Prices updated daily

ChatGPT & LLM API Cost Calculator

Paste a prompt, pick a model and see what it costs. Count tokens and compare API prices for OpenAI GPT, Anthropic Claude, Google Gemini, Mistral, DeepSeek and xAI Grok. Runs in your browser, no sign-up, no ads.

Model Press / to search

Compare LLM API prices

Prices per 1 million tokens in US dollars. The last column shows the cost of your prompt on each model. Click a row to use that model.

chat-latestOpenAI$5$0.5$30$0.02
gpt-4.1 detailsOpenAI$2$0.5$8$0.006
gpt-4.1-mini detailsOpenAI$0.4$0.1$1.6$0.0012
gpt-4o detailsOpenAI$2.5$1.25$10$0.0075
gpt-4o-mini detailsOpenAI$0.15$0.075$0.6$0.00045
gpt-5 detailsOpenAI$1.25$0.125$10$0.00625
gpt-5-mini detailsOpenAI$0.25$0.025$2$0.00125
gpt-5-nano detailsOpenAI$0.05$0.005$0.4$0.00025
gpt-5.1 detailsOpenAI$1.25$0.125$10$0.00625
gpt-5.2 detailsOpenAI$1.75$0.175$14$0.00875
gpt-5.4 detailsOpenAI$2.5$0.25$15$0.01
gpt-5.4-mini detailsOpenAI$0.75$0.075$4.5$0.003
gpt-5.4-nano detailsOpenAI$0.2$0.02$1.25$0.000825
gpt-5.5 detailsOpenAI$5$0.5$30$0.02
gpt-5.6 detailsOpenAI$4$0.4$20$0.014
gpt-5.6-luna detailsOpenAI$0.2$0.02$1.2$0.0008
gpt-5.6-sol detailsOpenAI$4$0.4$20$0.014
gpt-5.6-terra detailsOpenAI$2$0.2$12$0.008
gpt-6-astra detailsOpenAI$10$1$50$0.035
gpt-6-luna detailsOpenAI$0.1$0.01$0.5$0.00035
gpt-6-sol detailsOpenAI$2$0.2$10$0.007
gpt-6.1-sol detailsOpenAI$2$0.1$10$0.007
gpt-6.1-terra detailsOpenAI$1$0.05$5$0.0035
o3 detailsOpenAI$2$0.5$8$0.006
claude-fable-5 detailsAnthropic$10$1$50$0.035
claude-fable-5-1 detailsAnthropic$10$0.25$50$0.035
claude-haiku-4-5 detailsAnthropic$1$0.1$5$0.0035
claude-haiku-5-5 detailsAnthropic$0.1$0.01$0.5$0.00035
claude-mythos-5 detailsAnthropic$10$1$50$0.035
claude-mythos-5-1 detailsAnthropic$10$0.25$50$0.035
claude-opus-4-5 detailsAnthropic$5$0.5$25$0.0175
claude-opus-4-6 detailsAnthropic$5$0.5$25$0.0175
claude-opus-4-7 detailsAnthropic$5$0.5$25$0.0175
claude-opus-4-8 detailsAnthropic$5$0.5$25$0.0175
claude-opus-5 detailsAnthropic$5$0.5$25$0.0175
claude-opus-5-5 detailsAnthropic$4$0.2$20$0.014
claude-sonnet-4-5 detailsAnthropic$3$0.3$15$0.0105
claude-sonnet-4-6 detailsAnthropic$3$0.3$15$0.0105
claude-sonnet-5 detailsAnthropic$2$0.2$10$0.007
claude-sonnet-5-5 detailsAnthropic$2$0.1$10$0.007
gemini-2.5-flash detailsGoogle Gemini$0.3$0.03$2.5$0.00155
gemini-2.5-flash-lite detailsGoogle Gemini$0.1$0.01$0.4$0.0003
gemini-2.5-pro detailsGoogle Gemini$1.25$0.125$10$0.00625
gemini-3-flash-preview detailsGoogle Gemini$0.5$0.05$3$0.002
gemini-3.1-flash-lite detailsGoogle Gemini$0.25$0.025$1.5$0.001
gemini-3.1-pro-preview detailsGoogle Gemini$2$0.2$12$0.008
gemini-3.5-flash detailsGoogle Gemini$1.5$0.15$9$0.006
gemini-3.5-flash-lite detailsGoogle Gemini$0.3$0.03$2.5$0.00155
gemini-3.6-flash detailsGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-3.7-flash detailsGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-3.8-flash detailsGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-4-argon detailsGoogle Gemini$2$0.1$10$0.007
gemini-flash-latestGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-flash-lite-latestGoogle Gemini$0.3$0.03$2.5$0.00155
gemini-omni-1.1-flash detailsGoogle Gemini$1.5–$9$0.006
gemini-pro-latestGoogle Gemini$2$0.2$12$0.008
codestral-2508 detailsMistral$0.3$0.03$0.9$0.00075
codestral-latestMistral$0.3$0.03$0.9$0.00075
codestral-mamba-latestMistral$0.25$0.025$0.25$0.000375
deepseek-v4-1-flash-1017 detailsMistral$0.3$0.007$1.2$0.0009
devstral-latestMistral$0.4$0.04$2$0.0014
devstral-medium-latestMistral$0.4$0.04$2$0.0014
devstral-small-latestMistral$0.1$0.01$0.3$0.00025
labs-leanstral-1-5-1 detailsMistral$0–$0$0
magistral-medium-latestMistral$1.5$0.15$7.5$0.00525
magistral-small-latestMistral$0.15$0.015$0.6$0.00045
ministral-3-3b-2512 detailsMistral$0.1$0.01$0.1$0.00015
ministral-3-8b-2512 detailsMistral$0.15$0.015$0.15$0.000225
ministral-3-14b-2512 detailsMistral$0.2$0.02$0.2$0.0003
ministral-3b-2512 detailsMistral$0.1$0.01$0.1$0.00015
ministral-3b-latestMistral$0.1$0.01$0.1$0.00015
ministral-8b-2512 detailsMistral$0.15$0.015$0.15$0.000225
ministral-8b-latestMistral$0.15$0.015$0.15$0.000225
ministral-14b-2512 detailsMistral$0.2$0.02$0.2$0.0003
ministral-14b-latestMistral$0.2$0.02$0.2$0.0003
mistral-code-agent-latestMistral$0.4$0.04$2$0.0014
mistral-code-fim-latestMistral$0.3$0.03$0.9$0.00075
mistral-code-latestMistral$0.3$0.03$0.9$0.00075
mistral-large-3 detailsMistral$0.5$0.05$1.5$0.00125
mistral-large-4 detailsMistral$1.36$0.14$4.18$0.00345
mistral-large-4-0 detailsMistral$1.36$0.14$4.18$0.00345
mistral-large-2512 detailsMistral$0.5$0.05$1.5$0.00125
mistral-large-latestMistral$0.5$0.05$1.5$0.00125
mistral-medium detailsMistral$1.5$0.15$7.5$0.00525
mistral-medium-3 detailsMistral$1.5$0.15$7.5$0.00525
mistral-medium-3-5 detailsMistral$1.5$0.15$7.5$0.00525
mistral-medium-3.5 detailsMistral$1.5$0.15$7.5$0.00525
mistral-medium-latestMistral$1.5$0.15$7.5$0.00525
mistral-small detailsMistral$0.1$0.01$0.3$0.00025
mistral-small-latestMistral$0.15$0.015$0.6$0.00045
mistral-tiny detailsMistral$0.25$0.025$0.25$0.000375
open-mistral-nemo detailsMistral$0.3$0.03$0.3$0.00045
pixtral-large-latestMistral$2$0.2$6$0.005
deepseek-coder detailsDeepSeek$0.14$0.014$0.28$0.00028
deepseek-flash detailsDeepSeek$0.3$0.006$1.2$0.0009
deepseek-r1 detailsDeepSeek$0.55$0.14$2.19$0.00164
deepseek-v3 detailsDeepSeek$0.27$0.07$1.1$0.00082
deepseek-v3.2 detailsDeepSeek$0.28$0.028$0.4$0.00048
deepseek-v4-flash detailsDeepSeek$0.3$0.006$1.2$0.0009
deepseek-v4-pro detailsDeepSeek$1.32$0.044$3.96$0.0033
grok-4.3 detailsxAI$1.25$0.2$2.5$0.0025
grok-4.3-latestxAI$1.25$0.2$2.5$0.0025
grok-4.5 detailsxAI$2$0.3$6$0.005
grok-4.5-latestxAI$2$0.3$6$0.005
grok-4.6 detailsxAI$2$0.5$6$0.005
grok-4.7 detailsxAI$2$0.5$6$0.005
grok-4.20 detailsxAI$1.25$0.2$2.5$0.0025
grok-4.20-0309-non-reasoning detailsxAI$1.25$0.2$2.5$0.0025
grok-4.20-0309-reasoning detailsxAI$1.25$0.2$2.5$0.0025
grok-4.20-non-reasoning detailsxAI$1.25$0.2$2.5$0.0025
grok-4.20-non-reasoning-latestxAI$1.25$0.2$2.5$0.0025
grok-4.20-reasoning detailsxAI$1.25$0.2$2.5$0.0025
grok-4.20-reasoning-latestxAI$1.25$0.2$2.5$0.0025
grok-build-0.1 detailsxAI$1$0.2$2$0.002
grok-build-latestxAI$2$0.3$6$0.005
grok-code-fast detailsxAI$1$0.2$2$0.002
grok-code-fast-1-0825 detailsxAI$1$0.2$2$0.002

How much does the ChatGPT API cost?

OpenAI bills the API per token, separately from a ChatGPT subscription. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. The table shows what common OpenAI models cost for a typical chat request of 1,000 input and 500 output tokens.

Model Input / 1M Output / 1M 1 request 1,000 requests
gpt-6.1-sol$2$10$0.007$7.00
gpt-6.1-terra$1$5$0.0035$3.50
gpt-6-astra$10$50$0.035$35.00
gpt-6-luna$0.1$0.5$0.00035$0.35
gpt-6-sol$2$10$0.007$7.00
gpt-5.6$4$20$0.014$14.00
gpt-5.6-luna$0.2$1.2$0.0008$0.80
gpt-5.6-sol$4$20$0.014$14.00
gpt-5.6-terra$2$12$0.008$8.00
gpt-4o$2.5$10$0.0075$7.50
gpt-4o-mini$0.15$0.6$0.00045$0.45

FAQ

How much does the ChatGPT API cost?

The ChatGPT (OpenAI) API is billed per token, with separate prices for input and output tokens. Prices range from a few cents per million tokens for the smallest models to tens of dollars for the largest. A token is roughly 4 characters of English text. Paste your prompt into the calculator to see the exact cost per request.

Is the API included in ChatGPT Plus?

No. A ChatGPT Plus or Pro subscription covers the ChatGPT app only. The OpenAI API is billed separately, pay as you go, through the OpenAI platform.

How is the API cost calculated?

Cost = input tokens × input price + output tokens × output price. Prices are per 1 million tokens, in US dollars. Multiply by the number of requests to get the total.

How often are the prices updated?

Every day. Prices come from the open LiteLLM price list, which links each provider's official pricing page. Each model links to its source.

What is batch pricing?

OpenAI, Anthropic and Google offer a batch API: you send requests that are processed within 24 hours, at about half the normal price. Models without a batch price show a dash.

What is cached input?

When the start of a prompt repeats across requests, providers can cache it and charge a much lower rate for those tokens, often 10% of the normal input price. Turn on "Cached input" to price the whole prompt at that rate.

Are the token counts exact?

Token counts use OpenAI's o200k tokenizer, the one GPT-4o and newer OpenAI models use, so they are exact for those models. Claude, Gemini and other models count tokens differently, so treat those as close estimates. You can also type a token count yourself.

Is my text sent anywhere?

No. Everything runs in your browser. The page only downloads the price list.