OpenAI
·Released on Feb 24, 2026GPT-5.3 Codex API Benchmarks, Pricing & Provider Data
Compare GPT-5.3 Codex with another model
Choose a model to open its comparison page.
LLM
GPT-5.3 Codex benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0068/request. GPT-5.3 Codex free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
Quality
#26of 112
68.0
LMSpeed score
Speed
#29of 80
78char/s
3.91 s
Cost
#140of 186
$0.0068/ 1M · 8:1 in:out
$0.0011 in · $0.0058 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Reasoning59.8Estimated2/4 Measured dimensions
80% interval: 49.0–70.6
abstract logicPrior only
scientific causal61.5
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraintsPrior only
evidence verification58.1
lcr · lcr
#2Coding57.1RatedGlobal rank #93/4 Measured dimensions
80% interval: 48.6–65.7
code generation58.6
scicode · aa_sci_code
repository engineering55.3
swe_pro · swe_pro / vibecode · vibe_code_bench
debugging testing57.6
swe_rebench · swe_rebench / swe_verified · swe_verified
tooling qualityPrior only
#2Knowledge57.1Provisional1/4 Measured dimensions
80% interval: 43.1–71.1
broad knowledge57.1
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#4Instruction 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
#5Agents52.1RatedGlobal rank #324/4 Measured dimensions
80% interval: 45.5–58.7
planning54.3
deep_planning · gert_labs
tool use50.8
tau · tau2_bench
environment execution52.1
osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability51.3
jobbench · job_bench
#6Multimodal50.8Provisional1/4 Measured dimensions
80% interval: 34.4–67.1
perception ocrPrior only
document spatialPrior only
visual reasoning50.8
benchlm_category_multimodal · benchlm_category_multimodal_grounded
video actionPrior only
No data:MathMultilingual
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: Sep 13, 2026Overall
undefined metric} other undefined metrics}}
Overall score68.0#26 / 112
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Speed & latency
undefined metric} other undefined metrics}}
Output speed138.6 tok/s#29 / 80Time to first token37.60 s#77 / 80
Speed & latency
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Output speed
LMSpeed rank#29
Score138.6 tok/s
Sourceartificialanalysis.ai
UpdatedSep 13, 2026
Confidence4
Time to first token
LMSpeed rank#77
Score37.60 s
Sourceartificialanalysis.ai
UpdatedSep 13, 2026
Confidence4
Pricing
undefined metric} other undefined metrics}}
Input price$1.75/M#140 / 186Output price$14.00/M#156 / 186
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score52.1#3280% interval45.5–58.74/4 Measured dimensionsAgentic score62.8#38 / 77Terminal-Bench 2.077.3#11 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition54.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.59 · q 1.00
Tool use50.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z 0.00 · q 1.00
Environment & long-horizon execution52.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
osworld · os_world_verified · z -0.72 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 0.97 · q 1.00
Recovery & completion reliability51.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
jobbench · job_bench · z 0.02 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score57.1#980% interval48.6–65.73/4 Measured dimensionsCoding score52.0#50 / 87SWE-bench Verified85.0#6 / 49
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation58.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · aa_sci_code · z 0.97 · q 1.00
Repository engineering55.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_pro · swe_pro · z -0.05 · q 1.00
vibecode · vibe_code_bench · z 1.23 · q 1.00
Debugging & testing57.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_rebench · swe_rebench · z -0.27 · q 1.00
swe_verified · swe_verified · z 1.89 · q 1.00
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score59.880% interval49.0–70.62/4 Measured dimensionsGPQA91.5%#22 / 218HLE42.5%#23 / 216
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning61.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.71 · q 1.00
gpqa · gpqa · z 1.05 · q 1.00
hle · hle · z 0.93 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification58.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.73 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score57.180% interval43.1–71.11/4 Measured dimensionsArtificial Analysis Intelligence Index32.5#43 / 117AA-GPQA Diamond91.5#23 / 113
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge57.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 0.48 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z 0.59 · 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#43
Score32.5
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
AA-Omniscience IndexV3 evidence
LMSpeed rank#25
Score10.9
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#21
Score89.2
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofsPrior only
Applied & tool-assisted mathPrior only
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
Score50.880% interval34.4–67.11/4 Measured dimensionsAA-MMMU-Pro78.5#22 / 68Design Arena Website1175.0#59 / 78
Multimodal
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoning50.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
benchlm_category_multimodal · benchlm_category_multimodal_grounded · z 0.38 · q 1.00
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Multimodal Grounded scoreV3 evidence
LMSpeed rank#20
Score75.6
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score54.680% interval38.6–70.61/4 Measured dimensionsAA-IFBench75.4#18 / 84Instruction Following score92.6#10 / 52
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 0.32 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
3 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 |
|---|---|---|---|---|---|---|
Azure azure | $1.75/M | $14/M | 100% | — | — | undefined tokens / undefined tokens |
OpenAI openai | $1.75/M | $14/M | 99.9% | — | — | undefined tokens / undefined tokens |
OpenAI openai/fast | $3.50/M | $28/M | — | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare GPT-5.3 Codex API pricing across 453 providers. Prices range from $0.0068/request to $375.00/M. KFCV50 offers the lowest rate at $0.0068/request. 10 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-5.3-codex-spark | default | $0.0073/request | - | 242.3 t/s+75% | 2.95 s-92% | — | |
L1 100% L2 0% | gpt-5.3-codex | gptpro | -96%$0.068/M | -96%$0.548/M | 56.1 t/s | 4.62 s-88% | — | |
L1 100% | gpt-5.3-codex | OpenAI-官key | $2.27/M Cache read$0.228/MCache write$2.84/MCache write 1h$4.55/M | $18.20/M | 21.1 t/s | 2.44 s-93% | — | |
L1 96% | gpt-5.3-codex-spark | default | $1.75/M Cache read$0.175/M | $14.00/M | 20.7 t/s | 1.49 s-96% | — | |
L1 100% | gpt-5.3-codex | default | -93%$0.120/M Cache read$0.012/M | -93%$0.959/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | 官转OpenAI | -59%$0.719/M | -59%$5.75/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | GPT · Best cash equivalent (conditional promotion) | -95%$0.087/M Cache read$0.0088/M | -95%$0.700/M | — | — | — | |
L1 100% | gpt-5.3-codex | azure-officially | -29%$1.25/M Cache read$0.125/M | -29%$10.00/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | Codex-Pro | -99%$0.022/M Cache read$0.0022/MCache write$0.0022/MCache write 1h$0.0035/M | -99%$0.176/M | — | — | — | |
L1 100% | gpt-5.3-codex-medium | CodeX_05_token | $0.0068/request | - | — | — | — | |
L1 100% | gpt-5.3-codex-high | CodeX_05_token | $0.0068/request | - | — | — | — | |
L1 100% | gpt-5.3-codex | default | $0.014/request | - | — | — | — | |
L1 100% | gpt-5.3-codex-low | CodeX_05_token | $0.0068/request | - | — | — | — | |
L1 100% | gpt-5.3-codex-xhigh | default | $0.021/request | - | — | — | — | |
L1 100% | gpt-5.3-codex-spark | default | -86%$0.240/M Cache read$0.024/M | -86%$1.92/M | — | — | — | |
L1 100% | gpt-5.3-codex-2026-02-24 | default | -86%$0.240/M Cache read$0.024/M | -86%$1.92/M | — | — | — | |
L1 100% | gpt-5.3-codex-openai-compact | default | -86%$0.240/M Cache read$0.024/M | -86%$1.92/M | — | — | — | |
L1 100% | gpt-5.3-codex | default | -93%$0.120/M Cache read$0.012/M | -93%$0.959/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | 官转OpenAI | -59%$0.719/M | -59%$5.75/M | — | — | — | |
L1 100% | gpt-5.3-codex | default | -23%$1.34/M | -23%$10.74/M | — | — | — |
Showing 20 model IDs of 154.
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.
317 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.
292 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.
283 shared providers
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
241 shared providers
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
234 shared providers
Claude Haiku 4.5
claude-haiku-4-5
Anthropic Claude Haiku 4.5 delivers fast, low-cost responses while retaining solid instruction following for chat, classification, and lightweight coding.
225 shared providers
Frequently Asked Questions
- What benchmark data does GPT-5.3 Codex include?
- LMSpeed shows GPT-5.3 Codex benchmark context, API price, output speed, first-token latency, and provider data across 463 providers when those signals are available.
- What is the GPT-5.3 Codex API price?
- GPT-5.3 Codex has pricing from undefined provider} other undefined providers}}, ranging from $0.0068/request to $375.00/M. KFCV50 has the lowest listed price.
- What does the GPT-5.3 Codex API pricing table include?
- The GPT-5.3 Codex API pricing table compares 463 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-5.3 Codex API pricing?
- KFCV50 currently has the lowest listed GPT-5.3 Codex price at $0.0068/request across undefined provider} other undefined providers}}.
- Can I compare GPT-5.3 Codex API price and speed together?
- Yes. LMSpeed shows GPT-5.3 Codex API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is GPT-5.3 Codex API free?
- Yes, GPT-5.3 Codex free API options are available through 10 providerundefined other undefined} on LMSpeed, including 兔子API, 兔子API, 兔子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-5.3 Codex free API access?
- LMSpeed currently lists 10 free API providerundefined other undefined} for GPT-5.3 Codex: 兔子API, 兔子API, 兔子API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.