Choose a model to open its comparison page.
GPT-5.4 Mini benchmark, API pricing, and provider data cover 596 API providers, with prices starting at $0.000075/M. GPT-5.4 Mini free API options are available from 10 providers. The page also shows measured API speed and first-token latency.
OpenAI GPT-5.4 Mini is a compact language model in the GPT-5 series, optimized for quick responses and high throughput.
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
2 metrics
2 metrics
10 metrics · Rated
7 metrics · Estimated
5 metrics · Estimated
7 metrics · Provisional
3 metrics · Provisional
0 metrics · No data
4 metrics · Provisional
2 metrics · Provisional
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 | $0.750/M | $4.50/M | 100.0% | — | — | 400K tokens / 128K tokens |
OpenAI openai/flex | $0.375/M | $2.25/M | 86.6% | — | — | 400K tokens / 128K tokens |
OpenAI openai | $0.750/M | $4.50/M | 86.6% | — | — | 400K tokens / 128K tokens |
OpenAI openai/priority | $1.50/M | $9/M | 86.6% | — | — | 400K tokens / 128K tokens |
Compare GPT-5.4 Mini API pricing across 586 providers. Prices range from $0.000075/M to $7492.50/M. FineOneAPI offers the lowest rate at $0.000075/M. 10 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 1% | gpt-5.4-mini | default | $0.750/M Cache read$0.075/M | $4.50/M | 245.0 t/s+45% | 2.62 s-61% | — | |
L1 100% | gpt-5.4-mini | default | -93%$0.051/M | -93%$0.308/M | 200.7 t/s+19% | 1.44 s-78% | ||
L1 100% | gpt-5.4-mini-2026-03-17 | default | -93%$0.051/M | -93%$0.308/M | — | — | — | |
L1 99% | gpt-5.4-mini | default | $0.750/M Cache read$0.075/M | $4.50/M | 139.4 t/s | 2.84 s-57% | — | |
L1 70% | gpt-5.4-mini | default | $0.750/M Cache read$0.075/M | $4.50/M | 97.9 t/s | 4.04 s-40% | — | |
L1 100% | gpt-5.4-mini | GPT-Entry | -97%$0.022/M Cache read$0.0022/M | -97%$0.135/M | 94.8 t/s | 2.34 s-65% | ||
L1 83% | gpt-5.4-mini | default | $2.40/M Cache read$2.40/MCache write$2.40/MCache write 1h$3.84/M | $14.40/M | 92.9 t/s | 4.06 s-39% | — | |
L1 100% | gpt-5.4-mini | codex-sale | -96%$0.032/M Cache read$0.0032/M | -96%$0.193/M | — | — | — | |
L1 100% | gpt-5.4-mini | default | $0.750/M | $4.50/M | — | — | — | |
L1 100% | gpt-5.4-mini-xhigh | default | $0.750/M | $4.50/M | — | — | — | |
L1 100% | gpt-5.4-mini-medium | default | $0.750/M | $4.50/M | — | — | — | |
L1 100% | gpt-5.4-mini-low | default | $0.750/M | $4.50/M | — | — | — | |
L1 100% | gpt-5.4-mini-high | default | $0.750/M | $4.50/M | — | — | — | |
L1 100% | gpt-5.4-mini-2026-03-17 | default | $0.750/M | $4.50/M | — | — | — | |
Dext API Free | L1 100% | gpt-5.4-mini | 公益 | Free | Free | — | — | — |
L1 100% | gpt-5.4-mini | default | -86%$0.103/M Cache read$0.068/MCache write$0.068/MCache write 1h$0.110/M | -86%$0.619/M | — | — | — | |
L1 99% | gpt-5.4-mini | gpt混合号池 | -90%$0.075/M Cache read$0.0075/M | -90%$0.450/M | — | — | — | |
L1 100% | gpt-5.4-mini | 临时渠道 | -99%$0.010/M Cache read$0.0010/M | -99%$0.062/M | — | — | — | |
L1 100% | gpt-5.4-mini | default | -97%$0.025/M Cache read$0.0025/M | -97%$0.151/M | — | — | — | |
L1 100% | gpt-5.4-mini | chatgpt-pro | -95%$0.036/M Cache read$0.0036/MCache write$0.024/MCache write 1h$0.038/M | -95%$0.216/M | — | — | — |
