Where is the GPT-5.4 documentation?

The GPT-5.4 documentation on OpenRouter includes the GPT-5.4 Migration Guide cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GPT-5.4 cost?

GPT-5.4 costs $2.50/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.25/M tokens.

What is the context length of GPT-5.4?

GPT-5.4 has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-5.4 support tool calling and structured outputs?

Yes. GPT-5.4 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 support?

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

Which providers serve GPT-5.4?

GPT-5.4 is served by 3 providers on OpenRouter: OpenAI, Azure, and Amazon Bedrock. 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 released?

GPT-5.4 was released on March 5, 2026.

OpenAI: GPT-5.4

openai/gpt-5.4

Compare

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.

The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

Modalities

In / out price

$2.50 / $15per 1M

Context

1.1M

Released

Mar 5, 2026

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


	$2.50	$15.00	$0.25	1.74s	50 tok/s	100.00%
	$2.50	$15.00	$0.25	4.47s	80 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$1.25	$7.50	$0.125	1.64s	18 tok/s	99.61%
	$2.75	$16.50	$0.275	--	--	100.00%
	$2.75	$16.50	$0.275	0.64s	72 tok/s	100.00%
	$2.75	$16.50	$0.275	2.99s	66 tok/s	--
Fast	$5.00	$30.00	$0.50	--	--	100.00%

Input $2.50Output $15.00
50 tok/s100.00% uptime
Input $2.50Output $15.00
80 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $1.25Output $7.50
Flex
18 tok/s99.61% uptime
Input $2.75Output $16.50
-- tok/s100.00% uptime
Input $2.75Output $16.50
72 tok/s100.00% uptime
Input $2.75Output $16.50
66 tok/s-- uptime
Input $5.00Output $30.00
Fast
-- 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

$1.081/M tokens

Output

$15.19/M tokens

GPT-5.4 — Price history

Price history

No effective price data for this selection

		$1.044	$15.11	66.3%	93.5%
		$1.504	$15.03	52.2%	4.5%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.823	$7.49	38.0%	0.3%
		$2.070	$16.50	27.5%	0.6%
		$2.174	$16.50	23.3%	0.8%
		$2.358	$16.50	15.8%	0.3%
	Fast	$3.357	$30.00	36.5%	0.0%

Effective in $1.044Effective out $15.11
Token share
93.5%
Effective in $1.504Effective out $15.03
Token share
4.5%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.823Effective out $7.49
FlexToken share
0.3%
Effective in $2.070Effective out $16.50
Token share
0.6%
Effective in $2.174Effective out $16.50
Token share
0.8%
Effective in $2.358Effective out $16.50
Token share
0.3%
Effective in $3.357Effective out $30.00
FastToken share
0.0%

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)

99.80%

Availability over the last 3 days

Last 72 hours

Availability 99.80%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.78%

Without Routing

98.33%

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 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-5.4 (Xhigh) Coding Index	71.1
Artificial Analysis	GPT-5.4 (Xhigh) GPQA Diamond	92.0%
Artificial Analysis	GPT-5.4 (Xhigh) HLE	43.7%
Artificial Analysis	GPT-5.4 (Xhigh) IFBench	73.9%
Artificial Analysis	GPT-5.4 (Xhigh) τ²-Bench Telecom	87.1%
Artificial Analysis	GPT-5.4 (Xhigh) AA-LCR	82.0%
Artificial Analysis	GPT-5.4 (Xhigh) τ-Bench Banking	39.6%
Artificial Analysis	GPT-5.4 (Xhigh) GDPval-AA	37.8%
Artificial Analysis	GPT-5.4 (Xhigh) CritPt	23.4%
Artificial Analysis	GPT-5.4 (Xhigh) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.4 (Xhigh) Terminal-Bench 2.1	78.3%
Artificial Analysis	GPT-5.4 (Low) GPQA Diamond	87.1%
Artificial Analysis	GPT-5.4 (Low) HLE	30.8%
Artificial Analysis	GPT-5.4 (Low) IFBench	65.9%
Artificial Analysis	GPT-5.4 (Low) τ²-Bench Telecom	74.6%
Artificial Analysis	GPT-5.4 (Low) AA-LCR	76.7%
Artificial Analysis	GPT-5.4 (Low) CritPt	7.4%
Artificial Analysis	GPT-5.4 (Low) Terminal-Bench Hard	43.2%
Artificial Analysis	GPT-5.4 (Non-reasoning) GPQA Diamond	74.8%
Artificial Analysis	GPT-5.4 (Non-reasoning) HLE	11.3%
Artificial Analysis	GPT-5.4 (Non-reasoning) IFBench	48.4%
Artificial Analysis	GPT-5.4 (Non-reasoning) τ²-Bench Telecom	36.0%
Artificial Analysis	GPT-5.4 (Non-reasoning) AA-LCR	58.3%
Artificial Analysis	GPT-5.4 (Non-reasoning) CritPt	0.6%
Artificial Analysis	GPT-5.4 (Non-reasoning) Terminal-Bench Hard	37.9%
Design Arena	GPT-5.4 (Medium) Models Arena 3D Elo	1080
Design Arena	GPT-5.4 (Medium) Models Arena Asciiart Elo	1194
Design Arena	GPT-5.4 (Medium) Models Arena Code Categories Elo	1199
Design Arena	GPT-5.4 (Medium) Models Arena Data Visualization Elo	1233
Design Arena	GPT-5.4 (Medium) Models Arena Game Development Elo	1228
Design Arena	GPT-5.4 (Medium) Models Arena SVG Elo	1186
Design Arena	GPT-5.4 (Medium) Models Arena UI Component Elo	1231
Design Arena	GPT-5.4 (Medium) Models Arena Website Elo	1207
Vals AI	GPT 5.4 (xhigh) AIME	96.7%
Vals AI	GPT 5.4 (xhigh) CaseLaw v2	63.8%
Vals AI	GPT 5.4 (xhigh) Code Migration	35.0%
Vals AI	GPT 5.4 (xhigh) CorpFin v2	65.3%
Vals AI	GPT 5.4 (xhigh) Finance Agent v1.1	57.2%
Vals AI	GPT 5.4 (xhigh) GPQA Diamond	91.7%
Vals AI	GPT 5.4 (xhigh) Harvey's Legal Agent Benchmark v1	0.0%
Vals AI	GPT 5.4 (xhigh) IOI v1	67.8%
Vals AI	GPT 5.4 (xhigh) LiveCodeBench	84.1%
Vals AI	GPT 5.4 (xhigh) LegalBench	86.0%
Vals AI	GPT 5.4 (xhigh) MedCode	41.3%
Vals AI	GPT 5.4 (xhigh) MedQA	96.1%
Vals AI	GPT 5.4 (xhigh) MedScribe	77.5%
Vals AI	GPT 5.4 (xhigh) MMLU Pro	87.5%
Vals AI	GPT 5.4 (xhigh) MMMU Pro	87.5%
Vals AI	GPT 5.4 (xhigh) MortgageTax	68.3%
Vals AI	GPT 5.4 (xhigh) ProgramBench	0.0%
Vals AI	GPT 5.4 (xhigh) ProofBench v1	56.0%
Vals AI	GPT 5.4 (xhigh) SAGE v1	43.3%
Vals AI	GPT 5.4 (xhigh) SkillsBench	51.7%
Vals AI	GPT 5.4 (xhigh) SWE-bench	78.2%
Vals AI	GPT 5.4 (xhigh) TaxEval v2	74.0%
Vals AI	GPT 5.4 (xhigh) Terminal-Bench 2.0	58.4%
Vals AI	GPT 5.4 (xhigh) Vals Index	66.1%
Vals AI	GPT 5.4 (xhigh) Vals Multimodal Index	65.2%
Vals AI	GPT 5.4 (xhigh) Vibe Code Bench v1.1	67.4%

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.

Lumea CRM

new

10.4Btokens

Codex

A coding agent that helps you build and ship with AI

7.87Btokens

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.

7.63Btokens

Trading View

new

4.93Btokens

direct_vq_compact_validator

new

3.4Btokens

Rest of OpenRouter

5.64B

Top 5 Apps

425M

Available through EU in-region routing

OpenAI: GPT-5.4 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Azure

Prices in Europe

Azure: $2.75/M tokens input, $16.50/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. 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

Providers