Pricing

What a prompt costs,
model by model.

Same call, every major model, list prices per million tokens. Pick a call size and a monthly budget and see the real numbers instead of the marketing ones.

Typical call size

Medium means a page of context: 800 tokens in, 700 out.

$20

Cost of one medium call

Gemini Flashcheapest

Google · $0.1/M in · $0.4/M out

$0.00036

The cheapest serious option, with a very large context window.

55,555 calls per budget · 1.5× cheaper than GPT-4o mini

Llama 70B (hosted)

Meta / hosts · $0.3/M in · $0.4/M out

$0.00052

Open weights via a host — cheap output, quality varies by provider.

38,461 calls per budget · 1.0× cheaper than GPT-4o mini

GPT-4o mini

OpenAI · $0.15/M in · $0.6/M out

$0.00054

The default workhorse: fast, cheap, good enough for most everyday prompts.

37,037 calls per budget · the ChatGPT baseline

GPT-4.1 mini

OpenAI · $0.4/M in · $1.6/M out

$0.00144

A step up in instruction-following for a few times the price of 4o mini.

13,888 calls per budget · 2.7× GPT-4o mini

Claude Haiku

Anthropic · $0.8/M in · $4/M out

$0.00344

Quick and tidy writer; strong at following formatting rules.

5,813 calls per budget · 6.4× GPT-4o mini

GPT-4.1

OpenAI · $2/M in · $8/M out

$0.00720

Long-context, high-accuracy work: contracts, code, careful reasoning.

2,777 calls per budget · 13.3× GPT-4o mini

Gemini Pro

Google · $1.25/M in · $10/M out

$0.00800

Google's reasoning tier, priced close to GPT-4o on output.

2,500 calls per budget · 14.8× GPT-4o mini

GPT-4o

OpenAI · $2.5/M in · $10/M out

$0.00900

The flagship multimodal model — text, images and audio in one place.

2,222 calls per budget · 16.7× GPT-4o mini

Claude Sonnet

Anthropic · $3/M in · $15/M out

$0.0129

A favourite for long-form drafting and code review; the priciest here.

1,550 calls per budget · 23.9× GPT-4o mini

USD list prices per 1M tokens. Published rates change often — use these as a planning estimate, not a quote.

How to read this

Output tokens are the expensive half

Most models charge three to five times more for the answer than the prompt. Capping reply length with max_tokens saves more money than trimming your prompt.

ChatGPT is not the cheapest, and rarely the dearest

A medium call on GPT-4o mini lands at $0.00054. Gemini Flash undercuts it slightly; Claude Sonnet costs many times more for the same words.

Mixing models is normal

Route the easy 90% — classification, tidy-ups, summaries — to a mini model, and reserve a flagship for the calls where being wrong is expensive.

Your bill is dominated by history

In a chat app you resend the whole conversation every turn, so cost grows with the square of the thread length. Summarise old turns and the curve flattens.

Next steps

Model the numbers against your own traffic with the calculator on the API guide, or read the FAQ on quotas and rate limits before you scale up.