The AI arena is free today

Open Superagent

Devstral Medium vs GPT-4.1 nano

Devstral Medium leads the LLM Stats Score 13.6 to 1.6. GPT-4.1 nano is 4.6x cheaper per token.

Mistral AI · OpenAI · Updated for 2026

Which is better?

Devstral Medium leads the overall LLM Stats Score 13.6 to 1.6, ranking #243 overall.

On price, GPT-4.1 nano is roughly 4.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-4.1 nano also accepts a larger context window (1,047,576 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Devstral Medium

  • overall performance matters — it scores 13.6 and ranks #243 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Jul 2025

Choose GPT-4.1 nano

  • cost matters — it's about 4.6x cheaper per token
  • you process long inputs — it offers a 1,047,576 token context window

At a glance

The differences that matter most.

Core performance indexes
13.6
#243
1.6
#320
13.5
#236
2.0
#308
5.3
#200
-11.8
#266
Cost, coverage & limits
Benchmark wins
Input price
$0.40 / M
$0.10 / M
Output price
$2.00 / M
$0.40 / M
Context window
128,000
1,047,576

Individual benchmarks

1 reported for Devstral Medium · 24 for GPT-4.1 nano

No common benchmarks found

Devstral Medium and GPT-4.1 nanodon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

GPT-4.1 nano costs less

For input processing, Devstral Medium ($0.40/1M tokens) is 4.0x more expensive than GPT-4.1 nano ($0.10/1M tokens).

For output processing, Devstral Medium ($2.00/1M tokens) is 5.0x more expensive than GPT-4.1 nano ($0.40/1M tokens).

In conclusion, Devstral Medium is more expensive than GPT-4.1 nano.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
Mistral AI
Devstral Medium
Input tokens$0.40
Output tokens$2.00
Best providerMistral
OpenAI
GPT-4.1 nano
Input tokens$0.10
Output tokens$0.40
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-4.1 nano accepts 1,047,576 input tokens compared to Devstral Medium's 128,000 tokens. Devstral Medium can generate longer responses up to 128,000 tokens, while GPT-4.1 nano is limited to 32,768 tokens.

Mistral AI
Devstral Medium
Input128,000 tokens
Output128,000 tokens
OpenAI
GPT-4.1 nano
Input1,047,576 tokens
Output32,768 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-4.1 nano supports multimodal inputs, whereas Devstral Medium does not.

GPT-4.1 nano can handle both text and other forms of data like images, making it suitable for multimodal applications.

Devstral Medium

Text
Images
Audio
Video

GPT-4.1 nano

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Devstral Medium

Proprietary

Closed source

GPT-4.1 nano

Proprietary

Closed source

Release Timeline

When each model was launched

Devstral Medium was released on 2025-07-10, while GPT-4.1 nano was released on 2025-04-14.

Devstral Medium is 3 months newer than GPT-4.1 nano.

Devstral Medium

Jul 10, 2025

1.2 years ago

2mo newer
GPT-4.1 nano

Apr 14, 2025

1.4 years ago

Knowledge Cutoff

When training data ends

GPT-4.1 nano has a documented knowledge cutoff of 2024-05-31, while Devstral Medium's cutoff date is not specified.

We can confirm GPT-4.1 nano's training data extends to 2024-05-31, but cannot make a direct comparison without Devstral Medium's cutoff date.

Devstral Medium

GPT-4.1 nano

May 2024

Provider Availability

Devstral Medium is available from Mistral AI. GPT-4.1 nano is available from OpenAI.

Devstral Medium

mistral logo
Mistral
Input Price:Input: $0.40/1MOutput Price:Output: $2.00/1M

GPT-4.1 nano

openai logo
OpenAI
Input Price:Input: $0.10/1MOutput Price:Output: $0.40/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Devstral Medium and GPT-4.1 nano side-by-side, then vote on the output you prefer.

Devstral Medium
✓ Preferred
GPT-4.1 nano
Open in Playground

FAQ

Common questions about Devstral Medium vs GPT-4.1 nano.

Which is better, Devstral Medium or GPT-4.1 nano?

Devstral Medium leads the LLM Stats Score 13.6 to 1.6. Devstral Medium is made by Mistral AI and GPT-4.1 nano is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Devstral Medium compare to GPT-4.1 nano in benchmarks?

Devstral Medium scores SWE-Bench Verified: 61.6%. GPT-4.1 nano scores MMLU: 80.1%, IFEval: 74.5%, CharXiv-D: 73.9%, MMMLU: 66.9%, Multi-IF: 57.2%.

Is Devstral Medium cheaper than GPT-4.1 nano?

GPT-4.1 nano is 4.0x cheaper for input tokens. Devstral Medium costs $0.40/M input and $2.00/M output via mistral. GPT-4.1 nano costs $0.10/M input and $0.40/M output via openai.

What are the context window sizes for Devstral Medium and GPT-4.1 nano?

Devstral Medium supports 128K tokens and GPT-4.1 nano supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Devstral Medium and GPT-4.1 nano?

Key differences include LLM Stats Score (13.6 vs 1.6), context window (128K vs 1.0M), input pricing ($0.40 vs $0.10/M), multimodal support (no vs yes). See the full comparison above for benchmark-by-benchmark results.

Who makes Devstral Medium and GPT-4.1 nano?

Devstral Medium is developed by Mistral AI and GPT-4.1 nano is developed by OpenAI.