GPT-5.4 mini Official Specifications, Pricing & Benchmarks
GPT-5.4 mini (gpt-5.4-mini) by OpenAI, released 2026-03-17, featuring 400,000 context window, 128,000 max output tokens, and Text+Image input.
📋 GPT-5.4 mini Official API & System Card Specifications
Verified against official OpenAI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- gpt-5.4-mini
- Release Date
- 2026-03-17
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 400,000 tokens (400K)
- Max Output Tokens
- 128,000 tokens
- Input Modalities
- Text + Image
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.75
- Cached Input / 1M
- $ 0.075 -90%
- Output / 1M Tokens
- $ 4.5
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 GPT-5.4 mini Full Benchmark Scorecard
19 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 3 items
Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal.
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
🤖 Agents & Tools 5 items
τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.
OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work.
👁️ Multimodal 2 items
OmniDocBench 1.5 is a comprehensive benchmark for evaluating multimodal large language models on document understanding tasks, including OCR, document parsing, information extraction, and visual question answering across diverse document types.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings.
📜 Long Context 2 items
MRCR v2 (Multi-Round Coreference Resolution version 2) is an enhanced version of the synthetic long-context reasoning task.
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
🧠 Reasoning & Science 5 items
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length under 128k tokens, returning nodes reachable at specified depths.
A graph reasoning benchmark that evaluates language models' ability to find parent nodes in graphs with context length under 128k tokens, requiring understanding of graph structure and edge relationships.
MultiChallenge is a realistic multi-turn conversation evaluation benchmark that challenges frontier LLMs across four key categories: instruction retention (maintaining instructions throughout conversations), inference memory (recalling and connecting details from previous…
A benchmark evaluating language models' ability to generate factually accurate and well-grounded responses based on long-form input context, comprising 1,719 examples with documents up to 32k tokens requiring detailed responses that are fully grounded in provided documents.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to GPT-5.4 mini
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is GPT-5.4 mini open-source or proprietary?
GPT-5.4 mini (gpt-5.4-mini) is a proprietary commercial model by OpenAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of GPT-5.4 mini?
GPT-5.4 mini supports 400K input context and 128,000 max output tokens, priced at $0.75/1M input ($0.075/1M cached) and $4.5/1M output.