Prompt Cost Calculator
Updated Free mock REST & WebSocket APIs
Paste the prompt you're about to ship — system message, instructions, examples and context — and see what one call costs on every major model, priced with each model's own tokenizer. Add expected output and traffic to see the monthly total.
| Cached /1M | |||||
|---|---|---|---|---|---|
Ministral 3 8Bcheapest Mistral In $0.15 · Out $0.15 /1M · 256K | $0.15 | — | $0.15 | 256K | $2.74 |
gpt-oss-20b OpenAI · Groq In $0.075 · Out $0.30 /1M · 128K Open-weight model; price shown is Groq's. | $0.075 | — | $0.30 | 128K | $4.72 1.7× cheapest |
GPT-5 nano OpenAI In $0.05 · Out $0.40 /1M · 400K | $0.05 | $0.005 | $0.40 | 400K | $6.15 2.2× cheapest |
Gemini 2.5 Flash-Lite Google In $0.10 · Out $0.40 /1M · 1M Gemini 2.5 models are limited to existing users. | $0.10 | $0.01 | $0.40 | 1M | $6.31 2.3× cheapest |
GPT-6 Luna OpenAI In $0.10 · Out $0.50 /1M · 1.05M | $0.10 | $0.01 | $0.50 | 1.05M | $7.79 2.8× cheapest |
Claude Haiku 5.5 Anthropic In $0.10 · Out $0.50 /1M · 1M Prompts over 100,000 tokens are billed at $0.50 / $2.50 per 1M for the whole request. | $0.10 | $0.01 | $0.50 | 1M | $7.94 2.9× cheapest |
GPT-4o mini OpenAI In $0.15 · Out $0.60 /1M · 128K | $0.15 | $0.075 | $0.60 | 128K | $9.44 3.5× cheapest |
gpt-oss-120b OpenAI · Groq In $0.15 · Out $0.60 /1M · 128K Open-weight model; price shown is Groq's. | $0.15 | — | $0.60 | 128K | $9.44 3.5× cheapest |
Mistral Small 4 Mistral In $0.15 · Out $0.60 /1M · 256K | $0.15 | — | $0.60 | 256K | $9.49 3.5× cheapest |
Codestral Mistral In $0.30 · Out $0.90 /1M · 128K | $0.30 | — | $0.90 | 128K | $14.47 5.3× cheapest |
GPT-5.6 Luna OpenAI In $0.20 · Out $1.20 /1M · 1.05M | $0.20 | $0.02 | $1.20 | 1.05M | $18.59 6.8× cheapest |
Llama 3.3 70B Meta (Llama) · Together AI In $1.04 · Out $1.04 /1M · 128K | $1.04 | — | $1.04 | 128K | $18.81 6.9× cheapest |
DeepSeek Flash DeepSeek In $0.30 · Out $1.20 /1M · 1M Peak-hour price. Off-peak is 50% off: $0.15 / $0.60. | $0.30 | $0.006 | $1.20 | 1M | $18.97 6.9× cheapest |
GPT-5.4 nano OpenAI In $0.20 · Out $1.25 /1M · 400K | $0.20 | $0.02 | $1.25 | 400K | $19.34 7.1× cheapest |
Gemini 3.1 Flash-Lite Google In $0.25 · Out $1.50 /1M · 1M | $0.25 | $0.025 | $1.50 | 1M | $23.27 8.5× cheapest |
GPT-4.1 mini OpenAI In $0.40 · Out $1.60 /1M · 1.05M | $0.40 | $0.10 | $1.60 | 1.05M | $25.18 9.2× cheapest |
GPT-5 mini OpenAI In $0.25 · Out $2 /1M · 400K | $0.25 | $0.025 | $2 | 400K | $30.73 11× cheapest |
Grok Build 0.1 xAI In $1 · Out $2 /1M · 256K | $1 | $0.20 | $2 | 256K | $33.09 12× cheapest |
Mistral Large 4 Mistral In $0.68 · Out $2.09 /1M · 1M Sale price; list price is $1.36 / $4.18 per 1M. | $0.68 | $0.07 | $2.09 | 1M | $33.55 12× cheapest |
Gemini 2.5 Flash Google In $0.30 · Out $2.50 /1M · 1M Gemini 2.5 models are limited to existing users. | $0.30 | $0.03 | $2.50 | 1M | $38.43 14× cheapest |
Gemini 3.5 Flash-Lite Google In $0.30 · Out $2.50 /1M · 1M | $0.30 | $0.03 | $2.50 | 1M | $38.43 14× cheapest |
Grok 4.3 xAI In $1.25 · Out $2.50 /1M · 1M | $1.25 | $0.20 | $2.50 | 1M | $41.36 15× cheapest |
Gemini 3.8 Flash Google In $0.75 · Out $3.75 /1M · 1M Price rises to $1.50 / $7.50 per 1M on Jan 1, 2027. Explicit cache storage is billed per hour. | $0.75 | $0.075 | $3.75 | 1M | $58.57 21× cheapest |
DeepSeek V4 Pro DeepSeek In $1.32 · Out $3.96 /1M · 1M Peak-hour price. Off-peak (most hours and weekends) is 50% off: $0.66 / $1.98. | $1.32 | $0.044 | $3.96 | 1M | $63.68 23× cheapest |
o4-mini OpenAI In $1.10 · Out $4.40 /1M · 200K | $1.10 | $0.275 | $4.40 | 200K | $69.23 25× cheapest |
GPT-5.4 mini OpenAI In $0.75 · Out $4.50 /1M · 400K | $0.75 | $0.075 | $4.50 | 400K | $69.70 25× cheapest |
Claude Haiku 4.5 Anthropic In $1 · Out $5 /1M · 200K | $1 | $0.10 | $5 | 200K | $78.39 29× cheapest |
Grok 4.7 xAI In $2 · Out $6 /1M · 500K | $2 | $0.50 | $6 | 500K | $96.18 35× cheapest |
Mistral Medium 3.5 Mistral In $1.50 · Out $7.50 /1M · 256K | $1.50 | — | $7.50 | 256K | $117.36 43× cheapest |
GPT-4.1 OpenAI In $2 · Out $8 /1M · 1.05M | $2 | $0.50 | $8 | 1.05M | $125.88 46× cheapest |
o3 OpenAI In $2 · Out $8 /1M · 200K | $2 | $0.50 | $8 | 200K | $125.88 46× cheapest |
GPT-5 OpenAI In $1.25 · Out $10 /1M · 400K | $1.25 | $0.125 | $10 | 400K | $153.68 56× cheapest |
Gemini 2.5 Pro Google In $1.25 · Out $10 /1M · 1M Gemini 2.5 models are limited to existing users. | $1.25 | $0.125 | $10 | 1M | $153.86 56× cheapest |
GPT-6 Sol OpenAI In $2 · Out $10 /1M · 1.05M | $2 | $0.20 | $10 | 1.05M | $155.88 57× cheapest |
GPT-6.1 Sol OpenAI In $2 · Out $10 /1M · 1.05M | $2 | $0.10 | $10 | 1.05M | $155.88 57× cheapest |
Gemini 4 Argon Google In $2 · Out $10 /1M · 1M Price rises to $4 / $20 per 1M on Dec 1, 2026. Caching is implicit only. | $2 | $0.10 | $10 | 1M | $156.18 57× cheapest |
GPT-4o OpenAI In $2.50 · Out $10 /1M · 128K | $2.50 | $1.25 | $10 | 128K | $157.35 58× cheapest |
Claude Sonnet 5 Anthropic In $2 · Out $10 /1M · 1M | $2 | $0.20 | $10 | 1M | $158.82 58× cheapest |
Claude Sonnet 5.5 Anthropic In $2 · Out $10 /1M · 1M | $2 | $0.10 | $10 | 1M | $158.82 58× cheapest |
GPT-5.6 Terra OpenAI In $2 · Out $12 /1M · 1.05M | $2 | $0.20 | $12 | 1.05M | $185.88 68× cheapest |
Gemini 3.1 Pro (preview) Google In $2 · Out $12 /1M · 1M | $2 | $0.20 | $12 | 1M | $186.18 68× cheapest |
GPT-5.4 OpenAI In $2.50 · Out $15 /1M · 1.05M | $2.50 | $0.25 | $15 | 1.05M | $232.35 85× cheapest |
Claude Sonnet 4.6 Anthropic In $3 · Out $15 /1M · 1M | $3 | $0.30 | $15 | 1M | $235.17 86× cheapest |
GPT-5.6 Sol OpenAI In $4 · Out $20 /1M · 1.05M Promotional pricing through at least Nov 21, 2026. | $4 | $0.40 | $20 | 1.05M | $311.76 114× cheapest |
Claude Opus 5.5 Anthropic In $4 · Out $20 /1M · 1M | $4 | $0.20 | $20 | 1M | $317.64 116× cheapest |
Claude Opus 4.8 Anthropic In $5 · Out $25 /1M · 1M | $5 | $0.50 | $25 | 1M | $397.05 145× cheapest |
Claude Opus 5 Anthropic In $5 · Out $25 /1M · 1M | $5 | $0.50 | $25 | 1M | $397.05 145× cheapest |
GPT-5.5 OpenAI In $5 · Out $30 /1M · 1.05M | $5 | $0.50 | $30 | 1.05M | $464.70 170× cheapest |
GPT-6 Astra OpenAI In $10 · Out $50 /1M · 1.05M OpenAI's most capable model. | $10 | $1 | $50 | 1.05M | $779.40 285× cheapest |
Claude Fable 5.1 Anthropic In $10 · Out $50 /1M · 1M Anthropic's most capable widely released model. | $10 | $0.25 | $50 | 1M | $794.10 290× cheapest |
Prices checked on 2026-10-18 from each provider's official pricing page (standard tier, USD per 1M tokens). Prices change often — verify before you budget.
Sources: OpenAI · Anthropic · Google · Mistral · Meta (Llama) · DeepSeek · xAI. Excludes taxes, tool/search fees, image/audio tokens and cache-write or storage surcharges.
🔒 Everything is calculated in your browser — prompts you paste are never sent anywhere.
How to calculate the cost of a prompt
- Paste the full prompt: system message, few-shot examples, retrieved context and the user message.
- Enter the output tokens you expect back and how many calls you'll make per day.
- Compare cost per call; switch the period to day or month to see it at scale.
Why the same prompt costs differently per model
Price per token is only half the story — tokenizers differ. The same English prompt is about 1.5× more tokens on current Claude models than on GPT-5/GPT-6, and about 1.05× on Gemini. This calculator counts your prompt exactly with OpenAI's o200k tokenizer and estimates the others from it, so you compare real per-call costs.
Prompt cost checklist
- Few-shot examples are re-sent on every call. Three long examples can double a prompt — keep them short or cache them.
- JSON in prompts: minified JSON uses noticeably fewer tokens than pretty-printed.
- Structured outputs shorten responses and make them parseable — generate the schema with our JSON Schema generator.
- Output dominates for chatty tasks: 500 output tokens on GPT-6 Sol ($0.005) cost as much as 2,500 input tokens.
Related tools
Frequently asked questions
Is my text sent to OpenAI, Anthropic or anyone else?
No. Everything runs in your browser: the tokenizer files are downloaded once and your text never leaves your device. Nothing is logged or stored.
How accurate is the prompt cost?
GPT costs use exact tiktoken counts. Claude, Gemini and others use calibrated estimates, usually within about 10% for English. Real bills also include chat framing, tools and any images.
How do I reduce prompt cost?
Move stable instructions to the start so they're cached, shorten few-shot examples, minify JSON, and pick the smallest model that passes your evals.
Are these prices up to date?
Prices were checked on 2026-10-18 from each provider's official pricing page. They change often, so confirm on the provider's site before committing to a budget.
Your business here? Sponsor this tool from $16/week. See placements