Choose a model to open its comparison page.
GPT-5.3 Codex benchmark, API pricing, and provider data cover 531 API providers, with prices starting at $0.0068/request. GPT-5.3 Codex free API options are available from 8 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.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
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 endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Azure azure | $1.75/M | $14/M | 99.7% | — | — | 400K tokens / 128K tokens |
OpenAI openai | $1.75/M | $14/M | 98.3% | — | — | 400K tokens / 128K tokens |
OpenAI openai/priority | $3.50/M | $28/M | 98.3% | — | — | 400K tokens / 128K tokens |
Compare GPT-5.3 Codex API pricing across 523 providers. Prices range from $0.0068/request to $17482.50/M. KFCV50 offers the lowest rate at $0.0068/request. 8 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-5.3-codex-spark | default | $0.365/request | - | 242.3 t/s+144% | 2.95 s-95% | — | |
L1 99% | gpt-5.3-codex | gptpro | -96%$0.068/M | -96%$0.548/M | 56.1 t/s | 4.62 s-92% | — | |
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-96% | — | |
L1 100% | gpt-5.3-codex | azure-officially | -29%$1.25/M Cache read$0.125/M | -29%$10.00/M | — | — | — | |
L1 99% | gpt-5.3-codex | default | -93%$0.120/M | -93%$0.959/M | — | — | — | |
L1 99% | gpt-5.3-codex-spark | default | -93%$0.120/M | -93%$0.959/M | — | — | — | |
L1 99% | gpt-5.3-codex-2026-02-24 | default | $5.14/M | $41.10/M | — | — | — | |
L1 99% | gpt-5.3-codex | 实验性 | -95%$0.084/M Cache read$0.0084/M | -95%$0.671/M | — | — | — | |
L1 99% | gpt-5.3-codex | gpt-pro池子 | -82%$0.315/M Cache read$0.032/M | -82%$2.52/M | — | — | — | |
L1 99% | gpt-5.3-codex-spark | gpt-pro池子 | -82%$0.315/M Cache read$0.032/M | -82%$2.52/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | default | -97%$0.059/M Cache read$0.0059/M | -97%$0.470/M | — | — | — | |
L1 100% | gpt-5.3-codex | default | -97%$0.059/M Cache read$0.0059/M | -97%$0.470/M | — | — | — | |
L1 100% | gpt-5.3-codex | default | -87%$0.223/M | -87%$1.78/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | default | -87%$0.223/M | -87%$1.78/M | — | — | — | |
L1 100% | gpt-5.3-codex-2026-02-24 | default | $9.55/M | $76.44/M | — | — | — | |
L1 100% | gpt-5.3-codex | az | -79%$0.360/M Cache read$0.036/MCache write$0.449/MCache write 1h$0.719/M | -79%$2.88/M | — | — | — | |
L1 100% | gpt-5.3-codex-xhigh | az | -79%$0.360/M Cache read$0.036/MCache write$0.449/MCache write 1h$0.719/M | -79%$2.88/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark | Codex-gpt | -67%$0.575/M Cache write$0.719/MCache write 1h$1.15/M | -67%$4.60/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark-medium | Codex-gpt | -67%$0.575/M Cache write$0.719/MCache write 1h$1.15/M | -67%$4.60/M | — | — | — | |
L1 100% | gpt-5.3-codex-spark-xhigh | Codex-gpt | -67%$0.575/M Cache write$0.719/MCache write 1h$1.15/M | -67%$4.60/M | — | — | — |
2 metrics
2 metrics
6 metrics · Rated
8 metrics · Rated
5 metrics · Estimated
7 metrics · Provisional
0 metrics · No data
1 metric · Provisional
3 metrics · Provisional
2 metrics · Provisional
