OpenAI
·Released on Mar 17, 2026GPT-5.4 Nano API Benchmarks, Pricing & Provider Data
Compare GPT-5.4 Nano with another model
Choose a model to open its comparison page.
LLM
GPT-5.4 Nano benchmark, API pricing, and provider data cover 660 API providers, with prices starting at $0.0027/M. GPT-5.4 Nano free API options are available from 2 providers. The page also shows measured API speed and first-token latency.
OpenAI GPT-5.4 Nano is a compact language model in the GPT-5 series, optimized for low-latency responses and efficient inference.
Quality
#99of 100
37.0
LMSpeed score
Speed
137char/s
3.38 s
Cost
#33of 180
$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
- 7 / 8
- Methodology
- V3.0
#1Instruction following54.6Provisional1/4 Measured dimensions
80% interval: 38.6–70.6
constraint followingPrior only
structured outputPrior only
novel instruction generalization54.6
ifbench · aa_if_bench
long multiturn instructionPrior only
#2Math51.8Provisional1/4 Measured dimensions
80% interval: 35.8–67.9
foundational mathPrior only
competition mathPrior only
proof frontier51.8
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#3Reasoning49.9Estimated2/4 Measured dimensions
80% interval: 39.1–60.7
abstract logicPrior only
scientific causal46.1
critpt · critpt / gpqa · gpqa / hle · hle / hle · hle_no_tools
multistep constraintsPrior only
evidence verification53.7
lcr · lcr
#4Coding49.7Estimated2/4 Measured dimensions
80% interval: 37.9–61.5
code generation49.1
scicode · scicode
repository engineering50.3
vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#5Agents44.8RatedGlobal rank #483/4 Measured dimensions
80% interval: 36.7–53.0
planningPrior only
tool use44.7
mcp_atlas · mcp_atlas / tau · tau2_bench / toolathlon · toolathlon
environment execution37.6
gdpval_aa · benchlm_agentic_gdpval_aa / osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability52.3
apex_agents · apex_agents_aa
#6Knowledge43.5Provisional1/4 Measured dimensions
80% interval: 29.5–57.5
broad knowledge43.5
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#7Multimodal31.2Provisional1/4 Measured dimensions
80% interval: 15.1–47.3
perception ocrPrior only
document spatialPrior only
visual reasoning31.2
mmmu_pro · mmmu_pro
video actionPrior only
No data:Multilingual
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
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Aug 31, 2026Overall
undefined metric} other undefined metrics}}
Overall score37.0#99 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing
undefined metric} other undefined metrics}}
Input price$0.200/M#33 / 180Output price$1.25/M#60 / 180
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score44.8#4880% interval36.7–53.03/4 Measured dimensionsAgentic score16.6#66 / 69Terminal-Bench 2.046.3#48 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decompositionPrior only
Tool use44.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z -1.33 · q 1.00
tau · tau2_bench · z 0.38 · q 1.00
toolathlon · toolathlon · z -1.31 · q 1.00
Environment & long-horizon execution37.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
gdpval_aa · benchlm_agentic_gdpval_aa · z -0.19 · q 1.00
osworld · os_world_verified · z -2.64 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z -1.05 · q 1.00
Recovery & completion reliability52.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
apex_agents · apex_agents_aa · z 0.00 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score49.780% interval37.9–61.52/4 Measured dimensionsSciCode46.9%#37 / 205Coding score57.5#29 / 81
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Code generation49.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · scicode · z -0.26 · q 1.00
Repository engineering50.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
vibecode · vibe_code_bench · z 0.04 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
SciCodeV3 evidence
LMSpeed rank#37
Score46.9%
Sourceartificialanalysis.ai
UpdatedAug 31, 2026
Confidence4
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score49.980% interval39.1–60.72/4 Measured dimensionsGPQA81.7%#87 / 212HLE28.3%#58 / 209
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning46.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.52 · q 1.00
gpqa · gpqa · z -0.93 · q 1.00
hle · hle · z -0.86 · q 1.00
hle · hle_no_tools · z -2.07 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification53.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.13 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score43.580% interval29.5–57.51/4 Measured dimensionsKnowledge score54.8#55 / 69HLE w/o tools24.3#21 / 21
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge43.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z -0.86 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z -0.77 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#44
Score39.7
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
AA-Omniscience Hallucination Rate
LMSpeed rank#50
Score74.2
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score51.880% interval35.8–67.91/4 Measured dimensionsMath score44.1#39 / 62FrontierMath v2 (Tiers 1-3)25.9#23 / 47
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs51.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 0.00 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.06 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#23
Score25.9
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#20
Score6.3
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Multimodal
V3.0undefined metric} other undefined metrics}} · Provisional
Score31.280% interval15.1–47.31/4 Measured dimensionsMultimodal Grounded score16.0#42 / 44MMMU-Pro66.1#30 / 31
Multimodal
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoning31.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmmu_pro · mmmu_pro · z -2.58 · q 1.00
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score54.680% interval38.6–70.61/4 Measured dimensionsAA-IFBench75.9#14 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization54.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.34 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
4 endpointsThird-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 endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
OpenAI openai/flex | $0.100/M | $0.625/M | 100% | — | — | undefined tokens / undefined tokens |
Azure azure | $0.200/M | $1.25/M | 98.7% | — | — | undefined tokens / undefined tokens |
Azure azure/us | $0.220/M | $1.38/M | 97.8% | — | — | undefined tokens / undefined tokens |
OpenAI openai | $0.200/M | $1.25/M | 88.6% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare GPT-5.4 Nano API pricing across 658 providers. Prices range from $0.0027/M to $495.00/M. 6345ywz API offers the lowest rate at $0.0027/M. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-5.4-nano | default | -93%$0.014/M | -93%$0.086/M | 147.0 t/s | 4.37 s | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | -93%$0.014/M | -93%$0.086/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | $0.300/M | $1.88/M | 117.8 t/s | 1.40 s | — | |
L1 100% | gpt-5.4-nano-low | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano-high | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano-medium | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano-xhigh | default | $0.200/M | $1.25/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | -86%$0.027/M | -86%$0.171/M | — | — | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | -86%$0.027/M | -86%$0.171/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | -86%$0.027/M | -86%$0.171/M | — | — | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | -86%$0.027/M | -86%$0.171/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | -23%$0.153/M | -23%$0.959/M | — | — | — | |
L1 100% | gpt-5.4-nano | default | $75.00/M | $468.75/M | — | — | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | $75.00/M | $468.75/M | — | — | — | |
兔子API Free | L1 100% | gpt-5.4-nano | 原价分组 | Free | Free | — | — | — |
L1 100% | gpt-5.4-nano | default | -96%$0.0082/M Cache read$0.0008/M | -96%$0.051/M | — | — | — | |
L1 100% | gpt-5.4-nano-2026-03-17 | default | -96%$0.0082/M Cache read$0.0008/M | -96%$0.051/M | — | — | — | |
L1 100% | gpt-5.4-nano | gpt-azure | -73%$0.053/M | -73%$0.332/M | — | — | — |
Showing 20 model IDs of 81.
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
123 shared providers
GPT-5.4 Mini
gpt-5-4-mini
OpenAI GPT-5.4 Mini is a compact language model in the GPT-5 series, optimized for quick responses and high throughput.
123 shared providers
GPT-5.3 Codex
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
119 shared providers
GPT-5.2
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
117 shared providers
GPT-5.2 Codex
gpt-5-2-codex
OpenAI GPT-5.2 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
113 shared providers
GPT-5
gpt-5
OpenAI GPT-5 is OpenAI frontier general-purpose model with improved reasoning depth, coding reliability, and multimodal understanding for production assistants and agent workflows.
113 shared providers
Frequently Asked Questions
- What benchmark data does GPT-5.4 Nano include?
- LMSpeed shows GPT-5.4 Nano benchmark context, API price, output speed, first-token latency, and provider data across 660 providers when those signals are available.
- What is the GPT-5.4 Nano API price?
- GPT-5.4 Nano has pricing from 660 providers, ranging from $0.0027/M to $495.00/M. 6345ywz API has the lowest listed price.
- What does the GPT-5.4 Nano API pricing table include?
- The GPT-5.4 Nano API pricing table compares 660 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-5.4 Nano API pricing?
- 6345ywz API currently has the lowest listed GPT-5.4 Nano price at $0.0027/M across 660 providers.
- Can I compare GPT-5.4 Nano API price and speed together?
- Yes. LMSpeed shows GPT-5.4 Nano API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is GPT-5.4 Nano API free?
- Yes, GPT-5.4 Nano free API options are available through 2 providerundefined other undefined} on LMSpeed, including 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-5.4 Nano free API access?
- LMSpeed currently lists 2 free API providerundefined other undefined} for GPT-5.4 Nano: 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.