GPT-5 Pro
API guide
Chat completion
GPT-5 Pro is called via TheRouter's standard chat completions endpoint. Unlike other GPT-5 variants, reasoning_effort is locked to 'high' β the model always performs deep reasoning. The 272K max output makes this ideal for long-form generation.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5-pro",
"messages": [
{"role": "user", "content": "Prove the Riemann hypothesis step by step, explaining each lemma."}
]
}'Streaming
GPT-5 Pro supports streaming of its reasoning chain β you can observe the model's chain-of-thought before the final answer. Useful for transparency in research and safety-critical applications.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: text/event-stream" \
-d '{
"model": "openai/gpt-5-pro",
"messages": [
{"role": "user", "content": "Derive the equation for relativistic rocket motion."}
],
"stream": true
}'Tool calling
GPT-5 Pro supports function calling and parallel tool use. Combine with reasoning for multi-step tool orchestration β the model can plan, call, iterate, and synthesise across multiple tool outputs.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5-pro",
"messages": [{"role": "user", "content": "Find the current stock price of NVDA and TSMC, compare their P/E ratios, and calculate which one had better 1-year growth."}],
"tools": [{
"type": "function",
"function": {
"name": "get_stock_price",
"description": "Get current stock price and P/E ratio for a ticker symbol",
"parameters": {
"type": "object",
"properties": {
"ticker": {"type": "string", "description": "Stock ticker symbol"}
},
"required": ["ticker"]
}
}
}],
"parallel_tool_calls": true
}'Structured output
GPT-5 Pro supports response_format for structured JSON output within its deep reasoning chain. Useful for producing structured research reports, multi-field classification, or complex data extraction with verified correctness.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5-pro",
"messages": [
{"role": "user", "content": "Analyse this clinical trial result and return findings in the specified JSON schema:\n\n<trial data>"}
],
"response_format": { "type": "json_schema", "json_schema": {
"name": "trial_analysis",
"schema": {
"type": "object",
"properties": {
"efficacy": {"type": "string"},
"safety_concerns": {"type": "array", "items": {"type": "string"}},
"recommendation": {"type": "string"}
},
"required": ["efficacy", "safety_concerns", "recommendation"]
}
}}
}'Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date | developers.openai.com β | 2026-05-29 | verified |
| Knowledge cutoff | platform.openai.com β | 2026-05-29 | verified |
| Max output tokens | simonwillison.net β | 2026-05-29 | verified |
| Reasoning mode | developers.openai.com β | 2026-05-29 | verified |
| API availability | developers.openai.com β | 2026-05-29 | verified |
| License | β | β | verified |
| AIME 2025 | openai.com β | 2026-05-29 | verified |
| GPQA Diamond | openai.com β | 2026-05-29 | verified |
| Humanity's Last Exam | openai.com β | 2026-05-29 | verified |
| SWE-bench Verified | openai.com β | 2026-05-29 | to verify |
| MMMU | openai.com β | 2026-05-29 | to verify |
| HealthBench Hard | openai.com β | 2026-05-29 | to verify |
| OpenAI launches GPT-5 Pro at DevDay 2025 | developers.openai.com β | 2026-05-29 | verified |
| GPT-5 announced β Pro variant teased for Pro subscribers | openai.com β | 2026-05-29 | verified |
| Is GPT-5 Pro available via the standard OpenAI Chat Completions API? | developers.openai.com β | 2026-05-29 | to verify |
| What is the maximum output length of GPT-5 Pro? | simonwillison.net β | 2026-05-29 | to verify |
| Can GPT-5 Pro see images? | platform.openai.com β | 2026-05-29 | to verify |
| How much does GPT-5 Pro cost on TheRouter? | platform.openai.com β | 2026-05-29 | to verify |
| What does 'reasoning_effort: high only' mean in practice? | developers.openai.com β | 2026-05-29 | to verify |