AI Prompt Cost Comparator

Enter how many input and output tokens a request uses and how many requests you expect, and see the cost across current model price presets side by side, cheapest first. Add your own models and prices for anything not listed, such as negotiated rates or a new release.

Processed locally in your browser. Your data is not uploaded to our servers.

Prompt, context and any documents sent with each request.

The reply you expect back.

Total requests to price, for example one day or one month.

Optional. Applies each model’s cached-input price to this share of the input.

Your own models

Fill in a row to add a model with its own prices (per million tokens, in USD). Empty rows are ignored.

Custom model 1

Custom model 2

Result

Estimate

Lowest total: gpt-6-luna, 0.45 USD · Highest total: gpt-6-astra, 45.00 USD · Spread: 100×

Prices are in USD per million tokens. Rows are sorted from the lowest total cost.
ModelInput priceOutput priceCost per requestTotal costCompared with the lowest
gpt-6-luna OpenAI0.10.50.00045 USD0.45 USDLowest
Gemini 2.5 Flash GoogleGoogle currently limits access to the Gemini 2.5 models to users who have used them before. The model is not deprecated and no shutdown date is announced. Google’s model page0.32.50.00185 USD1.85 USD4.11× (+1.40 USD)
gpt-5.4-mini OpenAI0.754.50.00375 USD3.75 USD8.33× (+3.30 USD)
Claude Haiku 4.5 Anthropic150.0045 USD4.50 USD10× (+4.05 USD)
Claude Sonnet 5.5 Anthropic2100.009 USD9.00 USD20× (+8.55 USD)
gpt-6.1-sol OpenAI2100.009 USD9.00 USD20× (+8.55 USD)
Gemini 3.1 Pro Preview GooglePrice for prompts up to 200,000 tokens; longer prompts cost more.2120.01 USD10.00 USD22.22× (+9.55 USD)
Claude Opus 5.5 Anthropic4200.018 USD18.00 USD40× (+17.55 USD)
Claude Fable 5.1 Anthropic10500.045 USD45.00 USD100× (+44.55 USD)
gpt-6-astra OpenAI10500.045 USD45.00 USD100× (+44.55 USD)

Preset prices are standard pay-as-you-go API prices in USD per million tokens, read from each provider’s pricing page and last verified 2026-10-19. Providers change prices often: check the source and use your own row when in doubt.

Price sources:

Examples

Worked examples using the presets above (no caching):

WorkloadInput tokensOutput tokensRequestsLowest totalHighest total
Chat replies1,00030010,000gpt-6-luna: 2.50 USDgpt-6-astra: 250.00 USD
Questions over retrieved documents8,0005001,000gpt-6-luna: 1.05 USDgpt-6-astra: 105.00 USD
Summarising long documents50,0001,000100gpt-6-luna: 0.55 USDgpt-6-astra: 55.00 USD

Formula & Methodology

Given your token counts and the prices, the arithmetic is exact:

cost per request = input tokens × input price ÷ 1,000,000 + output tokens × output price ÷ 1,000,000with caching: cached share of the input uses the cached-input price insteadtotal cost = cost per request × number of requests

Good to know

  • The same text is not the same number of tokens everywhere: every provider has its own tokenizer, and Anthropic documents about 30% more tokens for its newer models. Compare with each provider’s own token count when accuracy matters.
  • Standard pay-as-you-go prices only. Batch, flex and priority tiers, cache-write and storage fees, long-prompt tiers, tool or search charges and taxes are not included.
  • The cached-input price is the price for reading from the cache.
  • The cheapest model is not automatically the best value: quality, speed, limits and reliability differ.
  • Preset prices are conveniences, dated and sourced. Use your own rows for negotiated prices or new models.

How to Use

  1. Enter the input and output tokens of a typical request and the number of requests.
  2. Optionally enter the share of input served from cache.
  3. Add your own models and prices if something is missing.
  4. Read the table: it is sorted from the lowest total cost and shows how much more each option costs.

Frequently Asked Questions

How is the cost of an AI request calculated?

Providers charge per million tokens, with one price for input and a higher one for output. The cost is input tokens × input price plus output tokens × output price, each divided by one million, multiplied by the number of requests.

Are the preset prices up to date?

They were read from each provider’s pricing page on the date shown and linked as sources. Prices and model names change often, so check the source before relying on them and use a custom row for anything newer.

Why does the cheapest model not always win?

Price per token ignores quality, speed and how many tokens the model needs to get a good answer. A cheaper model that needs retries or longer prompts can cost more overall.

Why do different providers count different token numbers for the same text?

Each provider uses its own tokenizer, so the same text produces different counts. Anthropic, for example, documents that its newer models produce about 30% more tokens than earlier ones for the same text.

Can I compare a model that is not listed?

Yes. Fill in a row under “Your own models” with its name and its input, output and optional cached-input prices per million tokens, and it joins the comparison.

Last updated: