GPT-5.4 Mini 2026-03-17
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.
- Input / output price
- $0.75 / $4.50 per 1M
- Context
- 400K tokens
- Released
- Mar 17, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
OpenAI openai/gpt-5.4-mini-2026-03-17 | $0.75/M | $4.50/M |
Is a provider down? ChatGPT status
Pricing
USD per 1M tokens on OpenAI, after gateway discounts.
- Input
- $0.75 per 1M
- Output
- $4.50 per 1M
- Cache read
- $0.075 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better76tokens/sacross providers
Response latency
Lower is better1.5sacross providers
Benchmarks
The Respan Index plus 25 published scores from 6 sources, each linked to where it was published.
34.2/ 100
Respan Index#82 of 176
- 82GPT-5.4 mini34.2
- 81GPT-5.134.6
- 83DeepSeek-V4-Flash (Preview)32.2
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench CodingLiveBench | 71.6% | LiveBench | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 60.3% | Håvard Tveit Ihle | Oct 5, 2026 |
| Terminal-Bench 2.0OpenAI | 60% | OpenAI | Mar 17, 2026 |
| SWE-Bench ProOpenAI | 54.4% | OpenAI | Mar 17, 2026 |
| Terminal-Bench 4.0Vals AI | 2.5% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OSWorld-VerifiedOpenAI | 72.1% | OpenAI | Mar 17, 2026 |
| ToolathlonOpenAI | 42.9% | OpenAI | Mar 17, 2026 |
| LiveBench Agentic CodingLiveBench | 41.7% | LiveBench | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondOpenAI | 88% | OpenAI | Mar 17, 2026 |
| GPQA DiamondEpoch AI | 86.9% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 71.3% | LiveBench | Oct 5, 2026 |
| LiveBench Data AnalysisLiveBench | 70.8% | LiveBench | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 23% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 11% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 88.9% | Epoch AI | Oct 5, 2026 |
| LiveBench MathematicsLiveBench | 78.5% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 51.2% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 9.8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 71% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 59.8% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 29.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1447 Elo · #69 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1398 Elo · #90 of 124 | LMArena | Nov 20, 2026 |
| LMArena VisionLMArena | 1250 Elo · #45 of 91 | LMArena | Nov 19, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
Compare GPT-5.4 Mini 2026-03-17: GPT-5.4 mini vs GPT-5 mini, GPT-5.4 mini vs GPT-6.2 Astra, GPT-5.4 mini vs GPT-6 Astra, GPT-5.4 mini vs GPT-6.1 Sol, GPT-5.4 mini vs GPT-6.1 Terra, GPT-5.4 mini vs GPT-6.2 Sol
Apps
Use GPT-5.4 Mini 2026-03-17 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
GPT-5.4 Mini 2026-03-17 FAQ
Short answers, built from the data on this page.
GPT-5.4 Mini 2026-03-17 is a model from OpenAI, released on Mar 17, 2026. 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.
On the Respan gateway, GPT-5.4 Mini 2026-03-17 costs $0.75 per 1M input tokens and $4.50 per 1M output tokens on OpenAI, after gateway discounts.
GPT-5.4 Mini 2026-03-17 is served by OpenAI.
GPT-5.4 Mini 2026-03-17 accepts up to 400K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "openai/gpt-5.4-mini-2026-03-17". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GPT-5.4 Mini 2026-03-17 scores 34.2 out of 100 on the Respan Index v1.1, ranking #82 of 176 models. By category: Coding 13.1, Agents 48.7, Reasoning 32.6, Knowledge & language 28.9, and Human preference 51.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
GPT-5.4 Mini 2026-03-17 has 25 published benchmark scores, including LiveBench Coding 71.6%, OSWorld-Verified 72.1%, and GPQA Diamond 88%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.