gpt-5-1-codex-max
Developer: OpenAI
Also known as
GPT-5.1 Codex Max by OpenAI is available through 94 API providers on LMSpeed. Compare API pricing from $0.010 to $6501642.50 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 72 tok/s.
Compare GPT-5.1 Codex Max API pricing across 93 providers. Input prices range from $0.010 to $6501642.50 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-5.1-codex-max | Free | Free | — |
| 素墨API | gpt-5.1-codex-max | $0.010 | $0.010 | — |
| 10dian-API | gpt-5.1-codex-max | $0.010 | $0.010 | — |
 星见雅 API | gpt-5.1-codex-max | $0.100 | $0.800 | 72.0 t/s |
| 91VIP API | gpt-5.1-codex-max | $0.100 | $0.100 | — |
 GLM BigModel Relay | gpt-5.1-codex-max | $0.125 | $1.00 | — |
 MonkingAI | gpt-5.1-codex-max | $0.200 | $1.60 | — |
| Yunchu API | gpt-5.1-codex-max | $0.240 | $1.92 | 46.5 t/s |
| 人人 API | gpt-5.1-codex-max | $0.300 | $2.40 | — |
| 人人 API | gpt-5.1-codex-max-xhigh | $0.300 | $2.40 | — |
| Nova AI | gpt-5.1-codex-max | $0.375 | $3.00 | — |
| 蜜音AI | gpt-5.1-codex-max | $0.375 | $3.00 | — |
| 玄黄 | gpt-5.1-codex-max | $0.625 | $5.00 | — |
| llm-2-api | gpt-5.1-codex-max | $0.800 | $6.40 | — |
| llm-2-api | gpt-5.1-codex-max-high | $0.800 | $6.40 | — |
| llm-2-api | gpt-5.1-codex-max-xhigh | $0.800 | $6.40 | — |
 OpenRouter Fans | openai/gpt-5.1-codex-max | $1.10 | $9.00 | — |
 KKSJ-AI | gpt-5.1-codex-max | $1.13 | $9.00 | — |
| OpenRouter Fans | gpt-5.1-codex-max | $1.13 | $9.00 | — |
| Codex API | gpt-5.1-codex-max-openai-compact | $1.20 | $9.60 | — |
Pricing data from provider public APIs
GPT-5.1 Codex Max 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 1-2 of 2 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 星见雅 APIgpt-5.1-codex-max | 72.02 tok/s | 7.98s | 3 |
Yunchu API gpt-5.1-codex-max | 46.47 tok/s | 5.28s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/28/2026, 24:02 | gpt-5.1-codex-max | 23.31 tok/s | 5.61s |
| 03/28/2026, 24:02 | gpt-5.1-codex-max | 73.25 tok/s | 3.53s |
| 03/28/2026, 24:02 | gpt-5.1-codex-max | 20.70 tok/s | 6.34s |
| 03/28/2026, 24:02 | gpt-5.1-codex-max | 12.95 tok/s | 5.87s |
| 03/28/2026, 24:02 | gpt-5.1-codex-max | 102.16 tok/s | 5.06s |
| 03/11/2026, 23:38 | gpt-5.1-codex-max | 75.12 tok/s | 4.95s |
| 03/11/2026, 23:38 | gpt-5.1-codex-max | 106.14 tok/s | 13.16s |
| 03/11/2026, 23:38 | gpt-5.1-codex-max | 34.81 tok/s | 5.83s |
