Transparent per-token pricing
Venice API pricing is transparent, prepaid, and strictly usage-based. You pay only for the tokens you consume, with no monthly subscriptions or hidden fees.
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Pricing calculator
Usage examples
Summarizing a 50k-token legal document
Input: 50,000 tokens ($0.0075). Output: 2,000 tokens ($0.001). Total: $0.0085.
Running 1,000 parallel code refactors
Input: 10,000 tokens ($0.0015). Output: 5,000 tokens ($0.0025). Total: $0.004 per request.
Long-context creative writing session
Input: 80,000 tokens ($0.012). Output: 16,000 tokens ($0.008). Total: $0.02 for one full context window fill.
Token costs: input vs output
Venice API pricing charges $0.15 per million input tokens and $0.50 per million output tokens. This structure reflects the compute cost of processing your prompt versus generating the response. You can send up to 100,000 tokens in a single request, but the output is capped at 16,000 tokens unless you specify a lower limit.
Errors do not consume credit. If the model fails to return a valid response, you pay nothing. This ensures your prepaid balance is spent only on successful completions. The formula is straightforward: (input_tokens / 1,000,000 * 0.15) + (output_tokens / 1,000,000 * 0.50).
Prepaid credit and crypto payments
We accept only USDT (TRC20) or USDC (Base) for topping up your account. Minimum top-ups start at $20, with a maximum single transaction of $500. Your credit never expires, so you can build a balance over time without worrying about monthly renewal dates. This trial allows you to verify the API works with your stack before committing funds. The prepaid model keeps your spend predictable and eliminates surprise bills from runaway loops.
Bonus credit tiers
Larger top-ups unlock bonus credit that extends your usable balance. Depositing $50 yields a 5% bonus, while $100 adds 10%. The highest tier, a $200 deposit, grants a 15% bonus. These bonuses are added instantly to your account and behave exactly like your base credit.
There are no expiration dates on bonus credit. If you top up $100, you receive $110 total. This structure rewards heavy users who prefer to secure their compute capacity in advance. You can mix bonus credit and base credit in the same requests without any distinction.
Frequently asked questions
Is Venice API pricing competitive compared to other uncensored LLM providers?
Our rates are $0.15 for input and $0.50 for output per million tokens. This is generally lower than many competitors who charge higher output rates. You pay only for what you use, with no minimum monthly spend.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
What happens if I hit my rate limit?
You are limited to 300 requests per minute and 8 concurrent requests per key. Exceeding this results in a 429 error. Your prepaid balance remains intact, and you can retry after the window resets.
Does Venice API pricing include refunds for unused credit?
Credit is non-refundable once deposited. However, it never expires. If you experience a billing error, such as a double charge, our support team will correct the balance on your account.
Retrieve your API key
Register, copy the key, and update your base URL. That’s all.
