OpenAI model

GPT-5 Pro API

Send openai/gpt-5-pro when the workload is worth 15 input and 120 output per million tokens. The listed window is still 400,000 tokens, the same as GPT-5 and Mini. If you have not compared that bill to openai/gpt-5 at 1.25 / 10, do not ship Pro as the default. CacheSafety is unpublished.

Read quickstartEstimate cost
OpenAIPlatform curatedCatalog
ThinkingFunction CallingWeb SearchVision
Input price$15 / 1M tokens
Output price$120 / 1M tokens
Context length400k tokens
Max output8.2k tokens

What is GPT-5 Pro API in NextModel?

Send openai/gpt-5-pro when the workload is worth 15 input and 120 output per million tokens. The listed window is still 400,000 tokens, the same as GPT-5 and Mini. If you have not compared that bill to openai/gpt-5 at 1.25 / 10, do not ship Pro as the default. CacheSafety is unpublished.

GPT-5 Pro via NextModel: 400k-token context; $15 / 1M tokens in / $120 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • Explicit Pro spend, not an accidental default.
  • 400k OpenAI vision or tool work that you already decided is not a Mini or GPT-5 job.
  • A paid overflow path behind cheaper GPT-5 ids on the same gateway.

When not to use

  • You wanted 400k OpenAI cheaply. That is Mini or GPT-5.
  • You need a cache score. Pro has no first-party row.
  • You need more than 400k. GPT-5.4 lists 1,050,000 at 2.50 / 15.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"openai/gpt-5-pro","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

OpenAICatalog

GPT-4.1

GPT-4.1 via NextModel: 1M-token context; $2 / 1M tokens in / $8 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$2 / 1M tokensInput$8 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-4.1 Mini

GPT-4.1 Mini via NextModel: 1M-token context; $0.4 / 1M tokens in / $1.60 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.4 / 1M tokensInput$1.60 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-4.1 Nano

GPT-4.1 Nano via NextModel: 1M-token context; $0.1 / 1M tokens in / $0.4 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.1 / 1M tokensInput$0.4 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare GPT-5 Pro

GPT-5 Pro vs GPT-4.1GPT-5 Pro vs GPT-4.1 MiniGPT-5 Pro vs GPT-4.1 NanoGPT-5 Pro vs GPT-4oGPT-5 Pro vs GPT-4o-mini

Reading

Articles that explain GPT-5 Pro

FAQ

GPT-5 Pro API questions

What model id do I send for GPT-5 Pro?

Send openai/gpt-5-pro to https://api.nextmodel.app/v1.

Why is this not the default GPT-5?

GPT-5 lists the same 400,000 token window at 1.25 / 10. Pro is 15 / 120. Quality delta is unpublished.

CacheSafety?

Unpublished for this exact id.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.

Get your API keyRead the quickstart