All models
Standard · OpenAI

GPT-5.4

Standard GPT-5 tier. Strong general purpose at moderate cost.

Context
200k
Max output
16k
Pro input
$0.4/M
Pro output
$2.4/M

Pricing — every plan

Plan
Input / 1M
Output / 1M
Official direct
$2.00
$12.00
Basic (free, 70% off)
$0.60
$3.60
Pro ($19 lifetime, 80% off)
$0.40
$2.40

Code samples

OpenAI SDK (Python) — works for all 3 vendors
from openai import OpenAI

client = OpenAI(
    base_url="https://claudeapi.cheap/api/proxy/v1",
    api_key="sk-cc-your-key-here",
)
resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
cURL
curl https://claudeapi.cheap/api/proxy/v1/chat/completions \
  -H "Authorization: Bearer sk-cc-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Tools that work great with GPT-5.4

Terminal coding agent

Codex CLI

OpenAI's official command-line coding agent — direct competitor to Claude Code, with the same token-burning appetite.

IDE extension

Continue.dev

Open-source IDE assistant for VS Code and JetBrains — autocomplete, chat, edit, agent — all powered by your API key.

FAQ

What does GPT-5.4 cost via ClaudeAPI.cheap?

On the Pro plan ($19 lifetime), GPT-5.4 is $0.40 per 1M input tokens and $2.40 per 1M output tokens. That's 80% off the official price ($2/$12). The Basic plan is free forever at 70% off.

Is GPT-5.4 the same model as direct API access?

Yes. The proxy forwards requests to the same underlying model with the same context window (200k tokens) and capabilities. Only vendor-fingerprint headers are stripped. Behavior, output quality, and reasoning are identical.

How do I switch my existing code to GPT-5.4 via ClaudeAPI.cheap?

Change one line — the base URL — in your existing Anthropic or OpenAI SDK initialization. Use https://claudeapi.cheap/api/proxy for Anthropic-format calls or https://claudeapi.cheap/api/proxy/v1 for OpenAI-format. Use your sk-cc-... key as the API key. No code changes beyond that.

What's the rate limit on GPT-5.4?

Pro plan caps at 500 requests/min and 2M tokens/min globally across all models. Basic plan is 200 RPM / 1M TPM. Newer models may have lower upstream caps that float — see /status for live availability.

Does GPT-5.4 support streaming and tools?

Yes. Streaming, tool/function calling, and prompt caching all work end-to-end. Vision is supported where the upstream model supports it.

Ready to use GPT-5.4 cheaper?

Free Basic plan, $19 lifetime Pro. Crypto only. No subscription.

Get an API key — free