GPT-4o API

Model ID: openai/gpt-4o · OpenAI · Billed per token

GPT-4o pricing

AibermOfficial
Input$0.414 / 1M tokens$2.50
Output$1.66 / 1M tokens$10.00
Cache read$0.124 / 1M tokens

Prices in USD. About 83% below the official price. Pay as you go, no minimum spend.

Get an API key · Read the docs

How to call GPT-4o

Use your Aiberm API key, set the base URL, and pass openai/gpt-4o 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": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'

Use GPT-4o in your tools

FAQ

How much does the GPT-4o API cost?

On Aiberm, GPT-4o (openai/gpt-4o) costs $0.414 per 1M input tokens and $1.66 per 1M output tokens, compared with the official $2.50 / $10.00 — about 83% less. You pay only for the tokens you use, with no minimum spend.

How do I call GPT-4o through Aiberm?

Set the base URL to https://aiberm.org, use openai/gpt-4o as the model name, and authenticate with your Aiberm API key. Supported request formats: OpenAI Chat Completions.

Does GPT-4o support prompt caching?

Yes. Cached input tokens are billed at $0.124 per 1M tokens.

Can I use GPT-4o 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 openai/gpt-4o. Each tool has a step-by-step guide in the Aiberm docs.

More OpenAI models

All models and prices