GPT-5.4 API

Model ID: gpt-5.4 · OpenAI · Billed per token

GPT-5.4 pricing

AibermOfficial
Input$0.690 / 1M tokens—
Output$5.52 / 1M tokens—
Cache read$0.138 / 1M tokens

Prices in USD. Pay as you go, no minimum spend.

Get an API key · Read the docs

How to call GPT-5.4

Use your Aiberm API key, set the base URL, and pass gpt-5.4 as the model name.

Supported request formats:

curl https://aiberm.org/v1/chat/completions \
  -H "Authorization: Bearer $AIBERM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5.4", "messages": [{"role": "user", "content": "Hello"}]}'

Use GPT-5.4 in your tools

FAQ

How much does the GPT-5.4 API cost?

On Aiberm, GPT-5.4 (gpt-5.4) costs $0.690 per 1M input tokens and $5.52 per 1M output tokens. You pay only for the tokens you use, with no minimum spend.

How do I call GPT-5.4 through Aiberm?

Set the base URL to https://aiberm.org, use gpt-5.4 as the model name, and authenticate with your Aiberm API key. Supported request formats: OpenAI Chat Completions.

Does GPT-5.4 support prompt caching?

Yes. Cached input tokens are billed at $0.138 per 1M tokens.

Can I use GPT-5.4 in Codex CLI, OpenCode or OpenClaw?

Yes. Add Aiberm as a provider in Codex CLI, OpenCode, OpenClaw with the base URL and your API key, then select gpt-5.4. Each tool has a step-by-step guide in the Aiberm docs.

More OpenAI models

All models and prices