GPT-4.1 Mini

openaiopenai/gpt-4.1-mini

Smaller, faster version of GPT-4.1. Excels at instruction following and tool calling with a 1M token context window and low latency without a reasoning step.

GPT-4.1 announcement ↗API docs ↗

GPT-4.1 Mini is OpenAI's cost-efficient mid-tier model from the GPT-4.1 family, released April 2025. It delivers GPT-4o-class intelligence at roughly half the latency and one-sixth the cost, with a 1-million-token context window and improved instruction following.

In production it excels at instruction-tuned agent loops, long-context code analysis, customer-facing chat with tight latency SLAs, and structured data extraction. Its improved tool-calling reliability and diff-format compliance make it a strong choice for developer tooling pipelines.

Best for

• Cost-sensitive agent loops combining tool calling, structured outputs, and long-context retrieval
• Coding assistance with diff-format patches — reliable search/replace for large file edits
• Customer-facing chat applications where sub-second latency matters
• Long-document RAG pipelines — 1M tokens enable ingesting entire codebases or legal contracts

Reach for something else if

• Complex multi-step reasoning — route to o3, o4-mini, or GPT-5 for hard math/code reasoning
• Vision-heavy multimodal tasks — use GPT-5 or GPT-4.1 for better image understanding
• Ultra-high throughput classification — GPT-4.1 Nano offers even lower latency and cost

Context Length

1.0M

Max Output

33K

Input Priceper 1M tokens

$0.432/ 1M tokens

Output Priceper 1M tokens

$1.73/ 1M tokens

Modalities

textimage→text

Capabilities

Vision

Pricing Breakdown

Type	Rate
Input	$0.432 / 1M tokens
Output	$1.73 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

Specifications

Release date	2025-04-14openai.com ↗	verified
Training cutoff	June 2024openai.com ↗	verified
License	Proprietary via OpenAI APIopenai.com ↗	verified
Knowledge cutoff	June 2024openai.com ↗	verified

Benchmarks

Benchmark	Score	Source
MMLU	Matches GPT-4o	openai.com ↗
GPQA Diamond	Matches GPT-4o	openai.com ↗
IFEval GPT-4.1 family; exact Mini score not separately reported vs GPT-4o (81.0%)	~87.4%%	openai.com ↗

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL

curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "openai/gpt-4.1-mini",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'

API guide

Full API reference →

Chat completion

cURL

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4.1-mini","messages":[{"role":"user","content":"Hello"}]}'

More from openai

openai/gpt-4.1Full-sized GPT-4.1 with higher benchmark scores openai/gpt-4.1-nanoSmallest and fastest in the 4.1 family openai/gpt-4o-miniPrevious-gen mini model — replaced by GPT-4.1 Mini

Similar models

Cross-provider sibling models

google/gemini-2.5-flash

Comparable cost-efficient, low-latency model with 1M+ context

anthropic/claude-haiku-4.5

Fastest Anthropic model with strong tool use

meta/llama-4-maverick

Open-weight alternative for self-hosted use cases

News & changes

2025-04-14

GPT-4.1 family launched

OpenAI releases GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano with 1M-token context, improved coding and instruction following, and significantly lower cost than GPT-4o. GPT-4.1 Mini matches GPT-4o on intelligence evals at half the latency.

re-authored by TheRouteropenai.com ↗

Frequently asked

How does GPT-4.1 Mini compare to GPT-4o Mini?

GPT-4.1 Mini surpasses GPT-4o Mini on coding, instruction following, and long-context tasks. It supports up to 1M tokens (vs 128K) and costs less than GPT-4o Mini on a per-token basis. It is positioned as the replacement for GPT-4o Mini in the API.

re-authored by TheRouteropenai.com ↗

Is GPT-4.1 Mini available through ChatGPT?

No. GPT-4.1 Mini is API-only. OpenAI states that GPT-4o's ChatGPT experience will continue to improve with the GPT-4.1 family's gains, but the models themselves are API-only.

re-authored by TheRouteropenai.com ↗

Does GPT-4.1 Mini support structured outputs (JSON schema)?

Yes. GPT-4.1 Mini supports response_format with JSON schema (strict mode), parallel tool calling, and all standard OpenAI capabilities through the TheRouter API.

re-authored by TheRouteropenai.com ↗

Fact ledger — every claim on this page traces here

source	URL	retrieved
Release date	openai.com ↗	2026-05-28	verified
Training cutoff	openai.com ↗	2026-05-28	verified
License	openai.com ↗	2026-05-28	verified
Knowledge cutoff	openai.com ↗	2026-05-28	verified
MMLU	openai.com ↗	2026-05-28	verified
GPQA Diamond	openai.com ↗	2026-05-28	verified
IFEval	openai.com ↗	2026-05-28	to verify
GPT-4.1 family launched	openai.com ↗	2026-05-28	verified
How does GPT-4.1 Mini compare to GPT-4o Mini?	openai.com ↗	2026-05-28	to verify
Is GPT-4.1 Mini available through ChatGPT?	openai.com ↗	2026-05-28	to verify
Does GPT-4.1 Mini support structured outputs (JSON schema)?	openai.com ↗	2026-05-28	to verify