Cost estimator
Estimate your cost when you are on the usage-based pricing plan. Remember that these are rough estimates, and the best way to know your cost is to test your use case on a small sample.
Cost for typical use cases
Basic use cases (cost for 1000 rows)
Use-case
Cost (including AI provider cost)
Translating a product catalog into one language (titles and descriptions)
$31.17
Enriching a product catalog (extracting 5 product attributes from descriptions)
$15.20
Categorizing a product catalog (100 categories)
$19.82
Creating meta-titles and meta-descriptions from titles and descriptions
$23.98
Generating alt texts from product images
$23.37
Filtering leads for ICP fitness
$0.47
Feedback analysis
$1.85
Reformatting / cleaning a column of data
$0.36
Web search use cases (cost for 1000 rows)
Market research (enriching 5 columns with web search)
$25.29
Enriching a product catalog (extracting 5 product attributes from web search)
$25.28
Web fetch use cases (cost for 1000 rows)
Coverage tracking (extracting headlines from news articles)
$13.70
Your total cost will depend on:
- Model choice (including whether you're using your own API key or not). Full price list available here.
- Whether you're using web search or not
- Input and output size per execution
- How many executions you run which is equal to the number of empty cells you need to fill out
- If you use the Agent, you need to add the cost of each chat message which is $0.16 on average. You typically need very few (sometimes only one) message to achieve the use cases above.
Simple estimator
If you know the number of executions you will run (equal to the number of cells you need to fill out) and have an example input and output for the average execution, you can use the simple estimator to get a quick estimate of your cost. Remember that these are rough estimates, and the best way to know your cost is to test your use case on a small sample.
Choose a model
OpenAI gpt-4o
No API key needed
gpt-4o$30 / 1M tokens
gpt-4o-mini$2 / 1M tokens
gpt-5-search-api$40 / 1M tokens + $10 / 1K executions
gpt-5.1$40 / 1M tokens
gpt-5$40 / 1M tokens
gpt-5-mini$8 / 1M tokens
gpt-5-nano$1 / 1M tokens
gpt-5-chat$20 / 1M tokens
gpt-4.1$20 / 1M tokens
gpt-4.1-mini$6 / 1M tokens
gpt-4.1-nano$1 / 1M tokens
o1$70 / 1M tokens
o3$10 / 1M tokens
o4-mini$10 / 1M tokens
gpt-3.5-turbo$2.5 / 1M tokens
sonar$10 / 1M tokens + $5 to $12 / 1K executions
sonar-reasoning$10 / 1M tokens + $5 to $12 / 1K executions
gemini-2.5-flash$4 / 1M tokens + $35 / 1K executions
Use your API key 🔑
gpt-4o 🔑$1 / 1M tokens
gpt-4o-mini 🔑$0.3 / 1M tokens
gpt-4o-search-preview 🔑$1 / 1M tokens
gpt-4o-mini-search-preview 🔑$0.3 / 1M tokens
gpt-5-search-api 🔑$1 / 1M tokens
gpt-5.1 🔑$1 / 1M tokens
gpt-5 🔑$1 / 1M tokens
gpt-5-mini 🔑$1 / 1M tokens
gpt-5-nano 🔑$1 / 1M tokens
gpt-5-chat 🔑$1 / 1M tokens
gpt-4.1 🔑$1 / 1M tokens
gpt-4.1-mini 🔑$1 / 1M tokens
gpt-4.1-nano 🔑$1 / 1M tokens
gpt-4-turbo 🔑$1 / 1M tokens
gpt-4 🔑$1 / 1M tokens
o1 🔑$1 / 1M tokens
o3-mini 🔑$1 / 1M tokens
o3 🔑$1 / 1M tokens
o4-mini 🔑$1 / 1M tokens
gpt-3.5-turbo 🔑$1 / 1M tokens
ft:gpt-3.5-turbo 🔑$1 / 1M tokens
ft:gpt-4o 🔑$1 / 1M tokens
ft:gpt-4o-mini 🔑$0.3 / 1M tokens
sonar 🔑$1 / 1M tokens
sonar-pro 🔑$1 / 1M tokens
sonar-reasoning 🔑$1 / 1M tokens
sonar-reasoning-pro 🔑$1 / 1M tokens
grok-3 🔑$1 / 1M tokens
grok-3-mini 🔑$1 / 1M tokens
grok-3-fast 🔑$1 / 1M tokens
grok-3-mini-fast 🔑$1 / 1M tokens
gemini-2.5-flash 🔑$1 / 1M tokens
gemini-2.5-flash-lite 🔑$1 / 1M tokens
gemini-2.5-pro 🔑$1 / 1M tokens
gemini-2.0-flash 🔑$1 / 1M tokens
gemini-2.0-flash-lite 🔑$1 / 1M tokens
deepseek-reasoner 🔑$1 / 1M tokens
mistral-large 🔑$1 / 1M tokens
mistral-small 🔑$1 / 1M tokens
ministral-8b 🔑$1 / 1M tokens
ministral-3b 🔑$1 / 1M tokens
openrouter 🔑$1 / 1M tokens
Executions needed
One execution = one cell of outputAverage tokens per execution
Detailed execution estimator
Notes
- Without an API key: The estimated cost covers everything and is deducted from your balance. Models that support prompt caching will get a 75% discount on cached input tokens, so the estimated cost can be higher than your actual cost.
- With an API key: You pay GPT for Work the estimated cost (deducted from your balance) and also pay the AI provider directly for API usage.