AI & LLM
Token, cost & context tools for LLMs
Gemini API Cost Calculator — Google Gemini 2.5 Pro Pricing
Gemini 2.5 Pro is priced at $1.25/M input tokens (for prompts ≤ 200K tokens) and $10.00/M output tokens, making it the most cost-effective 1M-context flagship model as of 2026-07-03. At the reference workload (1,000 input + 500 output tokens), each API call costs $0.0063: $0.0013 input + $0.005 output. Output tokens cost 8× more than input. At 1,000 calls/day: $6.25/day. Enter your actual token counts and daily volume for a precise monthly estimate.
Reference workload: 1,000 input + 500 output tokens
- Cost per call: $0.0063 (input $0.0013 + output $0.005)
- Per 1,000 calls: $6.25
- Input: $1.25/M (≤200K prompt) | Output: $10.00/M
- Output costs 8× more than input
- Rates as of 2026-07-03 (Gemini 2.5 Pro)
Frequently asked questions
How much does Gemini 2.5 Pro cost per API call?
At 1000 input + 500 output tokens, Gemini 2.5 Pro costs $0.0063/call and $6.25 per 1,000 calls — the lowest cost among the major 1M-context flagship models. Input is $1.25/M for prompts ≤ 200K tokens (rises to $2.50/M for longer prompts); output is $10.00/M. Rates as of 2026-07-03.
When does Gemini 2.5 Pro become cheaper than GPT-5.5 or Claude?
Gemini 2.5 Pro is cheaper than GPT-5.5 and Claude Opus 4.8 at every workload up to 200K input tokens: its input rate ($1.25/M) is 4× cheaper than both GPT-5.5 ($5.00/M) and Claude Opus 4.8 ($5.00/M). Above 200K tokens per prompt, Gemini's input price doubles to $2.50/M — still lower than GPT-5.5 and Claude. Choose Gemini when cost is the primary constraint and you need a 1M context window.