OpenAI · Efficient
GPT 5.1 Codex Mini
Lightweight GPT-5.1 Codex path.
- Reasoning
- Vision
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.25
- Output
- $2.00
- Cache read
- $0.025
Reference prices as published by the model provider. API example
Specifications
- Context window
- 400K
- Max output
- 128K
- Average output (7 days)
- 136 tokens
- Longer than 14% of 468 models
Side by side
GPT 5.1 Codex Mini compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GPT 5.1 Codex MiniOpenAIThis model | GPT 6 LunaOpenAIRemove | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Discovery tier | Efficient | Efficient |
| Added | Nov 13, 2025 | Sep 22, 2026 |
| Limits | ||
| Context window | 400K | 1.05MBest |
| Max output | 128K | 128K |
| Average output | 136 tokens | 120 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.25 | $0.10Best |
| Output | $2.00 | $0.50Best |
| Cache read | $0.025 | $0.01Best |
| Cache write | — | $0.13 |
| Performance | ||
| Throughput | — | 77.0 tok/s |
| Time to first token | — | 6.8 s |
| Request success (24h) | — | 99.7% |
| Benchmark indexes | ||
| Intelligence Index | 20.4 | 29.9Best |
| Math Index | 91.7 | — |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | No | Yes |
| Vision | Yes | Yes |
| Structured output | No | Yes |
| PDF input | No | Yes |
| Reasoning effort | — | none, low, medium, high, xhigh, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GPT 5.1 Codex Mini
- GPT 6 Luna
Intelligence Index
- GPT 5.1 Codex Mini20.4
- GPT 6 Luna29.9
GPT 5.1 Codex Mini tested at high reasoning effort
GPT 5.1 Codex Mini: Better than 50% of 326 scored models
Indexes
Math Index
Composite of the math evaluations
- GPT 5.1 Codex Mini: 91.7
- GPT 6 Luna: —
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 40.5%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 10.2%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 1,097 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 1,263 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 13.8%
AA-LCRv1.1
Reasoning across long documents
- GPT 5.1 Codex Mini: 66.7%
- GPT 6 Luna: 78.3%Top
MLCR-AA
Long-context reasoning over medical records
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 18.3%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GPT 5.1 Codex Mini: 18.5%
- GPT 6 Luna: 28.3%Top
GPQA Diamond
Graduate-level science questions
- GPT 5.1 Codex Mini: 81.3%
- GPT 6 Luna: —
MMLU-Pro
Multi-subject knowledge and reasoning
- GPT 5.1 Codex Mini: 82.0%
- GPT 6 Luna: —
IFBench
Following precise output instructions
- GPT 5.1 Codex Mini: 67.9%
- GPT 6 Luna: —
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 2.5%
SciCode
Scientific computing in Python
- GPT 5.1 Codex Mini: —
- GPT 6 Luna: 50.9%
LiveCodeBench
Recent competitive programming problems
- GPT 5.1 Codex Mini: 83.6%
- GPT 6 Luna: —
Math
AIME 2025
Competition mathematics, 2025 problems
- GPT 5.1 Codex Mini: 91.7%
- GPT 6 Luna: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- GPT 5.1 Codex Mini: 33.3%
- GPT 6 Luna: —
τ²-Bench Telecom
Tool use in a customer-support simulation
- GPT 5.1 Codex Mini: 62.9%
- GPT 6 Luna: —
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GPT 5.1 Codex Mini: 66.7%
- GPT 6 Luna: 78.3%Top
Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5.1 Codex Mini was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis
- GPT 5.1 Codex Mini
- GPT 6 Luna
| Leaderboard | GPT 5.1 Codex Mini | GPT 6 Luna |
|---|---|---|
| ARC-AGI-3 (Default harness) | Not in top 20 | #18 · 0.2% |
Ranks among Noumen catalog models on ARC Prize leaderboards. Only top-20 placements are listed.ARC Prize
- GPT 5.1 Codex Mini
- GPT 6 Luna
| Leaderboard | GPT 5.1 Codex Mini | GPT 6 Luna |
|---|---|---|
| SVG | Not in top 20 | #16 · 1250 |
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.1-codex-mini",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="openai/gpt-5.1-codex-mini",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)OpenAI
Related models
Other OpenAI models, starting with the same family.