GPT-4o API
GPT-4o is a language model from openai, available on Routeriva under the model ID gpt-4o. You call it with the same sk- key you use for every other model — no separate openai account is needed.
On Routeriva it costs $0.75 per 1M input tokens and $3.00 per 1M output tokens, compared with the official list price of $2.50 / $10.00 — about 70% less. Prices shown are the lowest across the routes that serve this model; your key is charged at its own route's price.
GPT-4o works with the official OpenAI SDKs on both /v1/chat/completions and /v1/responses, including streaming and tool calls, so Codex, Cursor and other OpenAI-based tools work by changing the base URL.
Key facts
- Model ID:
gpt-4o - Provider: openai
- Type: text
- Input: $0.75 / 1M (list $2.50)
- Output: $3.00 / 1M (list $10.00)
- Endpoints: /v1/chat/completions, /v1/responses
Good for
- General reasoning and coding
- Agents with tool calling (Codex, Responses API)
- Structured JSON output
Prices by route
| Route | Input / 1M | Output / 1M |
|---|---|---|
| Azure GPT 1 OLD | $0.75 | $3.00 |
Code sample
from openai import OpenAI
client = OpenAI(base_url="https://api.routeriva.com/v1", api_key="sk-your-key")
r = client.chat.completions.create(model="gpt-4o", messages=[{"role": "user", "content": "Hello"}])
print(r.choices[0].message.content)FAQ
How much does the GPT-4o API cost on Routeriva?
From $0.75 per 1M input tokens and $3.00 per 1M output tokens (official list $2.50 / $10.00, about 70% less). Live prices are on routeriva.com/models/gpt-4o.
What model ID do I use for GPT-4o?
Use "gpt-4o" as the model value with base URL https://api.routeriva.com/v1 and your sk- key.
Which endpoints support GPT-4o?
/v1/chat/completions, /v1/responses on https://api.routeriva.com.