GPT-4o
GPT-4o is served by 3 providers that kRouter can route to, with a 128K-token context window and pricing from $2.50 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get GPT-4o
| Provider | Route as |
|---|---|
| GitHub Copilot | gh/gpt-4o |
| OpenAI | openai/gpt-4o |
| Blackbox AI | blackbox/gpt-4o |
What GPT-4o is suited for
At 128K the window is modest, so it is better suited to focused edits than to long agent runs that accumulate history. It answers directly rather than reasoning at length, which keeps latency and output cost down on routine edits. Tool and function calling are supported, so it can drive an agent loop. It accepts images, so screenshots and diagrams can go straight into the prompt. Cached input is billed at $1.25 against $2.50 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 128K
- Max output
- 16K
- Input / 1M
- $2.50
- Output / 1M
- $10.00
- Image input
- Tool / function calling
Cheaper alternatives to GPT-4o
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve GPT-4o for the work that actually needs it.
- Kimi K2.5$1.20 in · $4.80 out per 1M
- Kimi K2.6$1.20 in · $4.80 out per 1M
- Kimi-K2.7$1.20 in · $4.80 out per 1M
- Qwen3 Coder Plus$1.00 in · $4.00 out per 1M
GPT-4o FAQ
How much does GPT-4o cost?
GPT-4o is $2.50 per 1M input tokens and $10.00 per 1M output tokens. Cached input is $1.25, which matters a lot for agent work that resends the same context each turn.
Which providers serve GPT-4o?
3 providers: GitHub Copilot, OpenAI, Blackbox AI. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is GPT-4o's context window?
128K tokens, with up to 16K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Is there a cheaper alternative to GPT-4o?
Yes — Kimi K2.5 ($1.20/1M in), Kimi K2.6 ($1.20/1M in), Kimi-K2.7 ($1.20/1M in), Qwen3 Coder Plus ($1.00/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep GPT-4o for the work that needs it.
Route to GPT-4o from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter