gpt-5-3-codex
Developer: OpenAI
Also known as
GPT-5.3 Codex by OpenAI is available through 164 API providers on LMSpeed. Compare API pricing from $0.0018 to $13003285.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 252 tok/s.
Compare GPT-5.3 Codex API pricing across 163 providers. Input prices range from $0.0018 to $13003285.00 per million input. 91VIP offers the lowest rate at $0.0018/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 我不是AI神 | gpt-5.3-codex | Free | Free | — |
| 91VIP | gpt-5.3-codex-spark | $0.0018 | $0.014 | — |
| Futureppo | gpt-5.3-codex-spark | $0.0018 | $0.014 | — |
| 素墨API | gpt-5.3-codex | $0.010 | $0.010 | — |
| 10dian-API | gpt-5.3-codex | $0.010 | $0.010 | — |
| 爱次元API | gpt-5.3-codex-spark | $0.015 | $0.015 | — |
| VSLLM | gpt-5.3-codex-spark | $0.025 | $0.025 | — |
| CookingAI | gpt-5.3-codex | $0.030 | $0.030 | — |
| VSLLM | gpt-5.3-codex | $0.050 | $0.050 | — |
 星见雅 API | gpt-5.3-codex | $0.100 | $0.800 | 32.1 t/s |
| 91VIP API | gpt-5.3-codex | $0.100 | $0.100 | — |
| 91VIP API | gpt-5.3-codex-spark | $0.100 | $0.100 | — |
 GLM BigModel Relay | gpt-5.3-codex | $0.175 | $1.40 | — |
| GLM BigModel Relay | gpt-5.3-codex-spark | $0.175 | $1.40 | — |
 VVCode | gpt-5.3-codex | $0.175 | $1.40 | — |
| Yunchu API | gpt-5.3-codex | $0.240 | $1.92 | — |
 MonkingAI | gpt-5.3-codex | $0.280 | $2.24 | — |
| 人人 API | gpt-5.3-codex | $0.300 | $2.40 | — |
| 人人 API | gpt-5.3-codex-high | $0.300 | $2.40 | — |
| 人人 API | gpt-5.3-codex-low | $0.300 | $2.40 | — |
Pricing data from provider public APIs
GPT-5.3 Codex is free to use through 1 provider with no per-token charges. These providers offer free API credits or a free tier:
| Provider | Speed (t/s) |
|---|---|
| 我不是AI神 | — |
Compare speed and latency performance across all API providers.
Showing 1-16 of 16 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
Mars HK gpt-5.3-codex-spark | 252.12 tok/s | 2.20s | 14 |
Unified AI Gateway gpt-5.3-codex | 64.15 tok/s | 2.75s | 5 |
gpt-5.3-codex | 61.35 tok/s | 3.50s | 5 |
gpt-5.3-codex | 56.97 tok/s | 2.98s | 10 |
gpt-5.3-codex | 53.21 tok/s | 3.89s | 5 |
 李/gpt-5.3-codex | 52.33 tok/s | 1.54s | 10 |
gpt-5.3-codex | 51.26 tok/s | 0.92s | 5 |
gpt-5.3-codex | 48.42 tok/s | 2.62s | 5 |
gpt-5.3-codex | 47.55 tok/s | 3.21s | 5 |
gpt-5.3-codex | 46.27 tok/s | 2.58s | 5 |
gpt-5.3-codex | 45.96 tok/s | 2.04s | 5 |
 gpt-5.3-codex | 45.72 tok/s | 4.38s | 5 |
gpt-5.3-codex | 43.58 tok/s | 3.19s | 5 |
gpt-5.3-codex | 35.36 tok/s | 17.64s | 5 |
gpt-5.3-codex | 32.11 tok/s | 5.76s | 25 |
gpt-5.3-codex | 21.13 tok/s | 8.34s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/12/2026, 16:06 | gpt-5.3-codex-spark | 80.75 tok/s | 3.05s |
| 04/12/2026, 16:06 | gpt-5.3-codex-spark | 335.87 tok/s | 2.74s |
| 04/12/2026, 16:06 | gpt-5.3-codex-spark | 141.44 tok/s | 1.79s |
| 04/12/2026, 10:40 | gpt-5.3-codex-spark | 98.86 tok/s | 2.95s |
| 04/12/2026, 10:40 | gpt-5.3-codex-spark | 421.24 tok/s | 2.08s |
| 04/12/2026, 10:40 | gpt-5.3-codex-spark | 352.23 tok/s | 1.39s |
| 04/12/2026, 10:40 | gpt-5.3-codex-spark | 100.92 tok/s | 1.17s |
| 04/12/2026, 10:40 | gpt-5.3-codex-spark | 196.55 tok/s | 1.17s |
| 04/12/2026, 10:33 | gpt-5.3-codex-spark | 486.33 tok/s | 2.25s |
| 04/12/2026, 10:32 | gpt-5.3-codex-spark | 503.70 tok/s | 1.95s |
| 04/12/2026, 10:32 | gpt-5.3-codex-spark | 171.76 tok/s | 2.71s |
| 04/12/2026, 10:32 | gpt-5.3-codex-spark | 64.69 tok/s | 1.94s |
| 04/12/2026, 09:27 | gpt-5.3-codex-spark | 83.86 tok/s | 2.93s |
| 04/12/2026, 09:27 | gpt-5.3-codex-spark | 491.53 tok/s | 2.61s |
| 04/12/2026, 08:01 | gpt-5.3-codex | 34.14 tok/s | 8.65s |
| 04/12/2026, 08:01 | gpt-5.3-codex | 26.88 tok/s | 15.86s |
| 04/12/2026, 08:01 | gpt-5.3-codex | 44.73 tok/s | 10.75s |
| 04/12/2026, 08:01 | gpt-5.3-codex | 14.91 tok/s | 5.83s |
| 04/12/2026, 08:01 | gpt-5.3-codex | 21.93 tok/s | 12.75s |
| 04/11/2026, 06:06 | gpt-5.3-codex | 23.22 tok/s | 7.28s |
