AI & LLM
Token, cost & context tools for LLMs
ChatGPT API Cost Calculator — GPT-4o Chat Pricing per Message
In a chat application, each API call typically sends the full conversation history plus a system prompt as input, with the model's reply as output. GPT-4o is priced at $2.50/M input and $10.00/M output tokens as of 2026-07-03. At the reference workload (1,000 input + 500 output tokens per turn), one turn costs $0.0075: input $0.0025 + output $0.005. 1,000 turns costs $7.50. Output is 4× more expensive than input — longer model replies drive cost more than longer user messages. Enter your own turn length and daily volume for a monthly estimate.
GPT-4o reference turn (1000 input + 500 output tokens): $0.0075
- Input cost: $0.0025 | Output cost: $0.005
- Per 1,000 turns: $7.50
- GPT-4o price: $2.50/M input | $10.00/M output
- Output tokens cost 4× more — shorter replies = lower cost
- Context window: 128,000 tokens | Rates as of 2026-07-03
Frequently asked questions
How much does a GPT-4o chat conversation cost via the API?
A single GPT-4o chat turn (1000 input + 500 output tokens) costs $0.0075. Multi-turn conversations grow in cost because each turn re-sends the full history as input — a 10-turn conversation can use 5,000–15,000 input tokens depending on message lengths. Use the full calculator with your average turn length to estimate total conversation cost.
Should I use GPT-4o or GPT-5.4-mini for a high-volume chat app?
GPT-4o costs $2.50/M input and $10.00/M output. GPT-5.4-mini costs $0.75/M input and $4.50/M output — roughly 3× and 2.2× cheaper respectively. For high-volume chat (>100K turns/day), the cost difference is substantial. Benchmark both models on your specific tasks — GPT-5.4-mini matches GPT-4o on many conversational workloads.