OpenAI Models API Cost Calculator & Comparison

Every OpenAI model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 55 active models, 55 with public pricing. Prices refreshed daily.

Models tracked

55

Active

55

With public pricing

55

Cheapest input

$0.00/1M

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. Green bar = cheapest.

Quick picks

Best OpenAI model for your use case.

As of April 2026, OpenAI offers 55 active models via API, ranging from $0/1M to $150.00/1M input tokens. The most context-rich model handles up to 1M tokens. Models support vision, deep reasoning, tool use. All prices are USD per 1 million tokens.

Lowest cost

gpt-oss-120b

$0/1M input

Largest context

GPT-5.4

1.1M tokens

Deep reasoning

GPT-5.4 Mini

Reasoning mode

Vision / multimodal

GPT-5.4 Nano

Image input

Tool use / agents

GPT-5.4 Pro

Function calling

Quality vs price

OpenAI benchmarks at a glance.

Each point is one model — X is blended $/1M tokens, Y is the average of available quality benchmarks. Larger bubbles mean larger context windows.

Per-model benchmark scores

ModelAvgScores
GPT-5.2-Codex89.9
GPQA Diamond89.9
GPT-5.1-Codex85.6
GPQA Diamond86HumanEval84.9MMLU86
o3 Pro84.5
GPQA Diamond84.5
GPT-5.1-Codex-Mini82.3
GPQA Diamond81.3HumanEval83.6MMLU82
GPT-4o-mini (2024-07-18)82.0
MMLU82
GPT-5 Codex81.4
GPQA Diamond83.7MMLU86.5SWE-Bench Verified74
o4 Mini High77.6
GPQA Diamond81.4MMLU83.2SWE-Bench Verified68.1
o3 Mini High76.7
GPQA Diamond77LiveCodeBench74MMLU79.1
GPT-4.1 Mini76.2
GPQA Diamond66.4IFEval84.1MMLU78.1
GPT-5.3-Codex73.4
AA Intelligence Index54GPQA Diamond91.5SWE-Bench Verified74.8
GPT-3.5 Turbo 16k70.0
MMLU70
GPT-5.2 Pro69.7
FrontierMath Tier-431.3GPQA Diamond90.3MMLU87.4
GPT-4.1 Nano65.2
GPQA Diamond50.3MMLU80.1
GPT-463.0
GPQA Diamond35.7HumanEval67MMLU86.4
GPT-4 Turbo Preview61.1
GPQA Diamond35.7MMLU86.5
GPT-5.4 Pro58.8
FrontierMath Tier-437.5GPQA Diamond94.6Humanity's Last Exam44.3
o158.7
GPQA Diamond74.7Humanity's Last Exam8.0LiveCodeBench67.9MMLU84.1
GPT-5.455.0
AA Intelligence Index57FrontierMath Tier-427.1GPQA Diamond74.8Humanity's Last Exam36.2SWE-Bench Verified80
GPT-553.9
AA Intelligence Index45FrontierMath Tier-412.5GPQA Diamond85Humanity's Last Exam25.3MMLU80.6SWE-Bench Verified74.9
GPT-5 Chat52.4
FrontierMath Tier-412.5GPQA Diamond68.6Humanity's Last Exam25.3MMLU82SWE-Bench Verified73.5
o4 Mini51.3
AIME 202492.7FrontierMath Tier-42.1GPQA Diamond78.4Humanity's Last Exam18.1MMLU83.2SciPredict16.2SWE-Bench Verified68.1
GPT-4 Turbo50.3
GPQA Diamond35.7HumanEval67MMLU86.5SWE-Bench Verified12
o3 Mini49.9
FrontierMath Tier-44.2GPQA Diamond74.8LiveCodeBench71.7MMLU79.1SciPredict19.8
GPT-5.249.2
AA Intelligence Index51FrontierMath Tier-418.8GPQA Diamond71.2Humanity's Last Exam27.8MMLU81.4SciPredict20.6SWE-Bench Verified73.8
GPT-4.149.1
FrontierMath Tier-40.0%GPQA Diamond66.6Humanity's Last Exam5.4IFEval87.4MMLU80.6SWE-Bench Verified54.6
GPT-5 Mini49.1
AA Intelligence Index41FrontierMath Tier-46.3GPQA Diamond80.3Humanity's Last Exam19.4MMLU82.8SWE-Bench Verified64.7
GPT-3.5 Turbo (older v0613)49.0
GPQA Diamond28.0MMLU70
GPT-5.148.0
FrontierMath Tier-44.2GPQA Diamond64.3Humanity's Last Exam23.7MMLU80.1SWE-Bench Verified68.0
GPT-5.2 Chat46.5
FrontierMath Tier-418.8GPQA Diamond91.4Humanity's Last Exam27.8SciPredict20.6SWE-Bench Verified73.8
o346.2
FrontierMath Tier-42.1GPQA Diamond82.7Humanity's Last Exam20.3MMLU85.3SciPredict17.9SWE-Bench Verified69.1
GPT-5.1 Chat45.2
FrontierMath Tier-44.2GPQA Diamond85.0Humanity's Last Exam23.7SWE-Bench Verified68.0
GPT-4o (2024-11-20)42.6
GPQA Diamond47.9Humanity's Last Exam2.7MMLU88.7SWE-Bench Verified31.0
gpt-oss-120b37.0
AA Intelligence Index37
gpt-oss-120b37.0
AA Intelligence Index37
GPT-4 Turbo (older v1106)35.7
GPQA Diamond35.7
GPT-5 Nano32.8
FrontierMath Tier-40.0%GPQA Diamond42.8MMLU55.6
GPT-5 Pro31.6
Humanity's Last Exam31.6
GPT-5.4 Mini31.3
FrontierMath Tier-42.1GPQA Diamond60.6
GPT-5.4 Nano31.0
FrontierMath Tier-46.3GPQA Diamond55.8
GPT-3.5 Turbo Instruct28.0
GPQA Diamond28.0
gpt-oss-20b22.0
AA Intelligence Index22
gpt-oss-20b22.0
AA Intelligence Index22
o1-pro8.1
Humanity's Last Exam8.1

Open weights

Open Models from OpenAI

OpenAI ships 5 open-source or open-weights models you can self-host or fine-tune. Each links to its Hugging Face card.

Every model

Every OpenAI model — pricing, context & capabilities.

ModelContextInput /1MOutput /1M
GPT-5.4 Mini400K$0.75$4.50
GPT-5.4 Nano400K$0.2$1.25
GPT-5.41.1M$2.50$15.00
GPT-5.4 Pro1.1M$30.00$180.00
GPT-5.3 Chat128K$1.75$14.00
GPT-5.3-Codex400K$1.75$14.00
GPT-5.2-Codex400K$1.75$14.00
GPT-5.2400K$1.75$14.00
GPT-5.2 Chat128K$1.75$14.00
GPT-5.2 Pro400K$21.00$168.00
GPT-5.1-Codex-Max400K$1.25$10.00
GPT-5.1400K$1.25$10.00
GPT-5.1 Chat128K$1.25$10.00
GPT-5.1-Codex400K$1.25$10.00
GPT-5.1-Codex-Mini400K$0.25$2.00
GPT Audio128K$2.50$10.00
GPT Audio Mini128K$0.6$2.40
gpt-oss-safeguard-20b131K$0.075$0.3
GPT-5 Image400K$10.00$10.00
GPT-5 Image Mini400K$2.50$2.00
GPT-5 Pro400K$15.00$120.00
GPT-5 Codex400K$1.25$10.00
GPT-5400K$1.25$10.00
GPT-5 Chat128K$1.25$10.00
GPT-5 Mini400K$0.25$2.00
GPT-5 Nano400K$0.05$0.4
gpt-oss-120b131K$0.039$0.19
gpt-oss-120b131K$0.0$0.0
gpt-oss-20b131K$0.03$0.14
gpt-oss-20b131K$0.0$0.0
o3 Deep Research200K$10.00$40.00
o4 Mini Deep Research200K$2.00$8.00
o3 Pro200K$20.00$80.00
o3200K$2.00$8.00
o4 Mini200K$1.10$4.40
o4 Mini High200K$1.10$4.40
GPT-4.11.0M$2.00$8.00
GPT-4.1 Mini1.0M$0.4$1.60
GPT-4.1 Nano1.0M$0.1$0.4
GPT-4o Search Preview128K$2.50$10.00
GPT-4o-mini Search Preview128K$0.15$0.6
o1-pro200K$150.00$600.00
o3 Mini200K$1.10$4.40
o3 Mini High200K$1.10$4.40
o1200K$15.00$60.00
GPT-4o (2024-11-20)128K$2.50$10.00
GPT-4o Audio128K$2.50$10.00
GPT-4o-mini (2024-07-18)128K$0.15$0.6
GPT-4 Turbo128K$10.00$30.00
GPT-4 Turbo Preview128K$10.00$30.00
GPT-4 Turbo (older v1106)128K$10.00$30.00
GPT-3.5 Turbo Instruct4K$1.50$2.00
GPT-3.5 Turbo (older v0613)4K$1.00$2.00
GPT-3.5 Turbo 16k16K$3.00$4.00
GPT-48K$30.00$60.00

FAQ

常见问题

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 to $150.00 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-oss-120b is the lowest-priced OpenAI model with public pricing at $0/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.
o1-pro is OpenAI's highest-tier model at $150.00/1M 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-5.4 Mini, GPT-5.4 Nano, GPT-5.4 and 31 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-5.4 Mini, GPT-5.4 Nano, GPT-5.4 and 51 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-5.4 Mini, GPT-5.4 Nano, GPT-5.4, GPT-5.4 Pro and 40 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-5.4 Mini, GPT-5.4 Nano, GPT-5.4, GPT-5.4 Pro and 30 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 wizard