GPT-5 Mini API pricing

OpenAI · Mid-range price tier · Proprietary · released 2025-09. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.

Deprecated. The model maker has announced retirement of this model's API · shutdown 2026-12-11 · suggested replacement: GPT-5.6 Terra. It still carries a price because hosts still serve it; treat it as a model to migrate off, not one to start on.

A support ticket workload of 100K requests a month costs $137.50 on GPT-5 Mini. GPT-5 Mini shares the lowest price we track in the Mid-range price tier with 2 other models, and its list price has not moved since 2026-08-15. None of its 2 hosts undercuts the price we quote. Its maker has announced its retirement, so it is a model to migrate off rather than start on.

Available on

Direct API, Azure AI Foundry, OpenRouter

Curated by hand; check with the provider before committing.

Market position

On blended price ($1.475 per 1M tokens at 30% input, 70% output) it is the cheapest of 113 models in the Mid-range price tier, tied with 2 others. Across every price tier it is cheaper than 47% of priced text models in the catalogue: 159th cheapest of 303, tied with 2 others. Its Arena ELO of 1374 ranks 114th of the 160 models that carry one, above 29% of them.

Licence, size and capabilities

GPT-5 Mini is recorded here as proprietary: access is through an API, priced by the token. Its parameter count is not published. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 400K context window once costs $0.10 in input tokens at list price.

Pricing by host

A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 2 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.

The price we quote is already the cheapest of the 2 hosts: OpenAI at $0.25 input / $2.00 output per 1M tokens. All of them charge within 10% of one another.

HostInput $/1MOutput $/1M
OpenAI (model maker, price we quote)$0.25$2.00
Azure (price we quote)$0.25$2.00

List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.

Monthly cost at 100K requests, by business use case

From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where OpenAI publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.

Use caseTokens (in/out)Monthly (after discounts – list)
Support Ticket1,500 / 500$117 – $138
Knowledge Q&A2,000 / 800$179 – $210
Meeting Summary10,000 / 1,200$235 – $490
Marketing Content2,500 / 1,800$411 – $422
Coding Task3,000 / 2,000$441 – $475
Invoice Processing1,500 / 600$74 – $158
Call Summary2,000 / 700$93 – $190
Agent Workflow6,000 / 3,000$656 – $750

Price history

GPT-5 Mini has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.25 input / $2.00 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.

Alternatives to GPT-5 Mini

None of the 4 comparable models below costs less than GPT-5 Mini on the blended price.

The nearest models in the Mid-range price tier on Arena ELO, each with its blended price and score difference against GPT-5 Mini.

Other models from OpenAI

The 8 nearest to GPT-5 Mini in price, of 48 other OpenAI models in the catalogue. Prices per 1M tokens, input then output.

All 49 OpenAI models and prices

Common questions about GPT-5 Mini pricing

How much does GPT-5 Mini cost?
GPT-5 Mini costs $0.25 per 1M input tokens and $2.00 per 1M output tokens. That is the model maker's own rate (OpenAI). Prices as listed on 2026-11-12.
Which host is cheapest for GPT-5 Mini?
The price we quote is already the cheapest of the 2 hosts: OpenAI at $0.25 input / $2.00 output per 1M tokens. All of them charge within 10% of one another. Host rates as listed on 2026-11-12.
Does GPT-5 Mini offer batch or cached pricing?
Yes, both. Batch API pricing is $0.125 per 1M input tokens and $1.00 per 1M output tokens, and prompt-cache reads cost $0.025 per 1M tokens, as listed on 2026-11-12.
What would GPT-5 Mini cost per month?
With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $138 on GPT-5 Mini at the list price quoted on 2026-11-12.
Can GPT-5 Mini be self-hosted?
No, as far as this site records. GPT-5 Mini is recorded here as proprietary: access is through an API, priced by the token.
Has the price of GPT-5 Mini changed?
GPT-5 Mini has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.25 input / $2.00 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.

It publishes a batch rate, and that discount is conditional: when the batch discount applies.

These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.

Build the business case · Get a FinOps review

LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server