OpenAI API Pricing Update: October 2025 Overview

October 2025

OpenAI continues to expand its model lineup with more specialized options and competitive pricing. Here’s a breakdown of the latest API pricing effective October 2025.

GPT-5 Series: Three Tiers for Every Need

GPT-5

• Best for: Coding and agentic tasks across industries
• Capabilities: Text & vision, reasoning, all built-in tools

• Context: 400k context length

  128k max output tokens

• Pricing: Input: $125

  Output: $10.00 per 1M tokens

GPT-5 mini

• Best for: Faster, cheaper version for well-defined tasks
• Capabilities: Text & vision, reasoning, all built-in tools

• Context: 400k context length

  128k max output tokens

• Pricing: Input: $0.25

  Output: $2.00 per 1M tokens

GPT-5 nano

• Best for: Fastest, cheapest version—great for summarization and classification
• Capabilities: Text & vision, reasoning, all built-in tools

• Context: 400k context length

  128k max output tokens

• Pricing: Input: $0.05

  Output: $0.40 per 1M tokens

Realtime API: Low-Latency Multimodal Experiences

Build realtime experiences including speech-to-speech with these rates:

Text Processing

• gpt-realtime: $4.00 / 1M input tokens

  $0.40 / 1M cached input tokens

  $16.00 / 1M output tokens

• GPT-4o mini: $0.60 / 1M input tokens

  $0.30 / 1M cached input tokens

  $2.40 / 1M output tokens

Audio Processing

• gpt-realtime: $32.00 / 1M input tokens

  $0.40 / 1M cached input tokens

  $64.00 / 1M output tokens

• GPT-4o mini: $10.00 / 1M input tokens

  $0.30 / 1M cached input tokens

  $20.00 / 1M output tokens

Image Processing

• gpt-realtime: $5.00 / 1M input tokens

  $0.50 / 1M cached input tokens

Image Generation API

Precise, high-fidelity image generation and editing:

• Text Input: $5.00 / 1M tokens

  $1.25 / 1M cached tokens*

• Image Input: $10.00 / 1M tokens

  $2.50 / 1M cached tokens*

  $40.00 / 1M output tokens

Image output costs:

• Low quality: ~$0.01 per square image
• Medium quality: ~$0.04 per square image
• High quality: ~$0.17 per square image

*available via the Responses API

Built-in Tools Pricing

Extend model capabilities with these additional tools:

• Code Interpreter: $0.03 per session
• File Search Storage: $0.10 / GB per day (first GB free)
• File Search Tool Call: $2.50 / 1k calls (Responses API only)

Web Search Pricing

• Web search preview (gpt-4o, gpt-4.i, gpt-4o-mini, gpt-4.i-mini): $25.00 / 1K calls
• Web search preview (gpt-5, o-series): $10.00 / 1K calls
• Web search (all models): $10.00 / 1K calls

Note: Search content tokens are free for gpt-4o and gpt-4.i models with web search preview

Cost Optimization Options

Pricing reflects standard processing rates. To optimize cost and performance for different use cases, we also offer:

• Batch API: Save 50% on inputs and outputs with the Batch API and run tasks asynchronously over 24 hours
• Priority Processing: Offers reliable, high-speed performance with the flexibility to pay-as-you-go

Key Takeaways

1. More Tiered Options: GPT-5 series now offers three distinct tiers for different use cases and budgets
2. Specialized APIs: Realtime and Image Generation APIs provide dedicated pricing for specific modalities
3. Cost Optimization: Multiple ways to reduce costs through caching, batch processing, and choosing the right model tier
4. Transparent Tool Pricing: Clear pricing for built-in tools like Code Interpreter and File Search

Choose the right model and optimization strategy based on your specific needs around latency, cost, and task complexity.

For detailed token usage by image quality and size, and the latest updates, always check the official OpenAI documentation.