OpenAI API Pricing Calculator
Use this OpenAI API pricing calculator to compare GPT-5, Codex, o3, and reasoning model costs. Codex Mini starts at $1.50/1M input and $6.00/1M output, while GPT-5.3 Codex costs $1.75/1M input and $14.00/1M output for deeper repo work.
OpenAI pricing quick answer
Use this OpenAI API pricing calculator to estimate GPT-5, Codex, and ChatGPT-style API workloads. Codex Mini starts at $1.50/1M input and $6.00/1M output, while GPT-5.3 Codex costs $1.75/1M input and $14.00/1M output for deeper repo work and stronger agentic coding.
OpenAI Recommendation
Use the OpenAI API pricing calculator on this page to budget GPT-5, Codex, and o-series usage. Start with Codex Mini at $1.50/1M input and $6.00/1M output, then move to GPT-5.3 Codex at $1.75/1M input and $14.00/1M output when code quality and deeper repo work matter more than absolute token savings. Choose GPT-5 nano for budget-heavy workloads, and step up to o1 Pro when quality matters more than token cost.
Compare OpenAI vs other providers
OpenAI Models & Pricing
| Model | Input Price | Output Price | Context Window | Max Output | Category | Capabilities |
|---|---|---|---|---|---|---|
GPT-6 Astra OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation. Released: 9/3/2026 | $10.00 per 1M tokens | $50.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | flagship | textvisioncodereasoning |
GPT-5.6 Cyber Purpose-trained GPT-5.6 model for authorized cybersecurity research, exploit validation, and advanced security testing. Released: 8/10/2026 | $12.50 per 1M tokens | $75.00 per 1M tokens | 400,000 tokens | 128,000 tokens | reasoning | textvisioncodereasoning |
GPT-5.6 Sol OpenAI's new flagship GPT-5.6 model for advanced coding, science, cybersecurity, and agentic work. Released: 6/26/2026 | $5.00 per 1M tokens | $30.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | flagship | textvisioncodereasoning |
GPT-5.6 Terra Balanced GPT-5.6 model for everyday work with GPT-5.5-class performance at lower cost. Released: 6/26/2026 | $2.50 per 1M tokens | $15.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | balanced | textvisioncodereasoning |
GPT-5.6 Luna Fastest and most cost-efficient GPT-5.6 variant for high-volume agentic and coding workloads. Released: 6/26/2026 | $1.00 per 1M tokens | $6.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | efficient | textvisioncodereasoning |
GPT-5.5 Instant Latest Instant-class ChatGPT model with stronger factuality, clearer answers, and improved personalization via the chat-latest API alias. Released: 5/5/2026 | $5.00 per 1M tokens | $30.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | flagship | textvisioncodereasoning |
GPT-5.5 OpenAI frontier model for complex reasoning, coding, and professional work. Released: 4/24/2026 | $5.00 per 1M tokens | $30.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | flagship | textvisioncodereasoning |
GPT-5.5 Pro Higher-compute GPT-5.5 variant for tougher problems requiring smarter, more precise responses. Released: 4/24/2026 | $30.00 per 1M tokens | $180.00 per 1M tokens | 1,050,000 tokens | 128,000 tokens | reasoning | textvisioncodereasoning |
$2.50 per 1M tokens | $15.00 per 1M tokens | 1,050,000 tokens | 131,072 tokens | flagship | textvisioncodereasoning | |
GPT-5.4 Pro The smartest and most precise GPT-5.4 variant for the most demanding tasks Released: 3/6/2026 | $30.00 per 1M tokens | $180.00 per 1M tokens | 1,050,000 tokens | 131,072 tokens | reasoning | textvisioncodereasoning |
$0.75 per 1M tokens | $4.50 per 1M tokens | 1,050,000 tokens | 65,536 tokens | efficient | textvisioncode | |
$0.20 per 1M tokens | $1.25 per 1M tokens | 128,000 tokens | 8,192 tokens | efficient | text | |
GPT-5.3 Codex Optimized for terminal execution, code review, and token efficiency. 77.3% Terminal-Bench, 2-4x fewer tokens per task Released: 3/1/2026 | $1.75 per 1M tokens | $14.00 per 1M tokens | 256,000 tokens | 32,768 tokens | coding | textcode |
$1.50 per 1M tokens | $6.00 per 1M tokens | 200,000 tokens | 32,768 tokens | efficient | textcodereasoning | |
$1.75 per 1M tokens | $14.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | flagship | textvisionaudiocodereasoning | |
$21.00 per 1M tokens | $168.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | reasoning | textvisionaudiocodereasoning | |
$1.25 per 1M tokens | $10.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | flagship | textvisionaudiocodereasoning | |
$1.25 per 1M tokens | $10.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | flagship | textvisionaudiocode | |
GPT-5 Pro Most powerful GPT-5 variant for the most complex tasks, using scaled parallel compute for highest quality answers Released: 8/7/2025 | $15.00 per 1M tokens | $120.00 per 1M tokens | 200,000 tokens | 100,000 tokens | flagship | textvisioncodereasoning |
$0.25 per 1M tokens | $2.00 per 1M tokens | 500,000 tokens | 65,536 tokens | efficient | textvisioncode | |
$0.05 per 1M tokens | $0.40 per 1M tokens | 128,000 tokens | 8,192 tokens | efficient | text | |
o4-mini Deep Research Faster, more affordable deep research model for complex research tasks Released: 6/26/2025 | $2.00 per 1M tokens | $8.00 per 1M tokens | 200,000 tokens | 32,768 tokens | reasoning | textreasoningcode |
o3 Deep Research Powerful deep research model built on o3 for complex multi-step research tasks Released: 6/26/2025 | $10.00 per 1M tokens | $40.00 per 1M tokens | 200,000 tokens | 32,768 tokens | reasoning | textreasoningvisioncode |
$20.00 per 1M tokens | $80.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | reasoning | textreasoningcode | |
$2.00 per 1M tokens | $8.00 per 1M tokens | 1,000,000 tokens | 131,072 tokens | reasoning | textreasoningvisioncode | |
$1.10 per 1M tokens | $4.40 per 1M tokens | 2,000,000 tokens | 131,072 tokens | reasoning | textreasoningcode | |
$2.00 per 1M tokens | $8.00 per 1M tokens | 200,000 tokens | 32,768 tokens | flagship | textvisioncode | |
$0.40 per 1M tokens | $1.60 per 1M tokens | 200,000 tokens | 16,384 tokens | efficient | textvisioncode | |
$0.10 per 1M tokens | $0.40 per 1M tokens | 128,000 tokens | 8,192 tokens | efficient | text | |
$1.10 per 1M tokens | $4.40 per 1M tokens | 500,000 tokens | 65,536 tokens | reasoning | textreasoningcode | |
o1 Pro Most powerful o1 reasoning model with extended compute for the hardest problems Released: 12/17/2024 | $150.00 per 1M tokens | $600.00 per 1M tokens | 200,000 tokens | 100,000 tokens | flagship | textvisioncodereasoning |
$15.00 per 1M tokens | $60.00 per 1M tokens | 200,000 tokens | 65,536 tokens | reasoning | textreasoning | |
$1.10 per 1M tokens | $4.40 per 1M tokens | 128,000 tokens | 65,536 tokens | reasoning | textreasoning | |
$0.15 per 1M tokens | $0.60 per 1M tokens | 128,000 tokens | 16,384 tokens | efficient | textvision | |
$2.50 per 1M tokens | $10.00 per 1M tokens | 128,000 tokens | 16,384 tokens | flagship | textvisionaudio | |
$10.00 per 1M tokens | $30.00 per 1M tokens | 128,000 tokens | 4,096 tokens | flagship | textvisioncode |
Calculate OpenAI Costs
Use our calculator to estimate costs for any OpenAI model based on your usage patterns.
Compare OpenAI Models
GPT-6 Astra vs GPT-5.6 Sol
GPT-5.6 Cyber vs GPT-5.5 Pro
GPT-5.6 Sol vs GPT-5.5 Instant
GPT-5.6 Terra vs GPT-5.6 Luna
GPT-5.6 Luna vs GPT-5.4 mini
GPT-5.5 Instant vs GPT-5.5
OpenAI Pricing FAQ
How much does the OpenAI API cost?
OpenAI API pricing on this page ranges from lower-cost GPT and Codex options up to premium reasoning models. For coding-specific routes, Codex Mini starts at $1.50 per million input tokens and $6.00 per million output tokens, while GPT-5.3 Codex costs $1.75 input and $14.00 output per million tokens.
Is there a ChatGPT or OpenAI pricing calculator?
Yes. This page includes an OpenAI API pricing calculator so you can estimate prompt cost, completion cost, cost per request, and monthly spend for GPT-5, Codex, o-series, and other OpenAI models without doing the token math by hand.
Which OpenAI model should I use for coding?
Start with Codex Mini when you want the lowest-cost OpenAI coding route for code review and lightweight edits. Step up to GPT-5.3 Codex when you need stronger coding quality or longer agentic sessions, and use the broader GPT-5 family when coding is only one part of a multimodal workflow.
What OpenAI models are on this page?
This page compares 36 OpenAI models including Codex Mini, GPT-5.3 Codex, GPT-5.5, GPT-5.4, GPT-5.2, GPT-5, and OpenAI reasoning models. The full table shows pricing, context window, and capabilities in one place.
How does OpenAI pricing compare to other providers?
Codex Mini starts at $1.50/1M input tokens, which keeps OpenAI competitive for coding-focused workloads. Use the comparison links on this page to stack OpenAI against Claude, Gemini, DeepSeek, and other providers on direct token cost, context window, and model tier.
Related Articles
OpenAI’s V7 Memory Story: 6 Team Workflows to Build Next
Build evidence-backed agent memory for support, sales, coding, and research, with practical workflows and model routi...
9/22/2026
OpenAI Research Acceleration Workflows: Turn Papers, Evals, and Logs Into AI Roadmaps
Build AI research acceleration workflows that convert papers, evals, and experiment logs into production-ready roadmaps.
9/7/2026
ChatGPT Work Signed-In Website and Webhook Workflows: What Teams Can Automate Now
How ChatGPT Work signed-in browsing and webhooks unlock Gmail, Slack, GitHub, research, recruiting, and ops automatio...
8/31/2026
GPT-5.6 in Kiro: Agentic Coding Workflows Teams Can Ship Now
OpenAI GPT-5.6 Sol, Terra, and Luna are now in AWS Kiro. Build spec-driven coding agents with routing, tests, and cos...
8/30/2026