GPT-5 Mini

Released
2025-08-07
Last refreshed
2026-10-07
Status
Researched 193d ago
ProprietaryCommercial use: restrictedMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use
OpenAI releases · 49 in the last 12 months · this family litChangelog →
Specifications
Family
GPT-5
Released
2025-08-07
Context
400K
Max output
128K
Architecture
Decoder Only
Knowledge cutoff
2024-05
Specialization
general
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$2.00
Input / 1M
$0.250

Cheapest of 4 routes · OpenAI API · cache read $0.025

About

Near-frontier intelligence for cost-sensitive, low-latency, high-volume workloads. Released August 2025. Replaces o4-mini (shutting down Oct 2026).

Providers(4)

Compare all 4

Compare API pricing across 4 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
OpenAI API$0.250$2.00$0.125 / $1.00read $0.025
Serverless
OpenRouter$0.250$2.00-read $0.025
Serverless
Replicate API$0.250$2.00--
Serverless
Vercel AI Gateway$0.250$2.00-read $0.025
Serverless

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API

Benchmark peer barsfor JSON / Tool use

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
55.5v4Observed 2026-04-19—
1390.0text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26
Configuration: GPT-5 mini (High)
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'GPT-5 mini (High)': rank 179, Arena Score 1389.9 (95% CI 1385.3-1394.5), 26799 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1184.0vision_style_control overall 2026-10-19 (style control, default view)Observed 2026-10-26
Configuration: GPT-5 mini (High)
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena vision style control leaderboard, overall category, published 2026-10-19 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'GPT-5 mini (High)': rank 104, Arena Score 1184.3 (95% CI 1176.2-1192.4), 28943 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1325.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: GPT-5 mini (High)
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5 mini (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 197 of 416, rating 1325.1 (95% CI 1314.9-1335.3), 3522 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

Compare GPT-5 Mini with other models