How much does GPT-5.1-Codex-Mini cost?

GPT-5.1-Codex-Mini costs $0.25 per million input tokens and $2.00 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.003 per message.

What benchmarks has GPT-5.1-Codex-Mini been tested on?

GPT-5.1-Codex-Mini has been evaluated on 8 benchmarks. Top scores: LiveBench — Mathematics: 76.3, LiveBench — Coding: 69.9, LiveBench — Reasoning: 64.7.

Is GPT-5.1-Codex-Mini open source?

No, GPT-5.1-Codex-Mini is a proprietary model by OpenAI.

How does GPT-5.1-Codex-Mini compare to Qwen2 VL 7B Instruct?

GPT-5.1-Codex-Mini has an average score of 67.4 while Qwen2 VL 7B Instruct scores 67.6. Qwen2 VL 7B Instruct slightly outperforms GPT-5.1-Codex-Mini overall. See full comparison →

Home/Models/GPT-5.1-Codex-Mini

GPT-5.1-Codex-Mini

Name: GPT-5.1-Codex-Mini
Price: 0.25 USD
Author: OpenAI

by OpenAI · Released Nov 2025

Multimodal

67.4

avg score

Rank #46

Compare

Better than 80% of all models

Context

400K tokens (~200 books)

Input $/1M

$0.25

Output $/1M

$2.00

Type

multimodal

License

Proprietary

Benchmarks

8 tested

Data updated today

About

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

Tested on 8 benchmarks with 60.4% average. Top scores: LiveBench — Mathematics (76.3%), LiveBench — Coding (69.9%), LiveBench — Reasoning (64.7%).

Looking for similar performance at lower cost?
Gemma 4 31B scores 68.2 (101% as good) at $0.13/1M input · 48% cheaper

Capabilities

coding

55.0

#54 globally

reasoning

57.2

#37 globally

math

76.3

#23 globally

knowledge

60.4

#46 globally

language

61.0

#83 globally

Benchmark Scores

Compare All

Tested on 8 benchmarks · Ranked across 5 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

codingCompare coding →

LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

69.9—

LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

40.0—

reasoningCompare reasoning →

LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

64.7—

LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

49.7—

mathCompare math →

LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

76.3—

Quick compare:

vs Qwen2 VL 7B Instruct

vs Gemini 2.5 Pro

vs Grok 3 Beta

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · OpenAI GPT-5.1

GPT-5.1Nov 2025

49.6

$1.25/M in400Kctx24 benchmarks

GPT-5.1 ChatNov 2025

$1.25/M in128Kctx(-272K)

GPT-5.1-CodexNov 2025

68.6+68.6

$1.25/M in400Kctx(+272K)8 benchmarks

GPT-5.1-Codex-MaxDec 2025

72.0+3.4

$1.25/M in400Kctx8 benchmarks

GPT-5.1-Codex-MiniNov 2025

60.4-11.6

$0.25/M in(-1)400Kctx8 benchmarks

See the full GPT-5.1 family →

Similar Models

Links

Info

OpenAI Pricing explorer Developers · API

Research

Technical Report

Documentation

API Docs Playground

Community

@OpenAI

BenchGecko API

gpt-5-1-codex-mini

Specifications

Typemultimodal
Context400K tokens (~200 books)
ReleasedNov 2025
LicenseProprietary
StatusActive
Cost / Message~$0.003

Available On

OpenAI$0.25

Frequently Asked Questions

GPT-5.1-Codex-Mini is a proprietary multimodal AI model by OpenAI, released in November 2025. It has an average benchmark score of 67.4. Context window: 400K tokens.

Benchmarks

LiveBench — Mathematics LiveBench — Coding LiveBench — Reasoning LiveBench — Language LiveBench — Overall

OpenAI · Provider OpenAI · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

GPT-5.1-Codex-Mini

Frequently Asked Questions

Related Models

Benchmarks

Related Pages