OpenAI

GPT-4.1 Nano

Tool callingStructured outputImage input

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Context
1.0M
Released
1y ago
Input / 1M tokens
$0.10
Output / 1M tokens
$0.40
Cached input / 1M tokens
$0.02

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer
OpenAI
Model family
GPT
Type
Language model
Predecessor
—
Successor
—
Released
April 14, 2025
Model ID
openai/gpt-4.1-nano
Openness
Closed
License
—
Input modalities
image, text, file
Output modalities
text
Modality
text+image+file->text
Tokenizer
GPT
Max output tokens
33K
Knowledge cutoff
2024-04
Hugging Face
—
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
openai/gpt-4.1-nano
Source family
gpt-nano
Last updated
2025-04-14
Knowledge cutoff
2024-04
Model context
1.0M
Model output limit
33K
Open weights
No
File attachments
Yes
Reasoning
No
Tool calling
Yes
Structured output
Yes
Temperature control
Yes

Published benchmarks

BenchmarkScoreEvaluation detailsEvidence
Aider Polyglot8.9 · percent correct2025-04-14Source
Complete source record (JSON)
{
  "id": "openai/gpt-4.1-nano",
  "name": "GPT-4.1 nano",
  "description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
  "family": "gpt-nano",
  "last_updated": "2025-04-14",
  "knowledge": "2024-04",
  "attachment": true,
  "reasoning": false,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1047576,
    "output": 32768
  },
  "benchmarks": [
    {
      "name": "Aider Polyglot",
      "score": 8.9,
      "source": "https://aider.chat/docs/leaderboards/",
      "metric": "percent correct",
      "date": "2025-04-14"
    }
  ],
  "release_date": "2025-04-14",
  "open_weights": false
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Azureazure1.0M$0.10$0.40$0.03—98.06%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

AzureazureBatch pricing1.0M$0.10$0.40$0.03—97.52%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

OpenAIopenai1.0M$0.10$0.40$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

OpenAIopenaiBatch pricing1.0M$0.10$0.40$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/swedencentral1.0M$0.11$0.44$0.03—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/swedencentralBatch pricing1.0M$0.11$0.44$0.03—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation