Choose a model to open its comparison page.
GPT-5 benchmark, API pricing, and provider data cover 1068 API providers, with prices starting at $0.0027/request. GPT-5 free API options are available from 17 providers. The page also shows measured API speed and first-token latency.
OpenAI GPT-5 is OpenAI frontier general-purpose model with improved reasoning depth, coding reliability, and multimodal understanding for production assistants and agent workflows.
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.
2 metrics
2 metrics
5 metrics · Estimated
5 metrics · Rated
5 metrics · Rated
5 metrics · Provisional
3 metrics · Estimated
0 metrics · Provisional
2 metrics · Provisional
1 metric · 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 | $1.25/M | $10/M | 97.0% | — | — | 400K tokens / 128K tokens |
OpenAI openai/default | $1.25/M | $10/M | 95.0% | — | — | 400K tokens / 128K tokens |
Azure azure/swedencentral | $1.25/M | $10/M | — | — | — | 400K tokens / 128K tokens |
Compare GPT-5 API pricing across 1051 providers. Prices range from $0.0027/request to $262.50/M. Yun API offers the lowest rate at $0.0027/request. 17 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-5-chat-latest | default | -86%$0.171/M | -86%$1.37/M | 101.9 t/s+38% | 0.95 s | — | |
L1 100% | gpt-5-2025-08-07 | default | -86%$0.171/M | -86%$1.37/M | — | — | — | |
L1 100% | gpt-5 | default | -86%$0.171/M | -86%$1.37/M | — | — | — | |
L1 100% | gpt-5-chat | default | $10.27/M | $82.19/M | — | — | — | |
L1 100% | gpt-5-chat-2025-08-07 | default | $10.27/M | $82.19/M | — | — | — | |
L1 100% | gpt-5-chat-2025-10-03 | default | $10.27/M | $82.19/M | — | — | — | |
L1 100% | gpt-5-chat-latest | default | $1.25/M | $10.00/M | 95.5 t/s+29% | 1.23 s | — | |
L1 100% | gpt-5-2025-08-07 | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5 | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-low | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-minimal | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-medium | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-high | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-fast | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-all | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5-flex | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gpt-5 | default | -87%$0.159/M | -87%$1.27/M | 58.1 t/s | 17.42 s | — | |
L1 100% | gpt-5-2025-08-07 | default | -87%$0.159/M | -87%$1.27/M | — | — | — | |
L1 100% | gpt-5-chat-latest | default | -87%$0.159/M | -87%$1.27/M | — | — | — | |
L1 100% | gpt-5-chat-2025-10-03 | default | $9.55/M | $76.44/M | — | — | — |
