gpt-5-2-codex
Developer: OpenAI
Also known as
GPT-5.2 Codex by OpenAI is available through 118 API providers on LMSpeed. Compare API pricing from $0.010 to $9102300.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 67 tok/s.
Compare GPT-5.2 Codex API pricing across 117 providers. Input prices range from $0.010 to $9102300.00 per million input. 素墨API offers the lowest rate at $0.010/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 我不是AI神 | gpt-5.2-codex | Free | Free | — |
| 素墨API | gpt-5.2-codex | $0.010 | $0.010 | — |
| 10dian-API | gpt-5.2-codex | $0.010 | $0.010 | — |
| CookingAI | gpt-5.2-codex | $0.030 | $0.030 | — |
| 91VIP API | gpt-5.2-codex | $0.050 | $0.050 | — |
 星见雅 API | gpt-5.2-codex | $0.100 | $0.800 | — |
 GLM BigModel Relay | gpt-5.2-codex | $0.175 | $1.40 | — |
 VVCode | gpt-5.2-codex | $0.175 | $1.40 | — |
| Yunchu API | gpt-5.2-codex | $0.240 | $1.92 | — |
 MonkingAI | gpt-5.2-codex | $0.280 | $2.24 | — |
| 人人 API | gpt-5.2-codex | $0.300 | $2.40 | — |
| 人人 API | gpt-5.2-codex-high | $0.300 | $2.40 | — |
| 人人 API | gpt-5.2-codex-low | $0.300 | $2.40 | — |
| 人人 API | gpt-5.2-codex-medium | $0.300 | $2.40 | — |
| 人人 API | gpt-5.2-codex-xhigh | $0.300 | $2.40 | — |
| SWT-API | gpt-5.2-codex | $0.375 | $3.00 | — |
| 蜜音AI | gpt-5.2-codex | $0.525 | $4.20 | — |
| Nova AI | gpt-5.2-codex | $0.527 | $4.21 | — |
| Codex API | gpt-5.2-codex | $0.750 | $6.00 | — |
| llm-2-api | gpt-5.2-codex | $0.800 | $6.40 | — |
Pricing data from provider public APIs
GPT-5.2 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 1-5 of 5 providers
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/02/2026, 08:19 | gpt-5.2-codex | 85.36 tok/s | 2.18s |
| 04/02/2026, 08:19 | gpt-5.2-codex | 40.06 tok/s | 1.58s |
| 04/02/2026, 08:19 | gpt-5.2-codex | 69.77 tok/s | 1.86s |
| 04/02/2026, 08:19 | gpt-5.2-codex | 17.70 tok/s | 1.49s |
| 04/02/2026, 08:19 | gpt-5.2-codex | 113.91 tok/s | 1.72s |
| 03/30/2026, 03:02 | gpt-5.2-codex | 53.60 tok/s | 2.40s |
| 03/30/2026, 03:02 | gpt-5.2-codex | 53.97 tok/s | 2.49s |
| 03/30/2026, 03:02 | gpt-5.2-codex | 143.47 tok/s | 7.72s |
| 03/30/2026, 03:02 | gpt-5.2-codex | 18.25 tok/s | 4.50s |
| 03/30/2026, 03:02 | gpt-5.2-codex | 65.63 tok/s | 6.43s |
| 03/28/2026, 12:45 | gpt-5.2-codex | 62.97 tok/s | 2.32s |
| 03/28/2026, 12:45 | gpt-5.2-codex | 55.47 tok/s | 1.98s |
| 03/28/2026, 12:45 | gpt-5.2-codex | 54.69 tok/s | 2.09s |
| 03/28/2026, 12:45 | gpt-5.2-codex | 50.57 tok/s | 2.73s |
| 03/28/2026, 12:45 | gpt-5.2-codex | 62.56 tok/s | 2.73s |
| 03/18/2026, 10:36 | gpt-5.2-codex | 56.92 tok/s | 1.32s |
| 03/18/2026, 10:36 | gpt-5.2-codex | 69.82 tok/s | 1.83s |
| 03/18/2026, 10:36 | gpt-5.2-codex | 54.48 tok/s | 1.36s |
| 03/18/2026, 10:36 | gpt-5.2-codex | 16.72 tok/s | 1.51s |
| 03/18/2026, 10:36 | gpt-5.2-codex | 63.25 tok/s | 1.22s |
