Models/OpenAI/GPT Image 1.5
OpenAIimage1 route

GPT Image 1.5

OpenAI's image model. Follows long, detailed prompts closely and renders legible text, layouts and edits.

gpt-image-1.5Get API key

Pricing per image

SizePer image
1:1-high$0.1111 credits
1:1-low$0.01lowest1 credit
1:1-medium$0.033 credits
2:3-high$0.1616 credits
2:3-low$0.022 credits
2:3-medium$0.044 credits
3:2-high$0.1616 credits
3:2-low$0.022 credits
3:2-medium$0.044 credits

Billed in credits per image (100 credits = $1, rounded up to a whole credit). Charged once, only for the route that succeeds. Failed attempts cost $0.00.

Request

# 1. Submit a generation and keep its id (a refusal prints {"error": {"message": ...}})
RESP=$(curl -s https://api.revana.si/v1/generations \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-1.5",
    "input": {
      "prompt": "A product photo of a ceramic coffee cup on a linen tablecloth, soft morning light",
      "aspect_ratio": "1:1"
    }
  }')
echo "$RESP"
ID=$(echo "$RESP" | jq -r .id)

# 2. Poll it until status is "succeeded" or "failed" (a failed one has error.message)
curl -s https://api.revana.si/v1/generations/$ID \
  -H "Authorization: Bearer $REVANA_API_KEY"

# 3. Download the file once it has succeeded
curl -L https://api.revana.si/v1/generations/$ID/content \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -o out.png

Set REVANA_API_KEY to your key. Full reference in the quickstart.

Options

Tasks
Text to imageImage to image
Aspect ratios
1:13:22:3
Input images
Up to 15
Billing unit
per image
Model id
gpt-image-1.5

1 route

One route today. If it fails you are not charged.

About the GPT Image 1.5 API

How much does the GPT Image 1.5 API cost?

GPT Image 1.5 costs from $0.01 per image on Revana (1:1-high: $0.11; 1:1-low: $0.01; 1:1-medium: $0.03; 2:3-high: $0.16; 2:3-low: $0.02; 2:3-medium: $0.04; more in the price table). You pay in prepaid credits, 100 credits to the dollar, with no subscription or monthly minimum. A generation that fails costs nothing.

How do I call GPT Image 1.5 from code?

Send POST https://api.revana.si/v1/generations with {"model": "gpt-image-1.5", "input": {...}} and your Revana API key as a Bearer token, poll GET /v1/generations/{id} until it succeeds, then download GET /v1/generations/{id}/content. Every model on Revana takes the same request shape.

What happens if a GPT Image 1.5 generation fails?

You are charged once, only for the route that delivers. A failed generation costs $0.00.

What can GPT Image 1.5 do on Revana?

GPT Image 1.5 supports text to image and image to image, aspect ratios 1:1, 3:2, 2:3 and up to 15 input images. A value it does not offer is refused with 422 before anything is charged.

Can my AI agent use GPT Image 1.5?

Yes. Connect the Revana MCP server (https://revana.si/api/mcp) to Claude, ChatGPT, Cursor or Codex, or have the agent call the REST API. The agent can list models, get a free quote and generate on your credits.

Guides

Compare with similar models

Also as markdown for agents. Every model and price: models.json.