OpenAI
·Released on Dec 17, 2024

O1 API Benchmarks, Pricing & Provider Data

Compare O1 with another model

Choose a model to open its comparison page.

Share on X
LLM

O1 benchmark, API pricing, and provider data cover 1018 API providers, with prices starting at $0.033/request. O1 free API options are available from 1 provider.

OpenAI O1 is a reasoning model in the O series, designed for complex reasoning, problem-solving, and analytical tasks.

Quality
#36of 102
0.0
LMSpeed score
Cost
#177of 184
$0.033/ 1M · 8:1 in:out
$0.0053 in · $0.028 out

Category Performance

Observed-capability estimates with uncertainty reported separately from independent benchmark families.

Coverage
6 / 8
Methodology
V3.0
Category PerformanceObserved-capability estimates with uncertainty reported separately from independent benchmark families.Agents45.5Coding50.5Reasoning50.7Knowledge62.5Math52.6Multilingual-Multimodal-Instruction following51.5
#1Knowledge62.5Provisional1/4 Measured dimensions
80% interval: 45.079.9
broad knowledge62.5
mmlu · mmlu
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#2Math52.6Estimated3/4 Measured dimensions
80% interval: 43.361.9
foundational math53.1
math_500 · math_500
competition math56.9
aime · aime
proof frontier47.7
frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#3Instruction following51.5Estimated2/4 Measured dimensions
80% interval: 39.663.4
constraint following50.4
ifeval · ifeval
structured outputPrior only
novel instruction generalization52.6
ifbench · aa_if_bench
long multiturn instructionPrior only
#4Reasoning50.7RatedGlobal rank #403/4 Measured dimensions
80% interval: 42.059.3
abstract logicPrior only
scientific causal46.5
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraints56
mmlu_pro · mmlu_pro
evidence verification49.5
lcr · lcr
#5Coding50.5Provisional1/4 Measured dimensions
80% interval: 36.664.4
code generation50.5
livecodebench · livecodebench / scicode · scicode
repository engineeringPrior only
debugging testingPrior only
tooling qualityPrior only
#6Agents45.5Provisional1/4 Measured dimensions
80% interval: 29.561.5
planningPrior only
tool use45.5
tau · tau2_bench
environment executionPrior only
recovery reliabilityPrior only
No data:MultilingualMultimodal

Specifications

Input and output token limits for this model, plus how it ranks on long-context understanding.

INPUT
200Ktokens
240 pages of text
OUTPUT
100Ktokens
8K128K1M4M
200K

Features

Technical Details

Input
Output
Released
Dec 2024
Knowledge cutoff
2023-10-31
Documentation
Tokenizer
GPT
Architecture
text+image+file->text
Moderated
Yes
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools

Rankings

Excels at

Falls behind in

Detailed scores

Updated: Sep 4, 2026

Pricing

undefined metric} other undefined metrics}}

Input price$15.00/M#177 / 184Output price$60.00/M#177 / 184
Input price
LMSpeed rank#177
Score$15.00/M
UpdatedSep 4, 2026
Confidence4
Output price
LMSpeed rank#177
Score$60.00/M
UpdatedSep 4, 2026
Confidence4

Agents

V3.0

undefined metric} other undefined metrics}} · Provisional

Score45.580% interval29.5–61.51/4 Measured dimensionsΤ²-bench results62.6#61 / 82
Dimensions and evidence
Planning & decompositionPrior only
Tool use45.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z -0.71 · q 1.00
Environment & long-horizon executionPrior only
Recovery & completion reliabilityPrior only
Τ²-bench resultsV3 evidence
LMSpeed rank#61
Score62.6
UpdatedAug 20, 2026
Confidence1

Coding

V3.0

undefined metric} other undefined metrics}} · Provisional

Score50.580% interval36.6–64.41/4 Measured dimensionsLiveCodeBench67.9%#34 / 115SciCode35.8%#127 / 209
Dimensions and evidence
Code generation50.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 0.53 · q 1.00
scicode · scicode · z -0.21 · q 1.00
Repository engineeringPrior only
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
LiveCodeBenchV3 evidence
LMSpeed rank#34
Score67.9%
UpdatedSep 4, 2026
Confidence4
SciCodeV3 evidence
LMSpeed rank#127
Score35.8%
UpdatedSep 4, 2026
Confidence4
AA Coding Index
LMSpeed rank#55
Score34.0
UpdatedAug 20, 2026
Confidence1
AA-SciCodeV3 evidence
LMSpeed rank#87
Score35.8
UpdatedAug 20, 2026
Confidence1

Reasoning

V3.0

undefined metric} other undefined metrics}} · Rated

Score50.7#4080% interval42.0–59.33/4 Measured dimensionsMMLU-Pro84.1%#34 / 129GPQA74.7%#123 / 216
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning46.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z -0.72 · q 1.00
gpqa · gpqa · z -0.05 · q 1.00
hle · hle · z -0.50 · q 1.00
Multi-step constraints56
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.59 · q 1.00
Evidence integration & verification49.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z -0.43 · q 1.00
MMLU-ProV3 evidence
LMSpeed rank#34
Score84.1%
UpdatedSep 4, 2026
Confidence4
GPQAV3 evidence
LMSpeed rank#123
Score74.7%
UpdatedSep 4, 2026
Confidence4
HLEV3 evidence
LMSpeed rank#139
Score7.0%
UpdatedSep 4, 2026
Confidence4
AA-LCRV3 evidence
LMSpeed rank#73
Score63.3
UpdatedAug 20, 2026
Confidence1
CritPtV3 evidence
LMSpeed rank#79
Score0.3
UpdatedAug 20, 2026
Confidence1

Knowledge

V3.0

undefined metric} other undefined metrics}} · Provisional

Score62.580% interval45.0–79.91/4 Measured dimensionsArtificial Analysis Intelligence Index17.2#91 / 112Knowledge score64.0#44 / 70
Dimensions and evidence
Broad knowledge62.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu · mmlu · z 1.93 · q 0.21
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Artificial Analysis Intelligence Index
LMSpeed rank#91
Score17.2
UpdatedAug 20, 2026
Confidence1
Knowledge score
LMSpeed rank#44
Score64.0
UpdatedAug 20, 2026
Confidence1
MMLUV3 evidence
LMSpeed rank#1
Score91.8
UpdatedAug 20, 2026
Confidence1
AA-GPQA Diamond
LMSpeed rank#85
Score74.7
UpdatedAug 20, 2026
Confidence1
AA-HLE
LMSpeed rank#86
Score7.0
UpdatedAug 20, 2026
Confidence1
AA-Omniscience Accuracy
LMSpeed rank#44
Score34.5
UpdatedAug 20, 2026
Confidence1
AA-Omniscience Hallucination Rate
LMSpeed rank#55
Score69.6
UpdatedAug 20, 2026
Confidence1

Math

V3.0

undefined metric} other undefined metrics}} · Estimated

Score52.680% interval43.3–61.93/4 Measured dimensionsAIME72.3%#19 / 68MATH-50097.0%#13 / 73
Dimensions and evidence
Foundational math53.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
math_500 · math_500 · z 0.44 · q 1.00
Competition math56.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aime · aime · z 0.90 · q 1.00
Advanced proofs47.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tiers13 · z -0.65 · q 1.00
Applied & tool-assisted mathPrior only
AIMEV3 evidence
LMSpeed rank#19
Score72.3%
UpdatedSep 4, 2026
Confidence4
MATH-500V3 evidence
LMSpeed rank#13
Score97.0%
UpdatedSep 4, 2026
Confidence4
Math score
LMSpeed rank#48
Score32.6
UpdatedAug 20, 2026
Confidence1
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#34
Score9.3
UpdatedAug 20, 2026
Confidence1

Multilingual

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only

Multimodal

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only

Instruction following

V3.0

undefined metric} other undefined metrics}} · Estimated

Score51.580% interval39.6–63.42/4 Measured dimensionsInstruction Following score86.1#15 / 25IFEval92.2#10 / 16
Dimensions and evidence
Constraint following50.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifeval · ifeval · z -0.15 · q 1.00
Structured outputPrior only
Novel-instruction generalization52.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.07 · q 1.00
Multi-turn & long instructionsPrior only
Instruction Following score
LMSpeed rank#15
Score86.1
UpdatedAug 20, 2026
Confidence1
IFEvalV3 evidence
LMSpeed rank#10
Score92.2
UpdatedAug 20, 2026
Confidence1
AA-IFBenchV3 evidence
LMSpeed rank#35
Score70.3
UpdatedAug 20, 2026
Confidence1

OpenRouter endpoints

1 endpoints

Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.

Provider endpointInputOutput1d uptime30m latency30m throughputContext / output
OpenAI
openai
$15/M$60/M100%undefined tokens / undefined tokens

Pricing Comparison

Compare O1 API pricing across 1017 providers. Prices range from $0.033/request to $300.00/M. 柏拉图AI offers the lowest rate at $0.033/request. 1 provider offers free API credits or a free tier.

ProviderHealthModel VariantGroupInput ($/M)Output ($/M)Speed (t/s)First tokenAudit
L1
100%
o1
default
-93%$1.03/M
Cache read$0.514/M
-93%$4.11/M
L1
100%
o1-2024-12-17
default
-93%$1.03/M
Cache read$0.514/M
-93%$4.11/M
L1
100%
o1-all
gf
$0.500/request
-
L1
100%
o1-2024-12-17
default
$15.00/M
$60.00/M
L1
100%
o1
default
$15.00/M
$60.00/M
L1
100%
o1-2024-12-17
default
-86%$2.05/M
Cache read$1.03/M
-86%$8.22/M
L1
100%
o1
default
-86%$2.05/M
Cache read$1.03/M
-86%$8.22/M
L1
100%
o1
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1-2024-12-17
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1-preview
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1-preview-2024-09-12
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1-preview-all
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1-all
default
-86%$2.05/M
-86%$8.22/M
L1
100%
o1
Azure
-93%$1.03/M
-93%$4.11/M
L1
100%
o1-2024-12-17
Azure
-93%$1.03/M
-93%$4.11/M
L1
100%
o1-2024-12-17
default
$15.00/M
Cache read$7.50/M
$60.00/M
L1
100%
o1
default
$15.00/M
Cache read$7.50/M
$60.00/M
L1
100%
o1-2024-12-17
原价分组
Free
Free
L1
100%
o1-all
default
$0.600/request
-
L1
100%
o1
default
$0.600/request
-
Showing 20 model IDs of 164.

Alternatives & Similar Models

Frequently Asked Questions

What benchmark data does O1 include?
LMSpeed shows O1 benchmark context, API price, output speed, first-token latency, and provider data across 1018 providers when those signals are available.
What is the O1 API price?
O1 has pricing from 1018 providers, ranging from $0.033/request to $300.00/M. 柏拉图AI has the lowest listed price.
What does the O1 API pricing table include?
The O1 API pricing table compares 1018 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
Which provider has the cheapest O1 API pricing?
柏拉图AI currently has the lowest listed O1 price at $0.033/request across 1018 providers.
Is O1 API free?
Yes, O1 free API options are available through 1 providerundefined other undefined} on LMSpeed, including 兔子API. These providers offer free API credits or a free tier with no per-token charges.
Where can I get O1 free API access?
LMSpeed currently lists 1 free API providerundefined other undefined} for O1: 兔子API. Check each provider row before using it because free tier limits can change.

Also known as

o1o1-2024-12-17o1-2024-12-17-higho1-2024-12-17-lowo1-2024-12-17-medium

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.

Build with LMSpeed Data

Free

Free public API for LLM pricing, benchmarks & provider data

  • Real-time pricing & availability
  • Speed & latency benchmarks
  • 300+ models, 600+ providers
  • 1,000 requests/day
View API Documentation