GPT-5.4 Mini · OpenAI

What does GPT-5.4 Mini cost to run in a coding agent?

GPT-5.4 Mini costs about $0.023 per average coding-agent request on our measured traffic, at list prices of $0.75 per million input and $4.50 per million output tokens. It scores 24 on the Artificial Analysis Intelligence Index, 37th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenAI API pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run current Claude, GPT, Gemini and open models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What GPT-5.4 Mini costs per coding-agent request

Cost at list price	GPT-5.4 Mini
Prompt under 100K tokens50% of requests, 87% of input cached	$0.012
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.030
Prompt over 272K tokens11% of requests, 86% of input cached	$0.056
Average request	$0.023
100 requests	$2.27
Median session16 requests; a session ends after 10 idle minutes	$0.30
A month of regular usemedian of 20 users active on 5+ days	$34.90

Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request. 3% of requests were larger than GPT-5.4 Mini's 400K context window and are left out of its figures.

GPT-5.4 Mini benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	24	37 of 48
Terminal-Bench 4.0agentic coding in a terminal	2.0%	27 of 39
Output speedmedian	233 tokens/s	3 of 44
Time to first answer tokenincludes thinking time	2.1 min	33 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: GPT-5.4 mini (Xhigh), speed on OpenAI. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

What to watch for

Its 400K-token window is smaller than 3% of our coding-agent requests, which are left out of the figures above, so long agent sessions will hit the limit. It is weak on long agentic coding tasks (see Terminal-Bench 4.0 above), so a cheap request can turn into more steps and retries.

About GPT-5.4 Mini

GPT-5.4 Mini is the small GPT-5.4 model, released March 17, 2026 for routing, classification and other high-volume calls. It is fast, at about 233 output tokens per second per Artificial Analysis, with a 400K context that is smaller than 3% of the coding-agent requests we measured. It scores 24 on the Artificial Analysis Intelligence Index and 2.0% in its Terminal-Bench 4.0 run. GPT-6 Luna scores higher (38) and costs about a fifth as much per request ($0.0041 vs $0.023).

Sources: Artificial Analysis

GPT-5.4 Mini FAQ

How much does GPT-5.4 Mini cost per coding-agent request?

$0.023 on average at list price, $2.27 per 100 requests, and $0.30 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenAI's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does GPT-5.4 Mini charge more for long prompts?

No. GPT-5.4 Mini bills the same rate per token up to its 400K-token context window, which is smaller than 3% of the coding-agent requests we measured.

How fast is GPT-5.4 Mini?

Artificial Analysis measures GPT-5.4 mini (Xhigh) at 233 output tokens per second, with 128 seconds to the first answer token, thinking time included, on OpenAI's API. Source: Artificial Analysis (artificialanalysis.ai).

Is GPT-5.4 Mini good for AI agents?

Short, simple calls in existing GPT-5.4 setups. On our scoring, which is calibrated to public benchmarks, it rates 5.0/10 for agentic ability and 5.6/10 for output quality. 400K context.

What is GPT-5.4 Mini's context window?

GPT-5.4 Mini has a 400K-token context window. OpenAI is the maker.

Can I self-host GPT-5.4 Mini?

No. GPT-5.4 Mini is a proprietary, hosted-only model from OpenAI. You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of GPT-5.4 Mini?

The main trade-offs: GPT-6 Luna scores higher and costs about a fifth as much per request; Not suited to long agentic coding (2.0% in Artificial Analysis's Terminal-Bench 4.0 run). It's strongest for short, simple calls in existing GPT-5.4 setups.