Provider

OpenAI API Cost Calculator and Comparison

Every OpenAI model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 20 active models, 20 with public pricing, from $0.050/1M to $75.00/1M input. Prices refreshed daily from OpenAI’s official pricing page.

Models tracked

27

Active

20

With public pricing

20

Cheapest input

$0.05/1M

As of April 2026, OpenAI offers 20 active AI models via API, ranging from $0.050/1M to $75.00/1M input tokens. The most context-rich model handles up to 1M tokens. Models include support for vision, deep reasoning, tool use. All prices are in USD per 1 million tokens; output tokens cost more than input on every model.

Interactive

Calculate your OpenAI API cost at your workload.

Set your workload — every priced model ranks in real time.

Adjust the workload

Every model below updates in real time.

1,00010,00050,000250,0001M10M

Ranked by your monthly bill

No models with public pricing available to compare right now.

Pricing at a glance

Blended $/1M tokens across the lineup.

Blended price uses a 3-to-1 input/output ratio — a common industry standard. Green bar = cheapest.

Quick picks

Best OpenAI model for your use case.

Lowest cost

GPT-5 nano

$0.050/1M input

Largest context

GPT-4.1 nano

1M tokens

Deep reasoning

GPT-5 mini

Reasoning mode

Vision / multimodal

GPT-4o mini

Image input

Tool use / agents

GPT-4.1 mini

Function calling

Every model

Every OpenAI model — pricing, context & capabilities.

ModelContextInput /1MOutput /1M
GPT-5 nano400K$0.05$0.4
GPT-4.1 nano1M$0.1$0.4
GPT-4o mini128K$0.15$0.6
gpt-oss-20B128K$0.2$0.6
GPT-5 mini400K$0.25$2.00
GPT-4.1 mini1M$0.4$1.60
o4-mini200K$0.4$1.60
GPT-3.5 Turbo16K$0.5$1.50
gpt-oss-120B128K$0.9$2.70
o3-mini200K$1.00$4.00
GPT-5200K$1.25$10.00
GPT-5.1200K$1.25$10.00
GPT-4.11M$2.00$8.00
GPT-4o128K$2.50$10.00
o1-mini128K$3.00$12.00
GPT-4 Turbo128K$10.00$30.00
o3200K$10.00$40.00
o1200K$15.00$60.00
GPT-5 pro400K$15.00$120.00
GPT-4.5128K$75.00$150.00
GPT-5.2preview200KPricing TBA—
GPT-5.2 Propreview400KPricing TBA—
GPT-5.2 Thinkingpreview200KPricing TBA—
GPT-5.3preview400KPricing TBA—
GPT-5.3 Codexpreview200KPricing TBA—
GPT-5.4preview400KPricing TBA—
GPT-5.4-Cyberpreview400KPricing TBA—

FAQ

OpenAI — questions we see most.

Pricing patterns, best-known use cases, and how this provider stacks up.

Get instant answers from our AI agent

OpenAI API pricing ranges from $0.050 to $75.00 per 1M input tokens. Output tokens cost more than input on every model. Prices are per 1 million tokens (1M ≈ 750,000 words). Use the calculator above to estimate your monthly spend at your actual workload.
GPT-5 nano is the lowest-priced OpenAI model with public pricing at $0.050/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.
GPT-4.5 is OpenAI's highest-tier model at $75.00/1M input. It delivers the most sophisticated reasoning, instruction-following, and nuance. For workloads that don't require frontier performance, a mid-tier model typically cuts inference costs substantially.
GPT-5 mini, o4-mini, o3-mini and 4 more support deep reasoning mode, which improves performance on multi-step coding, debugging, and code review. For simpler autocomplete or snippet generation, a faster, cheaper model often delivers acceptable quality at a fraction of the cost.
GPT-5 nano, GPT-4.1 nano, GPT-4o mini and 14 more support function calling (tool use), required for agentic workflows. Agents need a model that reliably follows structured output schemas — test with your specific tool definitions before committing to production volumes.
Yes — GPT-4o mini, GPT-5 mini, GPT-4.1 mini, GPT-5 and 6 more accept image input alongside text. You can pass screenshots, photos, charts, and documents for analysis. Vision adds no separate line-item on most OpenAI models — you're billed for the token equivalent of the image.
Yes — OpenAI supports prompt caching (discounts for repeated context) and batch processing (accept a delay, cut costs ~50%). These rates appear in the table above under "Cached /1M" and "Batch /1M." Caching pays off quickly if your prompts share a long system prompt or document prefix across many calls.
OpenAI has historically adjusted prices when launching new model generations, often cutting rates to stay competitive. Buzzi.ai snapshots pricing daily — you can subscribe to price-drop alerts on any OpenAI model using the "Alert me" button on its detail page.
Use the main comparison wizard to run the same calculator across OpenAI, Anthropic, Google, Meta, Mistral, and 20+ other providers. Set your exact workload and get a ranked cost chart in under a minute.
GPT-5 mini, o4-mini, o3-mini, o1-mini and 3 more offer an extended thinking or reasoning mode. The model spends extra compute "thinking" before answering — slower and more expensive, but meaningfully better on complex, multi-step problems. Standard mode is faster and cheaper for routine tasks.

Look wider

Compare OpenAI against other providers.

Open the full wizard — pick a use case, set your usage, and cross-compare against OpenAI, Anthropic, Google, and 20+ more.

Open the comparison wizardBook a call