GPT‑5 is here: Proxed.AI now supports the GPT‑5 family

We just shipped support for the GPT‑5 family across Proxed.AI. That means you can route requests to OpenAI’s newest models with the same secure proxy, partial keys, and DeviceCheck protections you already use.

#

What’s included

• New models: gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat-latest
• Pricing + cost tracking: Included in our pricing engine and dashboard estimates
• Validation: Integrated into model lists, badges, and capability checks

#

Pricing (per 1M tokens)

Model	Input	Output
gpt-5	$1.25	$10.00
gpt-5-mini	$0.25	$2.00
gpt-5-nano	$0.05	$0.40
gpt-5-chat-latest	$1.25	$10.00

Note: Cached input and alternative tiers (Flex, Batch, Priority) are coming later to the dashboard. Standard tier rates are live now in our calculators.

#

How to use

Switch your OpenAI model to any GPT‑5 variant. Everything else stays the same.

// Example: switch model id
const request = await fetch(`https://api.proxed.ai/v1/openai/${PROJECT_ID}/chat/completions`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${PARTIAL_KEY}.${DEVICE_TOKEN}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-5",
    messages: [{ role: "user", content: "Give me a concise plan." }],
  }),
});

If you prefer lower latency or cost, try gpt-5-mini or gpt-5-nano.

#

Notes

• All changes are backward-compatible. No SDK changes required.
• Cost estimates reflect the new GPT‑5 rates immediately.
• You can combine GPT‑5 with our structured routes (Text/Vision/PDF) as usual.

Have feedback or issues? Open a ticket on our GitHub or ping us on X.