, +10% from $100, +15% from $200 |
| Payment | USDT (TRC20) or USDC (Base), any whole amount from $20 to $500 |
| Token prices | $0.15 per 1M input tokens · $0.50 per 1M output tokens |
| Free trial | $0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
Questions and answers
Do I need a credit card to start?
No. You can sign up with Google or email/password. New accounts receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No card is required to start.
What happens if I use more tokens than my balance?
Requests will fail until you top up. You only pay for tokens that are successfully processed. Errors and refusals do not deduct from your balance.
Can I get a refund if I top up too much?
Credit is non-refundable but does not expire. If you made a mistake, such as a double charge, please contact our Support team to fix it.
How do I top up my account?
Use USDT on TRC20 or USDC on Base. Amounts must be whole numbers between $20 and $500. You can top up as many times as you like.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
