GPT-4o mini
GPT-4o mini by OpenAI: $0.15 input and $0.6 output per 1M tokens, 128K context. Call it through the odnoga LLM gateway.
GPT-4o mini is served by OpenAI and called through odnoga with the same OpenAI-compatible request shape as every other model in the catalog. It accepts images alongside text. It supports tool and function calling. It can be forced to return structured JSON. Its 128K-token context window sets how much input you can send in one request. Cached input is billed at $0.075 per 1M tokens, so repeated prefixes cost less.
Specification and price
| Vendor | OpenAI |
|---|---|
| Model ID | gpt-4o-mini |
| Context window | 128K tokens |
| Max output | 16K tokens |
| Capabilities | Vision, Tools, JSON mode, Streaming |
| Per 1M tokens | Vendor cost | Your price on Free+7% |
|---|---|---|
| Input | $0.15 | $0.161 |
| Output | $0.6 | $0.645 |
| Cached input | $0.075 | $0.081 |
Vendor cost is the list price per million tokens as recorded in the odnoga catalog; your price applies your plan margin with the same formula that bills every request — see pricing. Pricing
Call it through odnoga
const res = await fetch("https://api.odnoga.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.ODNOGA_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "gpt-4o-mini",
messages: [{ role: "user", content: "Hello" }],
}),
});
Same request shape for every vendor in the catalog — swap the model id and odnoga handles keys, routing, limits and cost accounting.
How to use GPT-4o mini
Derived from the odnoga catalog record for this model.
Best for
- High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries.
- Work that mixes images with text — screenshots, scanned documents, charts, product photos.
- Agents and workflows that call your own functions, because the model supports tool calling.
- Machine-readable output you can write straight into a database, using enforced JSON.
- User-facing chat where partial output should appear while the model is still writing.
Not the right pick when
- Anything where a wrong answer is costly without a human check — no model in the catalog removes that requirement.
Practical tips through odnoga
- 01Pin the model id in a managed prompt version, so a model swap is a version change you can compare and roll back, not an edit in application code.
- 02Compare it against 2–8 other models on the same frozen test cases in the evaluation laboratory before you make it the production default.
- 03Keep the stable part of your prompt at the front: cached input is billed at $0.075 per 1M tokens instead of $0.15.
- 04For repeated identical deterministic calls, odnoga answer reuse returns the stored answer and bills no vendor tokens — turn it off for creative output.
- 05Ask for JSON through the response format rather than in the prompt text — the schema is enforced instead of suggested.
- 06Set a fallback model on the route so a vendor incident degrades quality instead of returning an error, and a per-tenant budget so one caller cannot spend the month.
What a month costs
1,000 calls a month, 10,000 input tokens and 2,000 output tokens each, at your Free price (vendor cost +7%):
| Input (10M tokens) | $1.61 |
|---|---|
| Output (2M tokens) | $1.29 |
| Your cost per month on Free | $2.90 |
Vendor list cost $2.70 + odnoga margin $0.203 (+7%). Cached input or answer reuse lowers it; odnoga records both numbers per request.
GPT-4o mini compared
| Model | Context | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|
| GPT-4o mini | 128K | $0.15 | $0.6 | Vision, Tools, JSON mode, Streaming |
| ChatGPT (chat-latest) | 400K | $5 | $30 | Vision, Tools, JSON mode, Streaming |
| GPT Image 1 mini | — | $2 | $8 | Vision |
Questions
- How much does GPT-4o mini cost per 1M tokens?
- OpenAI lists $0.15 / $0.6 per 1M input / output tokens in the odnoga catalog. Through odnoga you pay that vendor price plus your plan margin, and every request is recorded with both numbers.
- What is GPT-4o mini best for?
- High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries. Work that mixes images with text — screenshots, scanned documents, charts, product photos. Agents and workflows that call your own functions, because the model supports tool calling.
- Can I switch to GPT-4o mini without changing my code?
- Yes. odnoga exposes one OpenAI-compatible endpoint, so switching means sending "gpt-4o-mini" as the model id — or changing it in the managed prompt version, with no application deploy.
- How large is the GPT-4o mini context window?
- 128K tokens of input, with up to 16K tokens of output per response.
All models · Pricing · Docs · Compare models in the evaluation lab