How much does GPT-5.4 Mini cost?

GPT-5.4 Mini costs $0.75/M input tokens and $4.50/M output tokens, with separate rates for Cache Read at $0.075/M tokens.

What is the context length of GPT-5.4 Mini?

GPT-5.4 Mini has a 400,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-5.4 Mini support tool calling and structured outputs?

Yes. GPT-5.4 Mini accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does GPT-5.4 Mini support?

GPT-5.4 Mini accepts files such as PDFs, images, and text as input and returns text.

Which providers serve GPT-5.4 Mini?

GPT-5.4 Mini is served by 2 providers on OpenRouter: OpenAI and Azure. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GPT-5.4 Mini released?

GPT-5.4 Mini was released on March 17, 2026. Its knowledge cutoff is August 31, 2025.

OpenAI: GPT-5.4 Mini

openai/gpt-5.4-mini

Compare

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.

The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

Modalities

In / out price

$0.75 / $4.50per 1M

Context

400K

Released

Mar 17, 2026

Knowledge cutoff

Aug 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.75	$4.50	$0.075	1.13s	82 tok/s	100.00%
	$0.75	$4.50	$0.075	1.72s	143 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.375	$2.25	$0.0375	0.93s	149 tok/s	100.00%
	$0.825	$4.95	$0.0825	1.36s	76 tok/s	100.00%
Fast	$1.50	$9.00	$0.15	1.39s	97 tok/s	100.00%

Input $0.75Output $4.50
82 tok/s100.00% uptime
Input $0.75Output $4.50
143 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.375Output $2.25
Flex
149 tok/s100.00% uptime
Input $0.825Output $4.95
76 tok/s100.00% uptime
Input $1.50Output $9.00
Fast
97 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.3912/M tokens

Output

$4.485/M tokens

GPT-5.4 Mini — Price history

Price history

No effective price data for this selection

		$0.322	$4.50	63.4%	10.5%
		$0.399	$4.50	52.0%	88.7%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.256	$2.25	35.3%	0.3%
		$0.455	$4.95	49.8%	0.1%
	Fast	$0.606	$9.00	66.2%	0.5%

Effective in $0.322Effective out $4.50
Token share
10.5%
Effective in $0.399Effective out $4.50
Token share
88.7%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.256Effective out $2.25
FlexToken share
0.3%
Effective in $0.455Effective out $4.95
Token share
0.1%
Effective in $0.606Effective out $9.00
FastToken share
0.5%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.85%

Availability over the last 3 days

Last 72 hours

Availability 99.85%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

Without Routing

98.25%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: GPT-5.4 Mini (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-5.4 mini (Medium) GPQA Diamond	82.3%
Artificial Analysis	GPT-5.4 mini (Medium) HLE	18.6%
Artificial Analysis	GPT-5.4 mini (Medium) IFBench	64.8%
Artificial Analysis	GPT-5.4 mini (Medium) τ²-Bench Telecom	36.5%
Artificial Analysis	GPT-5.4 mini (Medium) AA-LCR	67.0%
Artificial Analysis	GPT-5.4 mini (Medium) CritPt	2.9%
Artificial Analysis	GPT-5.4 mini (Medium) Terminal-Bench Hard	34.1%
Artificial Analysis	GPT-5.4 mini (Xhigh) Coding Index	56.1
Artificial Analysis	GPT-5.4 mini (Xhigh) Agentic Index	17.9
Artificial Analysis	GPT-5.4 mini (Xhigh) GPQA Diamond	87.5%
Artificial Analysis	GPT-5.4 mini (Xhigh) HLE	28.1%
Artificial Analysis	GPT-5.4 mini (Xhigh) IFBench	73.3%
Artificial Analysis	GPT-5.4 mini (Xhigh) τ²-Bench Telecom	83.3%
Artificial Analysis	GPT-5.4 mini (Xhigh) AA-LCR	77.0%
Artificial Analysis	GPT-5.4 mini (Xhigh) τ-Bench Banking	25.6%
Artificial Analysis	GPT-5.4 mini (Xhigh) GDPval-AA	26.1%
Artificial Analysis	GPT-5.4 mini (Xhigh) CritPt	10.0%
Artificial Analysis	GPT-5.4 mini (Xhigh) SciCode	52.1%
Artificial Analysis	GPT-5.4 mini (Xhigh) Terminal-Bench Hard	52.3%
Artificial Analysis	GPT-5.4 mini (Xhigh) Terminal-Bench 4.0	2.0%
Artificial Analysis	GPT-5.4 mini (Xhigh) Terminal-Bench 2.1	59.2%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) GPQA Diamond	60.6%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) HLE	5.9%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) IFBench	38.8%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) τ²-Bench Telecom	23.4%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) AA-LCR	37.0%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) GDPval-AA	4.9%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) CritPt	0.0%
Artificial Analysis	GPT-5.4 mini (Non-reasoning) Terminal-Bench Hard	18.2%
Vals AI	GPT 5.4 Mini AIME	95.6%
Vals AI	GPT 5.4 Mini CaseLaw v2	51.7%
Vals AI	GPT 5.4 Mini Code Migration	12.9%
Vals AI	GPT 5.4 Mini CorpFin v2	60.9%
Vals AI	GPT 5.4 Mini EMB	45.4%
Vals AI	GPT 5.4 Mini Finance Agent (v2)	45.4%
Vals AI	GPT 5.4 Mini GPQA Diamond	83.1%
Vals AI	GPT 5.4 Mini Harvey's Legal Agent Benchmark v1	0.0%
Vals AI	GPT 5.4 Mini IOI v1	6.4%
Vals AI	GPT 5.4 Mini LiveCodeBench	81.5%
Vals AI	GPT 5.4 Mini Legal Research Bench	12.5%
Vals AI	GPT 5.4 Mini MMLU Pro	84.6%
Vals AI	GPT 5.4 Mini MMMU Pro	79.2%
Vals AI	GPT 5.4 Mini MortgageTax	63.5%
Vals AI	GPT 5.4 Mini ProgramBench	0.0%
Vals AI	GPT 5.4 Mini ProofBench v1	21.0%
Vals AI	GPT 5.4 Mini SAGE v1	50.8%
Vals AI	GPT 5.4 Mini SWE-bench	73.0%
Vals AI	GPT 5.4 Mini Tax Agent Bench	8.8%
Vals AI	GPT 5.4 Mini TaxEval v2	71.2%
Vals AI	GPT 5.4 Mini Terminal-Bench 4.0	2.5%
Vals AI	GPT 5.4 Mini Vals Index	33.2%
Vals AI	GPT 5.4 Mini Vals Multimodal Index	54.2%
Vals AI	GPT 5.4 Mini Vibe Code Bench v1.1	48.0%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

29.1Btokens

ai-copilot-prod

new

16.7Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

9.73Btokens

CoChat

CoChat is an AI research workspace: agents search peer-reviewed literature, verify every source, and organize your findings — from question to cited answer.

5.2Btokens

LangChain

new

4.2Btokens

Rest of OpenRouter

6.92B

Top 5 Apps

1.17B

OpenAI: GPT Mini versions

Not currently available through EU in-region routing. In-region routing docs

More models from OpenAI

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

Image$8 / $30

GPT Image 2.6 Flare

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Image$8 / $30

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.50 / $2.50

GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

Text1.1M context$1 / $5

GPT-6.1 Terra (batch)

Text1.1M context$0.50 / $2.50

GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Decisions$0.10 / $0

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

Text1.1M context$2 / $10

GPT-6.1 Sol (batch)

Text1.1M context$1 / $5

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.10 / $0.50

GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.05 / $0.25

GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

Text1.1M context$0.10 / $0.50

GPT-6 Luna (batch)

Text1.1M context$0.05 / $0.25

GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

Text1.1M context$2 / $10

GPT-6 Sol (batch)

Text1.1M context$1 / $5

GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

Text1.1M context

OpenAI: GPT-5.4 Mini

Providers