GVGanivra

OpenAI API pricing · Updated

OpenAI API pricing

Quick answer

Current OpenAI API prices range from $0.10 per million input tokens on GPT-6 Luna to $30.00 on GPT-5.5 Pro. Per million input and output tokens, GPT-6 Luna costs $0.10 and $0.50, GPT-6.1 Terra $1.00 and $5.00, GPT-6.1 Sol $2.00 and $10.00, GPT-5.6 Sol $4.00 and $20.00, and GPT-6 Astra $10.00 and $50.00. Batch and Flex halve every price and Fast mode doubles it.

Estimate your monthly OpenAI API cost

Estimated monthly cost$1,100$0.011 per request on GPT-6.1 Sol. Excludes cache writes, tools and taxes.

OpenAI API prices per million tokens

ModelInputCache read30-min cache writeOutputBatch in / outStatus
GPT-6All GPT-6 prices →
GPT-6 Astragpt-6-astraPrompts over 272,000 tokens: $20.00 in / $75.00 out$10.00$1.00$12.50$50.00$5.00 / $25.00Active
GPT-6.1 Solgpt-6.1-solPrompts over 272,000 tokens: $4.00 in / $15.00 out$2.00$0.10$2.50$10.00$1.00 / $5.00Active
GPT-6.1 Terragpt-6.1-terraPrompts over 272,000 tokens: $2.00 in / $7.50 out$1.00$0.05$1.25$5.00$0.50 / $2.50Active
GPT-6 Solgpt-6-solPrompts over 272,000 tokens: $4.00 in / $15.00 out$2.00$0.20$2.50$10.00$1.00 / $5.00Active
GPT-6 Lunagpt-6-lunaPrompts over 272,000 tokens: $0.20 in / $0.75 out$0.10$0.01$0.125$0.50$0.05 / $0.25Active
GPT-5.6All GPT-5.6 prices →
GPT-5.6 Solgpt-5.6-solPromotional price through at least November 21, 2026Prompts over 272,000 tokens: $8.00 in / $30.00 out$4.00$0.40$5.00$20.00$2.00 / $10.00Active
GPT-5.6 Terragpt-5.6-terraPrompts over 272,000 tokens: $4.00 in / $18.00 out$2.00$0.20$2.50$12.00$1.00 / $6.00Active
GPT-5.6 Lunagpt-5.6-lunaPrompts over 272,000 tokens: $0.40 in / $1.80 out$0.20$0.02$0.25$1.20$0.10 / $0.60Active
GPT-5.5 and GPT-5.4
GPT-5.5gpt-5.5Prompts over 272,000 tokens: $10.00 in / $45.00 out$5.00$0.50—$30.00$2.50 / $15.00Active
GPT-5.5 Progpt-5.5-proPrompts over 272,000 tokens: $60.00 in / $270.00 out$30.00——$180.00$15.00 / $90.00Active
GPT-5.4gpt-5.4Prompts over 272,000 tokens: $5.00 in / $22.50 out$2.50$0.25—$15.00$1.25 / $7.50Active
GPT-5.4 Progpt-5.4-proPrompts over 272,000 tokens: $60.00 in / $270.00 out$30.00——$180.00$15.00 / $90.00Active
GPT-5.4 minigpt-5.4-mini$0.75$0.075—$4.50$0.375 / $2.25Active
GPT-5.4 nanogpt-5.4-nano$0.20$0.02—$1.25$0.10 / $0.625Deprecated, shuts down April 1, 2027
Cyber (Daybreak)
GPT-6-Cybergpt-6-cyberNeeds Daybreak Red access$20.00$2.00$25.00$100.00—Active
GPT-5.6 Cybergpt-5.6-cyberNeeds Daybreak Red accessPrompts over 272,000 tokens: $25.00 in / $112.50 out$12.50$1.25$15.625$75.00—Active
GPT-5.5 Cybergpt-5.5-cyberNeeds Daybreak Red access$12.50$1.25—$75.00—Active
Earlier GPT-5
GPT-5.3 Codexgpt-5.3-codex$1.75$0.175—$14.00—Deprecated, shuts down April 1, 2027
GPT-5.2gpt-5.2$1.75$0.175—$14.00$0.875 / $7.00Active
GPT-5.2 Progpt-5.2-pro$21.00——$168.00$10.50 / $84.00Active
GPT-5.1gpt-5.1$1.25$0.125—$10.00$0.625 / $5.00Deprecated, shuts down April 1, 2027
GPT-5gpt-5$1.25$0.125—$10.00$0.625 / $5.00Deprecated, shuts down December 11, 2026
GPT-5 minigpt-5-mini$0.25$0.025—$2.00$0.125 / $1.00Deprecated, shuts down December 11, 2026
GPT-5 nanogpt-5-nano$0.05$0.005—$0.40$0.025 / $0.20Deprecated, shuts down December 11, 2026
GPT-5 Progpt-5-pro$15.00——$120.00$7.50 / $60.00Deprecated, shuts down December 11, 2026
Reasoning (o-series)
o3o3$2.00$0.50—$8.00$1.00 / $4.00Deprecated, shuts down December 11, 2026
o3-proo3-pro$20.00——$80.00$10.00 / $40.00Deprecated, shuts down December 11, 2026
GPT-4.1 and GPT-4o
GPT-4.1gpt-4.1$2.00$0.50—$8.00$1.00 / $4.00Deprecated, shuts down January 14, 2027
GPT-4.1 minigpt-4.1-mini$0.40$0.10—$1.60$0.20 / $0.80Deprecated, shuts down January 14, 2027
GPT-4ogpt-4o$2.50$1.25—$10.00$1.25 / $5.00Deprecated, shuts down January 14, 2027
GPT-4o minigpt-4o-mini$0.15$0.075—$0.60$0.075 / $0.30Deprecated, shuts down January 14, 2027

Prices from OpenAI’s pricing page and deprecation schedule, for OpenAI’s own API. Models already shut down, such as o1 and o4-mini, are on the supported models page. Upcoming changes across providers are on the price change and shutdown tracker.

What one request costs on each OpenAI API model

Worked out from the prices above for GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna, at standard rates with no Batch discount.

RequestGPT-6 AstraGPT-6.1 SolGPT-6.1 TerraGPT-6 Luna
Chat reply3,000 input tokens, 500 output$0.055$0.011$0.0055$0.0006
Document summary30,000 input tokens, 1,500 output$0.375$0.075$0.037$0.0037
Agent task80,000 input tokens (60,000 cached), 6,000 output$0.560$0.106$0.053$0.0056

Head-to-head price comparisons: Claude Sonnet 5.5 vs GPT-6.1 Sol · Claude Opus 5.5 vs GPT-6 Astra · Claude Opus 5.5 vs GPT-6.1 Sol · Claude Fable 5.1 vs GPT-6 Astra · Claude Haiku 5.5 vs GPT-6 Luna · GPT-6.1 Sol vs Gemini 4 Argon · GPT-6 Astra vs Gemini 4 Argon · Claude Sonnet 5.5 vs GPT-6.1 Terra · Gemini 3.8 Flash vs GPT-6.1 Terra · Gemini 3.8 Flash vs GPT-6 Luna · Gemini 3.5 Flash-Lite vs GPT-6 Luna · GPT-6.1 Sol vs DeepSeek V4.1 Flash · GPT-6.1 Sol vs GPT-6 Astra · GPT-6.1 Sol vs GPT-6.1 Terra · GPT-6.1 Terra vs GPT-6 Luna · GPT-6.1 Sol vs GPT-5.6 Sol · all comparisons.

OpenAI API discounts and extra charges

Batch API
50% off every token price, for requests processed asynchronously.
Flex processing
50% off every token price on the models that offer it, in exchange for slower responses.
Fast mode
Faster processing, usually at 2× the Standard price. OpenAI renamed Priority processing to Fast mode on July 30, 2026.
Ultrafast
6× the Standard price, offered on GPT-6 Astra and GPT-6.1 Sol only.
Long context
On GPT-6, GPT-5.6, GPT-5.5 and GPT-5.4, a prompt over 272,000 input tokens bills the whole request at 2× input and cache and 1.5× output.
Prompt caching
Cached input costs 5% to 50% of the input price depending on the model. GPT-6 and GPT-5.6 also charge cache writes: 1.25× the input price for 30 minutes or 2.5× for 12 hours.
Regional processing
Data residency endpoints add 10% for models released on or after March 5, 2026. FedRAMP endpoints add 10% from November 1, 2026.
Web search
$10 per 1,000 calls, plus the search content tokens at the model’s rates.
File search
$2.50 per 1,000 tool calls, plus $0.10 per GB of storage per day after the first free GB.
Code Interpreter and Hosted Shell
Containers cost from $0.03 per 20-minute session for 1 GB of memory up to $1.92 for 64 GB.

Your OpenAI bill shows the total. Ganivra shows it per customer.

Ganivra prices every OpenAI call at these rates and adds it up by customer, feature and workflow, next to what each customer pays. You see who is profitable and who isn’t.

Start free 14-day trial

OpenAI API pricing questions

How much does the OpenAI API cost?

It depends on the model. Per million tokens, GPT-6 Luna costs $0.10 input and $0.50 output, GPT-6.1 Terra $1.00 input and $5.00 output, GPT-6.1 Sol $2.00 input and $10.00 output, GPT-5.6 Sol $4.00 input and $20.00 output and GPT-6 Astra $10.00 input and $50.00 output. A chat reply of 3,000 input and 500 output tokens costs $0.0006 on GPT-6 Luna and $0.011 on GPT-6.1 Sol.

What is the cheapest OpenAI model?

GPT-6 Luna, at $0.10 input and $0.50 output per million tokens. GPT-5 nano is cheaper at $0.05 input and $0.40 output, but it shuts down on December 11, 2026, and its replacement, GPT-5.6 Luna, costs $0.20 input and $1.20 output.

Is GPT-6 cheaper than GPT-5.6?

Yes, at the same tier. Per million tokens, GPT-6.1 Sol costs $2.00 input and $10.00 output and GPT-6 Sol $2.00 input and $10.00 output, while GPT-5.6 Sol costs $4.00 input and $20.00 output. GPT-5.6 is the replacement for the GPT-5 models that shut down on December 11, 2026; GPT-6 is the newer family.

How much does GPT-5 mini cost?

GPT-5 mini costs $0.25 input and $2.00 output per million tokens, but it shuts down on December 11, 2026. Its replacement, GPT-5.6 Terra, costs $2.00 input and $12.00 output. GPT-4.1 costs $2.00 input and $8.00 output and shuts down on January 14, 2027.

What is the most expensive OpenAI model?

GPT-5.5 Pro and GPT-5.4 Pro, at $30.00 input and $180.00 output per million tokens, with no discount for cached input. Among the GPT-6 models, GPT-6 Astra is the most expensive at $10.00 input and $50.00 output.

What is the difference between Standard, Batch, Flex, Fast mode and Ultrafast?

They are service tiers for the same model. Standard is the list price. Batch and Flex cost 50% less in exchange for slower or asynchronous processing. Fast mode, formerly Priority processing, usually costs 2× for faster responses. Ultrafast costs 6× and is offered on GPT-6 Astra and GPT-6.1 Sol only.

Does the OpenAI API charge more for long prompts?

Yes, on GPT-6, GPT-5.6, GPT-5.5 and GPT-5.4. Once a prompt passes 272,000 input tokens, the whole request costs 2× for input and cache and 1.5× for output: $4.00 input and $15.00 output per million on GPT-6.1 Sol.

Which OpenAI models are being retired?

GPT-5, GPT-5 mini, GPT-5 nano, GPT-5 Pro, o3 and o3-pro shut down on December 11, 2026, replaced by GPT-5.6 models. GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini follow on January 14, 2027, and GPT-5.1, GPT-5.3 Codex and GPT-5.4 nano on April 1, 2027. o1, o3-mini, o4-mini and GPT-4.1 nano already shut down on October 23, 2026.

Do the Responses API and Chat Completions cost the same?

Yes. OpenAI does not price the Responses, Chat Completions, Realtime or Assistants APIs separately: tokens are billed at the model's input and output rates. The Batch API is billed at the Batch tier price.

How do OpenAI prices compare with Claude?

Several tiers line up exactly. GPT-6 Luna and Claude Haiku 5.5 both cost $0.10/$0.50 per million input and output tokens ($0.10/$0.50 on Haiku), GPT-6.1 Sol and Claude Sonnet 5.5 $2.00/$10.00 ($2.00/$10.00 on Sonnet), and GPT-6 Astra and Claude Fable 5.1 $10.00/$50.00 ($10.00/$50.00 on Fable). Long prompts, cache rates and how many tokens each model uses make the real difference.

How much do OpenAI tools cost?

Web search costs $10 per 1,000 calls plus the search content tokens. File search costs $2.50 per 1,000 calls plus $0.10 per GB of storage per day after 1 GB free. Code Interpreter and Hosted Shell containers cost from $0.03 per 20-minute session.

How do I track OpenAI API cost per customer?

Tag each OpenAI call with the customer it served, then price it at these rates and add it up by customer. Ganivra does this automatically with two lines of the Python SDK, including Batch, Flex and Fast mode calls, and shows each customer's OpenAI cost next to what they pay you.

More detail: Why similar OpenAI API requests can cost 3× as much · GPT-6 pricing · GPT-5.6 pricing · Claude API pricing · Gemini API pricing · all supported models and prices.