Gemini 3.5 Flash (medium) Token Counter & Cost Calculator
Count tokens for Gemini 3.5 Flash (medium) and estimate the exact API cost — $1.50
per 1M input tokens, $9.00 per 1M output tokens — using a real
o200k_base BPE tokenizer. Everything runs in your browser; nothing is uploaded.
Counts are exact for OpenAI models (o200k_base is GPT-4o/4.1/5's tokenizer). For Claude, Gemini and other vendors — whose tokenizers are not public — treat the count as a close estimate (typically within ±15%).
Model price data failed to load — cost estimates are unavailable right now. Token counts above still work; try reloading the page.
Cost of this text across popular models
| Model | Input $/1M | Output $/1M | This text (input) | +500 output tokens |
|---|
Close estimate (±15%): Google does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation.
Cost lookup — Gemini 3.5 Flash (medium)
| Tokens | Cost on Gemini 3.5 Flash (medium) |
|---|---|
| 1K input tokens | 0.15¢ |
| 10K input tokens | $0.0150 |
| 100K input tokens | $0.1500 |
| 1M input tokens | $1.50 |
| 1K output tokens | 0.9¢ |
| 10K output tokens | $0.0900 |
FAQ
How accurate is the Gemini 3.5 Flash (medium) token count?
Close estimate (±15%): Google does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation. Paste your own text above to see the exact number for your prompt.
How is Gemini 3.5 Flash (medium) API cost calculated?
Cost = (input tokens ÷ 1,000,000) × $1.50 + (output tokens ÷ 1,000,000) × $9.00 — Gemini 3.5 Flash (medium)'s official per-1M-token prices from Artificial Analysis.
Does this cover every reasoning-effort tier of Gemini 3.5 Flash (medium)?
Pricing shown is for the merged representative tier. Gemini 3.5 Flash (medium) groups 3 reasoning-effort variants: Gemini 3.5 Flash (medium), Gemini 3.5 Flash (high), Gemini 3.5 Flash (minimal).
See full Gemini 3.5 Flash (medium) pricing & benchmarks, or the main token counter for every model.