How much does the GPT-5 API cost?

GPT-5 API costs $1.25 per 1M input tokens and $10.00 per 1M output tokens. A typical request (1,500 input + 400 output tokens) costs about $0.0059. GPT-5.5 costs $5/$30 per 1M tokens, GPT-5 mini costs $0.25/$2.00, and GPT-4o costs $2.50/$10.00.

Is GPT-5 cheaper than Claude?

GPT-5 ($1.25/$10) is cheaper than Claude Sonnet 4.6 ($3/$15) and Claude Opus 4.7 ($5/$25) for input tokens, but more expensive for output tokens. GPT-5 mini ($0.25/$2) is cheaper than Claude Haiku 4.5 ($1/$5) on both input and output. For budget workloads, GPT-5 mini and GPT-4o mini offer the best value.

How much does GPT-5 cost per month?

Monthly GPT-5 costs depend on usage: 100 requests/day (~3K/mo) costs ~$18/month, 1,000 requests/day (~30K/mo) costs ~$177/month, 10,000 requests/day (~300K/mo) costs ~$1,770/month. Use the calculator above to estimate for your specific usage.

What is the cheapest OpenAI model?

The cheapest OpenAI models are GPT-oss 20B ($0.08/$0.35 per 1M tokens) and GPT-4o mini ($0.15/$0.60). GPT-5 mini ($0.25/$2.00) offers better quality at a slightly higher price. For most budget workloads, GPT-4o mini is the best value.

GPT-5 API Cost Calculator

Estimate your OpenAI API spend across GPT-5, GPT-5.5, GPT-5 mini, GPT-4o, and all OpenAI models. See cost per request, per 1K requests, and monthly totals.

Typical request:

By volume:

OpenAI Model

Input tokens per request

Output tokens per request

Requests per day

Streaming mode Streaming has same cost, different delivery

Cost Estimate

Input cost per request $0.0000

Output cost per request $0.0000

Total cost per request $0.0000

Cost per 1,000 requests $0.00

Daily cost $0.00

Monthly cost $0.00

Annual cost $0.00

All OpenAI Models — Cost Comparison

See how your costs compare across all OpenAI models with your current settings

Cheaper Alternatives from Other Providers

These models from other providers offer similar capabilities at lower prices:

Model	Provider	Input/1M	Output/1M	Your Cost/Req	Savings vs GPT-5

OpenAI GPT-5 Pricing Explained

OpenAI's GPT-5 API is priced at $1.25 per 1M input tokens and $10.00 per 1M output tokens. This makes it one of the best-value premium models — cheaper than Claude Sonnet 4.6 ($3/$15) and Gemini 3.1 Pro ($2/$12) for input-heavy workloads.

When to Use Each OpenAI Model

GPT-5.5 ($5/$30): Maximum capability. Use for the most complex reasoning, research, and analysis tasks.
GPT-5 ($1.25/$10): Best balance of quality and cost. Use for code generation, complex analysis, and multi-step reasoning.
GPT-5 mini ($0.25/$2): Great for moderate tasks. Summarization, content generation, and most chatbot workloads.
GPT-4o ($2.50/$10): Proven reliability. Good for production workloads where consistency matters.
GPT-4o mini ($0.15/$0.60): Budget champion. Classification, extraction, simple Q&A — handles 70% of typical workloads.
GPT-oss 120B ($0.15/$0.60): Open-source option via API. Same price as GPT-4o mini, different architecture.

How to Reduce Your OpenAI API Costs

Use model routing: Route simple tasks to GPT-4o mini, complex ones to GPT-5. Saves 40-80%.
Reduce output tokens: Set max_tokens limits. Output costs 8x more than input for GPT-5.
Use caching: OpenAI offers prompt caching for repeated prefixes — up to 50% discount on cached tokens.
Batch processing: Use the Batch API for non-urgent tasks — 50% discount on batch pricing.
Monitor usage: Set up billing alerts in the OpenAI dashboard to catch cost spikes early.

Related Tools

Claude API Cost Calculator — Compare Anthropic pricing
Multi-Model Routing Builder — Design a cost-optimized routing strategy
Model Switch Calculator — See savings from switching models
Cost Optimizer — Get a personalized optimization report
API Cost Report Card — Grade your spending efficiency, get a shareable report

Want to compare OpenAI with other providers?

OpenAI vs Anthropic →