GPT-4.1 2025-04-14
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.
- Input / output price
- $2.00 / $8.00 per 1M
- Context
- 1M tokens
- Released
- Apr 14, 2025
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-4.1-2025-04-14 | $2.00/M | $8.00/M |
Is a provider down? ChatGPT status
Pricing
USD per 1M tokens on OpenAI, after gateway discounts.
- Input
- $2.00 per 1M
- Output
- $8.00 per 1M
- Cache read
- $0.50 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 better25tokens/sacross providers
Response latency
Lower is better0.6sacross providers
Benchmarks
The Respan Index plus 16 published scores from 5 sources, each linked to where it was published.
19.2/ 100
Respan Index#134 of 176
- 134GPT-4.119.2
- 132Claude Haiku 4.519.3
- 135NVIDIA Nemotron 3 Super 120B-A12B19.1
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedOpenAI | 54.6% | OpenAI | Apr 14, 2025 |
| SWE-bench VerifiedEpoch AI | 48.5% | Epoch AI | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 39% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 66.9% | Epoch AI | Oct 5, 2026 |
| GPQA DiamondOpenAI | 66.3% | OpenAI | Apr 14, 2025 |
| SimpleBenchSimpleBench | 27% | SimpleBench | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 11% | Epoch AI | Nov 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 83% | Epoch AI | Oct 5, 2026 |
| AIME 2024OpenAI | 48.1% | OpenAI | Apr 14, 2025 |
| OTIS Mock AIME 2024-2025Epoch AI | 38.3% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 6% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLUOpenAI | 90.2% | OpenAI | Apr 14, 2025 |
| SimpleQA VerifiedEpoch AI | 31.1% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Video-MME (long, no subtitles)OpenAI | 72% | OpenAI | Apr 14, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1415 Elo · #110 of 191 | LMArena | Oct 8, 2026 |
| LMArena VisionLMArena | 1214 Elo · #66 of 91 | LMArena | Oct 9, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
Compare GPT-4.1 2025-04-14: GPT-4.1 vs GPT-5, GPT-4.1 vs GPT-6.2 Astra, GPT-4.1 vs GPT-6 Astra, GPT-4.1 vs GPT-6.1 Sol, GPT-4.1 vs GPT-6.1 Terra, GPT-4.1 vs GPT-6.2 Sol
Apps
Use GPT-4.1 2025-04-14 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-4.1 2025-04-14 FAQ
Short answers, built from the data on this page.
GPT-4.1 2025-04-14 is a model from OpenAI, released on Apr 14, 2025. GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.
On the Respan gateway, GPT-4.1 2025-04-14 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens on OpenAI, after gateway discounts.
GPT-4.1 2025-04-14 is served by OpenAI.
GPT-4.1 2025-04-14 accepts up to 1M 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-4.1-2025-04-14". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GPT-4.1 2025-04-14 scores 19.2 out of 100 on the Respan Index v1.1, ranking #134 of 176 models. By category: Coding 3.8, Agents 11.9 (estimated), Reasoning 20.5, Knowledge & language 30.9, and Human preference 47.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
GPT-4.1 2025-04-14 has 16 published benchmark scores, including SWE-bench Verified 54.6%, GPQA Diamond 66.9%, and MATH Level 5 83%. 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.