OpenAI model

GPT-5 API

Send openai/gpt-5 for OpenAI vision, tools, or JSON that needs a 400,000 token window at 1.25 / 10. GPT-5.1 publishes the same 1.25 / 10 price and window, so pin 5 only if that is the id you already call. Walk away if 400k is overkill: GPT-5 Mini is 0.25 / 2, and Mini is the one with a measured 80% Safe Hit Rate.

Read quickstartEstimate cost
OpenAIPlatform curatedCatalog
ThinkingFunction CallingWeb SearchVision
Input price$1.25 / 1M tokens
Output price$10 / 1M tokens
Context length400k tokens
Max output8.2k tokens

What is GPT-5 API in NextModel?

Send openai/gpt-5 for OpenAI vision, tools, or JSON that needs a 400,000 token window at 1.25 / 10. GPT-5.1 publishes the same 1.25 / 10 price and window, so pin 5 only if that is the id you already call. Walk away if 400k is overkill: GPT-5 Mini is 0.25 / 2, and Mini is the one with a measured 80% Safe Hit Rate.

GPT-5 via NextModel: 400k-token context; $1.25 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • 400k OpenAI jobs that should not pay GPT-5 Pro 15 / 120.
  • Vision plus tool or JSON in one call at the 1.25 input price.
  • A stable openai/gpt-5 id when you are not ready to move callers to 5.1 or 5.4.

When not to use

  • You want the measured cache id. That is openai/gpt-5-mini, not this one.
  • You need more than 400k. GPT-5.4 lists 1,050,000.
  • Short cheap work. GPT-5 Nano is 0.05 / 0.40.

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","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

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

Reading

Articles that explain GPT-5

FAQ

GPT-5 API questions

What model id do I send for GPT-5?

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

Is GPT-5 different from GPT-5.1 in this catalog?

Not on the published numbers. Both list 1.25 / 10 and 400,000 tokens. Quality delta is unpublished.

CacheSafety?

No first-party row for openai/gpt-5. The 80% Safe Hit Rate belongs to openai/gpt-5-mini.

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