GPT Image 2
GPT Image 2 by OpenAI: $5 input and $30 output per 1M tokens, — context. Call it through the odnoga LLM gateway.
GPT Image 2 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. Cached input is billed at $1.25 per 1M tokens, so repeated prefixes cost less.
Specification and price
| Vendor | OpenAI |
|---|---|
| Model ID | gpt-image-2 |
| Context window | — tokens |
| Max output | — |
| Capabilities | Vision |
| Per 1M tokens | Vendor cost | Your price on Free+7% |
|---|---|---|
| Input | $5 | $5.38 |
| Output | $30 | $32.26 |
| Cached input | $1.25 | $1.34 |
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-image-2",
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 Image 2
Reviewed 2026-09-14
Best for
- Product and marketing imagery generated from a text description, at flexible image sizes.
- Editing an existing image while keeping the parts that must not change — the model takes high-fidelity image input.
- In-product image features where users describe what they want in plain language.
- Iterating on one visual detail at a time, which is how OpenAI recommends refining edits.
Not the right pick when
- Text answers of any kind: this is an image model, not a chat model.
- Pixel-exact reproduction of a logo or legal document — always have a human check the result.
- Bulk generation without a cost ceiling; image calls are priced per image, not per token.
Practical tips through odnoga
- 01Describe subject, composition, style and constraints in that order, then refine one thing per iteration.
- 02For edits, say explicitly what must stay the same — that is what preserves detail across rounds.
- 03Set a per-tenant budget before exposing generation to end users; image spend climbs faster than text.
- 04Keep the prompt in a managed version so a change to house style is one version bump, not a code change.
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) | $53.76 |
|---|---|
| Output (2M tokens) | $64.52 |
| Your cost per month on Free | $118 |
Vendor list cost $110 + odnoga margin $8.28 (+7%). Cached input or answer reuse lowers it; odnoga records both numbers per request.
GPT Image 2 compared
| Model | Context | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|
| GPT Image 2 | — | $5 | $30 | Vision |
| ChatGPT (chat-latest) | 400K | $5 | $30 | Vision, Tools, JSON mode, Streaming |
| GPT Image 1 mini | — | $2 | $8 | Vision |
Questions
- What can GPT Image 2 do?
- OpenAI describes it as a state-of-the-art image generation model for fast, high-quality generation and editing, supporting flexible image sizes and high-fidelity image inputs.
- How is it billed through odnoga?
- Per generated image at the catalog rate, recorded in the same per-request ledger as text calls, so image and text spend appear together per tenant.
- Can I keep a brand style consistent?
- Put the style rules in a managed prompt version and reuse it for every generation; changing the style is then one version change with an audit trail.
All models · Pricing · Docs · Compare models in the evaluation lab
Sources: OpenAI — GPT Image 2 model page, OpenAI — image prompting guide