Skip to main content

GPT-4.1 Mini 2025-04-14

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.

Input / output price
$0.40 / $1.60 per 1M
Context
1M tokens
Released
Apr 14, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "openai/gpt-4.1-mini-2025-04-14".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
OpenAIopenai/gpt-4.1-mini-2025-04-14
$0.40/M$1.60/M

Is a provider down? ChatGPT status

Pricing

USD per 1M tokens on OpenAI, after gateway discounts.

Input
$0.40 per 1M
Output
$1.60 per 1M
Cache read
$0.10 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.40/MOpenAI

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 better

64tokens/sacross providers

Faster than 69% of the other 599 models on the gateway

Response latency

Lower is better

1.2sacross providers

Faster than 64% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 13 published scores from 4 sources, each linked to where it was published.

15.3/ 100

Respan Index#159 of 176

176 ranked models. The shaded band is this model's 95% interval, 12.6 to 21.0. NVIDIA Nemotron 3 Nano 30B-A3B BF16 and QwQ-32B fall inside it, so the gap is within the margin of error.
GPT-4.1 Mini 2025-04-14 by category: Coding 4.0, Agents 7.1 (estimated), Reasoning 18.8, Knowledge & language 12.6, Human preference 43.9
  1. 159GPT-4.1 mini15.3
  2. 158NVIDIA Nemotron 3 Nano 30B-A3B BF1615.6
  3. 160QwQ-32B15.0

Published scores

BenchmarkScore
WeirdMLHåvard Tveit Ihle37.6%

Compare GPT-4.1 Mini 2025-04-14: GPT-4.1 mini vs GPT-5 mini, GPT-4.1 mini vs GPT-6.2 Astra, GPT-4.1 mini vs GPT-6 Astra, GPT-4.1 mini vs GPT-6.1 Sol, GPT-4.1 mini vs GPT-6.1 Terra, GPT-4.1 mini vs GPT-6.2 Sol

Apps

Use GPT-4.1 Mini 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 Mini 2025-04-14 FAQ

Short answers, built from the data on this page.

GPT-4.1 Mini 2025-04-14 is a model from OpenAI, released on Apr 14, 2025. GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.

On the Respan gateway, GPT-4.1 Mini 2025-04-14 costs $0.40 per 1M input tokens and $1.60 per 1M output tokens on OpenAI, after gateway discounts.

GPT-4.1 Mini 2025-04-14 is served by OpenAI.

GPT-4.1 Mini 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-mini-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 Mini 2025-04-14 scores 15.3 out of 100 on the Respan Index v1.1, ranking #159 of 176 models. By category: Coding 4.0, Agents 7.1 (estimated), Reasoning 18.8, Knowledge & language 12.6, and Human preference 43.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GPT-4.1 Mini 2025-04-14 has 13 published benchmark scores, including WeirdML 37.6%, GPQA Diamond 65.8%, and MATH Level 5 87.3%. 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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.