Token302LLM API Cost Calculator
Enter your token usage and compare the real cost across GPT, Claude, Gemini and DeepSeek. The cheapest option is highlighted.
| Model | Input $/1M | Output $/1M | Per request | Total |
|---|---|---|---|---|
Gemini Flash-Lite Google | $0.1 | $0.4 | $0.0018 | $1.80cheapest |
DeepSeek V4 Flash DeepSeek | $0.14 | $0.28 | $0.0020 | $1.96 |
DeepSeek V4 Pro DeepSeek | $0.44 | $0.87 | $0.0061 | $6.14 |
Claude Haiku 4.5 Anthropic | $1 | $5 | $0.0200 | $20.00 |
GPT-5.6 Luna OpenAI | $1 | $6 | $0.0220 | $22.00 |
Gemini 3.5 Flash Google | $1.5 | $9 | $0.0330 | $33.00 |
Gemini 3 Pro Google | $2 | $12 | $0.0440 | $44.00 |
GPT-5.6 Terra OpenAI | $2.5 | $15 | $0.0550 | $55.00 |
Claude Sonnet 5 Anthropic | $3 | $15 | $0.0600 | $60.00 |
Claude Opus 4.8 Anthropic | $5 | $25 | $0.1000 | $100.00 |
GPT-5.6 OpenAI | $5 | $30 | $0.1100 | $110.00 |
Prices in USD per 1M tokens, last verified 2026-07-27. Anthropic figures are first-party API rates; others are from public pricing pages. Provider prices change often and some tiers vary by context length. Treat these as indicative and confirm with the provider before relying on them.
Frequently asked
How is the cost calculated?
Cost is (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price), multiplied by the number of requests. Providers bill input and output tokens at different rates, which is why the split matters.
How many tokens is my text?
Use the Token Counter to get an exact token count for your prompt, then plug it in here. As a rough guide, one token is about four characters of English.
Are these prices current?
We verify prices periodically and show the date they were last checked. Provider pricing changes often and some tiers vary by context length, so confirm with the provider before relying on a number for billing.