OpenAI
·Released on Aug 7, 2025

GPT-5 API Benchmarks, Pricing & Provider Data

Compare GPT-5 with another model

Choose a model to open its comparison page.

Share on X
LLM

GPT-5 benchmark, API pricing, and provider data cover 1679 API providers, with prices starting at $0.0027/request. GPT-5 free API options are available from 12 providers. The page also shows measured API speed and first-token latency.

OpenAI GPT-5 is OpenAI frontier general-purpose model with improved reasoning depth, coding reliability, and multimodal understanding for production assistants and agent workflows.

Quality
0.0
LMSpeed score
Speed
88char/s
6.23 s
Cost
#120of 181
$0.0027/ 1M · 8:1 in:out
$0.0004 in · $0.0023 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.Agents45.1Coding49Reasoning52.7Knowledge49.5Math61.4Multilingual-Multimodal-Instruction following53.6
#1Math61.4Estimated2/4 Measured dimensions
80% interval: 49.573.2
foundational math63.4
math_500 · math_500
competition math59.3
aime · aime
proof frontierPrior only
applied tool mathPrior only
#2Instruction following53.6Provisional1/4 Measured dimensions
80% interval: 37.669.6
constraint followingPrior only
structured outputPrior only
novel instruction generalization53.6
ifbench · aa_if_bench
long multiturn instructionPrior only
#3Reasoning52.7RatedGlobal rank #323/4 Measured dimensions
80% interval: 44.061.4
abstract logicPrior only
scientific causal48.9
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraints53.3
mmlu_pro · mmlu_pro
evidence verification55.9
lcr · lcr
#4Knowledge49.5Provisional1/4 Measured dimensions
80% interval: 33.465.5
broad knowledge49.5
aa_omniscience · aa_omniscience_index
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#5Coding49Estimated2/4 Measured dimensions
80% interval: 37.860.2
code generation49.7
livecodebench · livecodebench / scicode · scicode
repository engineering48.3
vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#6Agents45.1Estimated3/4 Measured dimensions
80% interval: 35.854.3
planningPrior only
tool use50.5
tau · tau2_bench
environment execution49.5
gdpval_aa · benchlm_agentic_gdpval_aa
recovery reliability35.2
jobbench · job_bench
No data:MultilingualMultimodal

Specifications

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

INPUT
400Ktokens
480 pages of text
OUTPUT
128Ktokens
8K128K1M4M
400K

Features

Technical Details

Input
Output
Released
Aug 2025
Knowledge cutoff
2024-09-30
Documentation
Tokenizer
GPT
Architecture
text+image+file->text
Moderated
Yes
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetools

Rankings

Excels at

It's decent at

Falls behind in

Detailed scores

Updated: Sep 1, 2026

Pricing

undefined metric} other undefined metrics}}

Input price$1.25/M#120 / 181Output price$10.00/M#139 / 181
Input price
LMSpeed rank#120
Score$1.25/M
UpdatedSep 1, 2026
Confidence4
Output price
LMSpeed rank#139
Score$10.00/M
UpdatedSep 1, 2026
Confidence4

Agents

V3.0

undefined metric} other undefined metrics}} · Estimated

Score45.180% interval35.8–54.33/4 Measured dimensionsAA Agentic Index26.5#39 / 65Τ²-bench results84.8#46 / 82
Dimensions and evidence
Planning & decompositionPrior only
Tool use50.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z -0.05 · q 1.00
Environment & long-horizon execution49.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
gdpval_aa · benchlm_agentic_gdpval_aa · z -0.25 · q 1.00
Recovery & completion reliability35.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
jobbench · job_bench · z -2.22 · q 1.00
AA Agentic Index
LMSpeed rank#39
Score26.5
UpdatedAug 20, 2026
Confidence1
Τ²-bench resultsV3 evidence
LMSpeed rank#46
Score84.8
UpdatedAug 20, 2026
Confidence1
GDPval-AA
LMSpeed rank#41
Score29.1
UpdatedAug 20, 2026
Confidence1
GDPval-AAV3 evidence
LMSpeed rank#42
Score1083.0
UpdatedAug 20, 2026
Confidence1
JobBenchV3 evidence
LMSpeed rank#23
Score8.5
UpdatedAug 20, 2026
Confidence1

Coding

V3.0

undefined metric} other undefined metrics}} · Estimated

Score4980% interval37.8–60.22/4 Measured dimensionsLiveCodeBench55.8%#49 / 115SciCode38.8%#99 / 206
Dimensions and evidence
Code generation49.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 0.16 · q 1.00
scicode · scicode · z 0.00 · q 1.00
Repository engineering48.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
vibecode · vibe_code_bench · z -0.22 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
LiveCodeBenchV3 evidence
LMSpeed rank#49
Score55.8%
UpdatedSep 1, 2026
Confidence4
SciCodeV3 evidence
LMSpeed rank#99
Score38.8%
UpdatedSep 1, 2026
Confidence4
Vibe Code BenchV3 evidence
LMSpeed rank#22
Score20.1
UpdatedAug 20, 2026
Confidence1
AA Coding Index
LMSpeed rank#53
Score37.8
UpdatedAug 20, 2026
Confidence1
AA-SciCodeV3 evidence
LMSpeed rank#56
Score42.9
UpdatedAug 20, 2026
Confidence1

Reasoning

V3.0

undefined metric} other undefined metrics}} · Rated

Score52.7#3280% interval44.0–61.43/4 Measured dimensionsMMLU-Pro87.1%#12 / 129GPQA67.3%#143 / 213
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning48.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.30 · q 1.00
gpqa · gpqa · z -0.41 · q 1.00
hle · hle · z -0.53 · q 1.00
Multi-step constraints53.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.23 · q 1.00
Evidence integration & verification55.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.44 · q 1.00
MMLU-ProV3 evidence
LMSpeed rank#12
Score87.1%
UpdatedSep 1, 2026
Confidence4
GPQAV3 evidence
LMSpeed rank#143
Score67.3%
UpdatedSep 1, 2026
Confidence4
HLEV3 evidence
LMSpeed rank#152
Score6.0%
UpdatedSep 1, 2026
Confidence4
AA-LCRV3 evidence
LMSpeed rank#23
Score76.3
UpdatedAug 20, 2026
Confidence1
CritPtV3 evidence
LMSpeed rank#38
Score5.7
UpdatedAug 20, 2026
Confidence1

Knowledge

V3.0

undefined metric} other undefined metrics}} · Provisional

Score49.580% interval33.4–65.51/4 Measured dimensionsArtificial Analysis Intelligence Index35.3#61 / 111AA-GPQA Diamond85.4#55 / 108
Dimensions and evidence
Broad knowledge49.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z -0.16 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#61
Score35.3
UpdatedAug 20, 2026
Confidence1
AA-GPQA Diamond
LMSpeed rank#55
Score85.4
UpdatedAug 20, 2026
Confidence1
AA-HLE
LMSpeed rank#47
Score28.5
UpdatedAug 20, 2026
Confidence1
AA-Omniscience Accuracy
LMSpeed rank#30
Score40.3
UpdatedAug 20, 2026
Confidence1
AA-Omniscience Hallucination Rate
LMSpeed rank#36
Score82.2
UpdatedAug 20, 2026
Confidence1

Math

V3.0

undefined metric} other undefined metrics}} · Estimated

Score61.480% interval49.5–73.22/4 Measured dimensionsAIME36.7%#35 / 68MATH-50086.1%#42 / 73
Dimensions and evidence
Foundational math63.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
math_500 · math_500 · z 1.82 · q 1.00
Competition math59.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aime · aime · z 1.22 · q 1.00
Advanced proofsPrior only
Applied & tool-assisted mathPrior only
AIMEV3 evidence
LMSpeed rank#35
Score36.7%
UpdatedSep 1, 2026
Confidence4
MATH-500V3 evidence
LMSpeed rank#42
Score86.1%
UpdatedSep 1, 2026
Confidence4
AA MATH-500
LMSpeed rank#1
Score99.4
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

80% interval30.8–69.20/4 Measured dimensionsAA-MMMU-Pro74.2#37 / 65Design Arena Website1195.0#49 / 75
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only
AA-MMMU-Pro
LMSpeed rank#37
Score74.2
UpdatedAug 20, 2026
Confidence1
Design Arena Website
LMSpeed rank#49
Score1195.0
UpdatedAug 20, 2026
Confidence1

Instruction following

V3.0

undefined metric} other undefined metrics}} · Provisional

Score53.680% interval37.6–69.61/4 Measured dimensionsAA-IFBench73.1#27 / 84
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization53.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.20 · q 1.00
Multi-turn & long instructionsPrior only
AA-IFBenchV3 evidence
LMSpeed rank#27
Score73.1
UpdatedAug 20, 2026
Confidence1

OpenRouter endpoints

3 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
Azure
azure
$1.25/M$10/M99.9%undefined tokens / undefined tokens
OpenAI
openai/default
$1.25/M$10/M97.3%undefined tokens / undefined tokens
Azure
azure/swedencentral
$1.38/M$11/Mundefined tokens / undefined tokens

Pricing Comparison

Compare GPT-5 API pricing across 1667 providers. Prices range from $0.0027/request to $300.00/M. Yun API offers the lowest rate at $0.0027/request. 12 providers offer free API credits or a free tier.

ProviderHealthModel VariantGroupInput ($/M)Output ($/M)Speed (t/s)First tokenAudit
L1
100%
gpt-5-chat-latest
default
-86%$0.171/M
Cache read$0.017/M
-86%$1.37/M
101.9 t/s
0.95 s
L1
100%
gpt-5
default
-86%$0.171/M
Cache read$0.017/M
-86%$1.37/M
L1
100%
gpt-5-2025-08-07
default
-86%$0.171/M
Cache read$0.017/M
-86%$1.37/M
L1
100%
gpt-5-chat-latest
default
$1.25/M
$10.00/M
95.5 t/s
1.23 s
L1
100%
gpt-5-flex
default
$1.25/M
$10.00/M
L1
100%
gpt-5-all
default
$1.25/M
$10.00/M
L1
100%
gpt-5-fast
default
$1.25/M
$10.00/M
L1
100%
gpt-5-high
default
$1.25/M
$10.00/M
L1
100%
gpt-5-medium
default
$1.25/M
$10.00/M
L1
100%
gpt-5-minimal
default
$1.25/M
$10.00/M
L1
100%
gpt-5-low
default
$1.25/M
$10.00/M
L1
100%
gpt-5
default
$1.25/M
$10.00/M
L1
100%
gpt-5-2025-08-07
default
$1.25/M
$10.00/M
L1
99%
gpt-5
default
-87%$0.159/M
Cache read$0.016/M
-87%$1.27/M
58.1 t/s
17.42 s
L1
99%
gpt-5-2025-08-07
default
-87%$0.159/M
Cache read$0.016/M
-87%$1.27/M
L1
99%
gpt-5-chat-latest
default
-87%$0.159/M
Cache read$0.016/M
-87%$1.27/M
L1
100%
gpt-5-chat
default
$1.25/M
Cache read$0.130/M
$10.00/M
45.8 t/s
6.58 s
L1
100%
gpt-5-chat-latest
default
-10%$1.13/M
Cache read$0.113/M
-10%$9.00/M
L1
100%
gpt-5
default
$1.25/M
Cache read$0.130/M
$10.00/M
L1
100%
gpt-5-2025-08-07
default
$1.25/M
Cache read$0.125/M
$10.00/M
Showing 20 model IDs of 305.

Alternatives & Similar Models

Frequently Asked Questions

What benchmark data does GPT-5 include?
LMSpeed shows GPT-5 benchmark context, API price, output speed, first-token latency, and provider data across 1679 providers when those signals are available.
What is the GPT-5 API price?
GPT-5 has pricing from 1679 providers, ranging from $0.0027/request to $300.00/M. Yun API has the lowest listed price.
What does the GPT-5 API pricing table include?
The GPT-5 API pricing table compares 1679 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
Which provider has the cheapest GPT-5 API pricing?
Yun API currently has the lowest listed GPT-5 price at $0.0027/request across 1679 providers.
Can I compare GPT-5 API price and speed together?
Yes. LMSpeed shows GPT-5 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
Is GPT-5 API free?
Yes, GPT-5 free API options are available through 12 providerundefined other undefined} on LMSpeed, including 兔子API, 兔子API, 初叶🍂Furry API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
Where can I get GPT-5 free API access?
LMSpeed currently lists 12 free API providerundefined other undefined} for GPT-5: 兔子API, 兔子API, 初叶🍂Furry API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.

Also known as

GPT-5OR-openai/gpt-5OR-openai/gpt-5-chatgpt-5gpt-5-2025-08-07

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