Models / GPT-5.4ID: openai/gpt-5.4
reasoning model by OpenAI

GPT-5.4

High-efficiency OpenAI reasoning model with an expanded 1.05M token context window, suited for extensive codebases, deep reasoning, and computer-use tasks.

Certified & verified by nRouter· facts checked 2026-09-14 against 2 official sources

PlaygroundQuick Start
Context window1.05M
Max output128K
Maker

OpenAI

Served On

OpenAI

Specifications

Context window, ranked against other reasoning models

Proportional scale: 0 to 1.05M tokens. Not ranked, no published context window: gpt-5.5-pro, gpt-5.6-cyber, kimi-k2-thinking.

Context window

1.1M

Source: platform.openai.com
Max output

128K

Source: platform.openai.com
Modality

reasoning

Vision
Function calling
System prompt

Benchmarks & Performance Rankings

Empirical intelligence benchmarks and category leaderboard placements for GPT-5.4.

Compare in BenchmarksLeaderboard
Leaderboard Placements
#13
overallScore: 97.5%
Core Benchmark DimensionsSource: OpenAI Technical Report & LMSYS
MMLUKnowledge

91.5%

HumanEvalCoding

94%

Latency p50TTFT

340ms

p99: 920ms

ThroughputStream

98tok/s

SWE-bench: 56.5%

Recommended by nRouter Smart Routing: Production agent pipelines, automated code reviews, and structured data transformation. Key operational strength: Balanced high-accuracy reasoning with strong steerability and function calling precision.

Benchmarks

LMSYS Chatbot Arena (text)Rank #46 · Score 1466
Source: arena.ai · Leaderboard: 2026-09-112026-09-13

Pricing

Rates are read live

Pricing for gpt-5.4 is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Availability

Not enough data yet

We have not collected enough health probes for this model to publish an uptime or latency figure. A percentage from a handful of samples is fabricated precision, so none is shown until the sample count supports one.

How GPT-5.4 is billed

Billed at the provider's list price, with no per-token markup.

Exact list price
Tokens settle at the published rate of the model that served your call.
Cache discounts passed through
Provider prompt-caching discounts reach your balance with no added fee.
Cost on every response
Each response carries the x-nr-request-cost header, so you can reconcile spend per request.

More from OpenAI

gpt-5.6-lunagpt-5.5-progpt-4o-minigpt-4o-mini-tts-2025-12-15

Start building with gpt-5.4

One API key, three steps. Choose your tool to begin.

  1. Get a key

    Create API key

  2. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"

  3. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · openai/gpt-5.4
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with openai/gpt-5.4
claude --model openai/gpt-5.4