Choose a model to open its comparison page.
GPT-4o benchmark, API pricing, and provider data cover 680 API providers, with prices starting at $0.0066/request. GPT-4o free API options are available from 22 providers. The page also shows measured API speed and first-token latency.
OpenAI GPT-4o is a multimodal flagship model with fast text, vision, and audio understanding, optimized for real-time chat, coding assistants, and production API workloads.
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
2 metrics · Provisional
5 metrics · Estimated
4 metrics · Rated
6 metrics · Provisional
4 metrics · Estimated
1 metric · Provisional
2 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 |
|---|---|---|---|---|---|---|
OpenAI openai | $2.50/M | $10/M | 100.0% | — | — | 128K tokens / 16.4K tokens |
Azure azure | $2.50/M | $10/M | 99.9% | — | — | 128K tokens / 16.4K tokens |
Compare GPT-4o API pricing across 658 providers. Prices range from $0.0066/request to $105.00/M. 柏拉图AI offers the lowest rate at $0.0066/request. 22 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | gpt-4o-2024-11-20 | default | $2.50/M Cache read$1.25/M | $10.00/M | 88.0 t/s | 1.59 s | — | |
L1 99% | gpt-4o-2024-08-06 | default | $2.50/M Cache read$1.25/M | $10.00/M | — | — | — | |
L1 99% | gpt-4o | default | $2.50/M Cache read$1.25/M | $10.00/M | — | — | — | |
L1 99% | gpt-4o-2024-05-13 | default | $5.00/M | $15.00/M | — | — | — | |
L1 99% | gpt-4o-all | default | $30.00/M | $60.00/M | — | — | — | |
L1 100% | gpt-4o | default | -93%$0.171/M | -93%$0.685/M | 57.6 t/s | 2.58 s | — | |
L1 100% | gpt-4o-2024-08-06 | default | -93%$0.171/M | -93%$0.685/M | — | — | — | |
L1 100% | gpt-4o-2024-11-20 | default | -93%$0.171/M | -93%$0.685/M | — | — | — | |
L1 100% | gpt-4o-2024-05-13 | default | -86%$0.342/M | -90%$1.03/M | — | — | — | |
L1 100% | gpt-4o | default | -86%$0.342/M | -86%$1.37/M | 48.2 t/s | 13.14 s | — | |
L1 100% | gpt-4o-2024-08-06 | default | -86%$0.342/M | -86%$1.37/M | — | — | — | |
L1 100% | gpt-4o-2024-11-20 | default | -86%$0.342/M | -86%$1.37/M | — | — | — | |
L1 100% | gpt-4o-2024-05-13 | default | -73%$0.685/M | -79%$2.05/M | — | — | — | |
L1 100% | gpt-4o-all | default | -73%$0.685/M | -79%$2.05/M | — | — | — | |
L1 99% | gpt-4o | default | -96%$0.103/M Cache read$0.051/M | -96%$0.411/M | 39.7 t/s | 2.99 s | — | |
L1 99% | gpt-4o-2024-11-20 | default | -96%$0.103/M Cache read$0.051/M | -96%$0.411/M | — | — | — | |
L1 99% | gpt-4o-2024-08-06 | default | -96%$0.103/M Cache read$0.051/M | -96%$0.411/M | — | — | — | |
L1 99% | gpt-4o-2024-05-13 | default | -92%$0.205/M | -94%$0.616/M | — | — | — | |
L1 100% | gpt-4o-2024-08-06 | default | $2.50/M | $10.00/M | — | — | — | |
L1 100% | gpt-4o | default | $2.50/M | $10.00/M | — | — | — |
