LLM API Cost Calculator
Estimate what an AI model will cost you each month, and compare Claude, GPT and Gemini side by side.
Your prompt, system instructions, documents and chat history.
The model's reply, including any reasoning tokens.
The same workload on every model
Cheapest first. Prices in US dollars per million tokens (input / output).
How your AI API bill is worked out
Tokens a month × price per million tokens, input and output priced separately.
- 1
Requests a month
1,000 × 30 days
= 30,000 - 2
Count the tokens
30,000 × 1,000
= 30M in
30,000 × 500
= 15M out - 3
Price each side
30M × $2/M
= $60.00 in
15M × $10/M
= $150 out - 4
Add them up
$60.00 + $150
= $210 a month
Read more: how pricing works, a worked example and every price used
AI model APIs charge per token. A token is a chunk of text, about ¾ of an English word, so 1,000 tokens is roughly 750 words. Input tokens (what you send) and output tokens (what the model writes back) are priced separately, and output usually costs several times more.
monthly cost = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000
Worked example
A support bot handling 1,000 chats a day, each with 1,000 input and 500 output tokens, uses 30 million input and 15 million output tokens a month. On Claude Sonnet 5.5 ($2 / $10 per million) that is 30 × 2 + 15 × 10 = $210 a month, or $0.007 per chat.
Ways to cut the bill
- Prompt caching: all three providers charge much less for input they have recently seen, such as a long system prompt that repeats on every request.
- Batch processing: work that can wait up to a day costs half price.
- Smaller models: send simple tasks to a smaller, cheaper model and save the larger ones for hard questions.
- Shorter outputs: because output costs the most, asking for concise answers saves more than trimming the prompt.
Prices used
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Claude Fable 5.1 Anthropic | $10 | $50 |
| Claude Opus 5.5 Anthropic | $4 | $20 |
| Claude Sonnet 5.5 Anthropic | $2 | $10 |
| Claude Haiku 5.5 Anthropic · Prompts up to 100K tokens; $0.50 / $2.50 above that | $0.1 | $0.5 |
| GPT-5.6 Sol OpenAI | $5 | $30 |
| GPT-5.6 Terra OpenAI | $2 | $12 |
| GPT-5.6 Luna OpenAI | $0.2 | $1.2 |
| Gemini 3.1 Pro (preview) Google · Prompts up to 200K tokens | $2 | $12 |
| Gemini 3.8 Flash Google · Rises to $1.5 / $7.5 after 31 Dec 2026 | $0.75 | $3.75 |
| Gemini 3.5 Flash-Lite | $0.3 | $2.5 |
Standard prices from each provider's official pricing page, checked on 9 October 2026. Some models charge more for very long prompts. Prices change often, so confirm with the provider before committing to a budget.