All models

GPT-Image-2.6 Flare

New Launched on IteraCompute

Online

OpenAI

openai/gpt-image-2.6-flare
Tool calling
UnsupportedTool calling · Unsupported
Reasoning
UnsupportedReasoning · Unsupported
Vision
SupportedVision · Supported
Streaming
UnsupportedStreaming · Unsupported
JSON mode
UnsupportedJSON mode · Unsupported

USD / 1M tokens

Text input
$5.00
Image input
$8.00
Image output
$30.00
Precision
Official precision
Price checked

Overview

GPT-Image-2.6 Flare accepts text and reference images and produces raster images. This supplier route exposes generation and multipart editing through the Images API. Use the parameter table and operation-specific constraints below.

Version
gpt-image-2.6-flare
Input / output
text, image / image
Endpoint
/v1/images/generations, /v1/images/edits

API protocols and integration

Base URL · OpenAI SDK
https://api.iteracompute.com/v1
Authentication
Authorization: Bearer ITERACOMPUTE_API_KEY

Choose request fields, response parsing and stream completion by endpoint. This table describes wire formats; see this model's capabilities and verification scope.

Customer endpointModel statusInput / output budgetResultSSE completion
OpenAI Images · Generation
POST /v1/images/generations
Declared for this modelprompt; Gemini: contents / generationConfig
n (1–4); model-specific size and quality
data[].b64_json; usageunsupported
OpenAI Images · Editing
POST /v1/images/edits
Declared for this modelmultipart: image[]; prompt; optional mask
n (1–4); size; quality
data[].b64_json; usageunsupported

Generation uses JSON; GPT image edits use multipart. Images are returned as base64 and billed by actual tokens.

View docs
LLMs.txt · Copy for an AI coding assistant

Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.

LLMs.txt
# IteraCompute · openai/gpt-image-2.6-flare

Model ID: openai/gpt-image-2.6-flare
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json

Use only the customer endpoints below. Request and response formats differ by protocol. An endpoint declaration does not certify every capability.

## Images · Generation
POST https://api.iteracompute.com/v1/images/generations
Input: prompt; Gemini: contents / generationConfig
Output budget: n (1–4); model-specific size and quality
Read result: data[].b64_json; usage
SSE completion: unsupported
Docs: https://iteracompute.com/docs.html#images-api

## Images · Editing
POST https://api.iteracompute.com/v1/images/edits
Input: multipart: image[]; prompt; optional mask
Output budget: n (1–4); size; quality
Read result: data[].b64_json; usage
SSE completion: unsupported
Docs: https://iteracompute.com/docs.html#images-api

## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Parameter revision: 2a00204d4c1dbd1d761c0d5e9e658b8112656654df03428eb0bed44e603109be
Capability tools: disabled
Capability reasoning: disabled
Capability vision: configured enabled (see verification scope)
Capability streaming: disabled
Capability json_mode: disabled
Capability image_generation: configured enabled (see verification scope)
Capability image_editing: configured enabled (see verification scope)
- prompt: string; accepted; min=unknown; max=unknown; default=Undisclosed. Image instruction, 1–4000 UTF-8 bytes.
- n: integer; accepted; min=1; max=4; default=Undisclosed. Number of completions; many routes accept only 1.
- size: string; accepted; min=unknown; max=unknown; default=Undisclosed. Image dimensions; pixel and aspect limits also apply.
- response_format: enum; accepted; values=["b64_json"]; default=Undisclosed. Text: Chat output format. Images: b64_json only; not text JSON mode.
- stream: enum; accepted; values=[false]; default=Undisclosed. Enable SSE streaming; completion markers depend on the protocol.
- quality: enum; accepted; values=["auto","low","medium","high","xhigh","max"]; default=Undisclosed. Image quality; editing accepts low, medium or high.
- output_format: enum; accepted; values=["png","jpeg","webp"]; default=Undisclosed. Raster image encoding: png, jpeg or webp.
- output_compression: integer; accepted; min=0; max=100; default=Undisclosed. JPEG/WebP compression, 0–100; unavailable for PNG.
- moderation: enum; accepted; values=["auto","low"]; default=Undisclosed. Supplier image moderation setting: auto or low.
- background: enum; accepted; values=["auto","opaque","transparent"]; default=Undisclosed. Responses: background execution (false on stateless routes). Images: auto, opaque or transparent.
- image: array; accepted; min=unknown; max=unknown; default=Undisclosed. Editing reference uploads (image[] in multipart), 1–4 files; total reference and mask bytes ≤8 MiB.
- mask: object; accepted; min=unknown; max=unknown; default=Undisclosed. Optional PNG mask upload for image editing.

## Images example · JSON body
```json
{
  "model": "openai/gpt-image-2.6-flare",
  "prompt": "A blue square on a white background",
  "n": 1,
  "size": "1024x1024",
  "response_format": "b64_json",
  "quality": "low",
  "output_format": "png"
}
```

## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.

Open plain text

API parameters

  • Use POST /v1/images/generations with JSON, or POST /v1/images/edits with multipart image[] files. Generated and edited images include supplier usage for reconciliation.
  • Generation quality accepts auto, low, medium, high, xhigh and max. output_compression is 0–100 and applies only to JPEG or WebP. Background accepts auto, opaque or transparent.
  • Retail follows official Standard rates: text input USD 5, image input USD 8 and image output USD 30 per million tokens. Image output is not free text output.
  • Cost uses actual text-input, image-input and image-output tokens. Size and quality can change token usage; do not treat a sample image cost as a fixed per-image price.

These parameters and ranges describe the current route. Account and context limits also apply. Parameter acceptance does not establish model capability.

Tool calling
Unsupported
Reasoning
Unsupported
Vision
Supported
Streaming
Unsupported
JSON mode
Unsupported
Image generation
Supported
Image editing
Supported

Parameters and values

Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.

ParameterTypeAcceptanceRangeUsage / protocol
stringAccepted—Image instruction, 1–4000 UTF-8 bytes.
integerAccepted[1, 4]Number of completions; many routes accept only 1.
stringAccepted—Image dimensions; pixel and aspect limits also apply.
enumAccepted["b64_json"]Text: Chat output format. Images: b64_json only; not text JSON mode.
enumAccepted[false]Enable SSE streaming; completion markers depend on the protocol.
enumAccepted["auto","low","medium","high","xhigh","max"]Image quality; editing accepts low, medium or high.
enumAccepted["png","jpeg","webp"]Raster image encoding: png, jpeg or webp.
integerAccepted[0, 100]JPEG/WebP compression, 0–100; unavailable for PNG.
enumAccepted["auto","low"]Supplier image moderation setting: auto or low.
enumAccepted["auto","opaque","transparent"]Responses: background execution (false on stateless routes). Images: auto, opaque or transparent.
arrayAccepted—Editing reference uploads (image[] in multipart), 1–4 files; total reference and mask bytes ≤8 MiB.
objectAccepted—Optional PNG mask upload for image editing.

Current configuration example

POST /v1/images/generations

Image generation request
{
  "model": "openai/gpt-image-2.6-flare",
  "prompt": "A blue square on a white background",
  "n": 1,
  "size": "1024x1024",
  "response_format": "b64_json",
  "quality": "low",
  "output_format": "png"
}

Parameter revision:2a00204d4c1d

API

POST /v1/images/generations

import base64, json, os, urllib.request

body = json.loads("{\n  \"model\": \"openai/gpt-image-2.6-flare\",\n  \"prompt\": \"A blue square on a white background\",\n  \"n\": 1,\n  \"size\": \"1024x1024\",\n  \"response_format\": \"b64_json\",\n  \"quality\": \"low\",\n  \"output_format\": \"png\"\n}")
request = urllib.request.Request(
    "https://api.iteracompute.com/v1/images/generations",
    data=json.dumps(body).encode(),
    headers={"Authorization": "Bearer " + os.environ["ITERACOMPUTE_API_KEY"],
             "Content-Type": "application/json"},
)
with urllib.request.urlopen(request, timeout=1800) as response:
    result = json.load(response)
with open("generated.png", "wb") as image:
    image.write(base64.b64decode(result["data"][0]["b64_json"]))
print(result["usage"])
Edit image · multipart
curl https://api.iteracompute.com/v1/images/edits \
  -H "Authorization: Bearer ITERACOMPUTE_API_KEY" \
  -F 'model=openai/gpt-image-2.6-flare' \
  -F 'prompt=Make the square red' -F 'n=1' -F 'quality=low' \
  -F 'size=1024x1024' -F 'image[]=@reference.png;type=image/png'

Pricing

USD per million tokens. — means unknown. Account and subscription limits still apply.

Text input$5.00
Image input$8.00
Image output$30.00
Version / Model ID
openai/gpt-image-2.6-flaregpt-image-2.6-flare
Context
—
Precision
Official precision
Price checked
Verification scope and sources
View verification scope and sources

2026-11-13 · Verified text-to-image generation and masked reference-image editing at 1024×1024 / low quality, with JPEG/WebP output, n=1 and n=4, actual token usage and billing. Streaming, tool calls and JSON text mode are unavailable. Higher quality/resolution combinations and cache usage were not exhaustively tested.

Complete token prices

USD per million tokens. Unknown prices are shown as —. Token ranges include cache reads and writes; ranges use (start, end].

Billing itemOur priceOfficial reference
Input$5$5
Cache read$1.25—
Output$0$0
Revision: 977758e5cc50

Usage limits

  • This route returns raster PNG, JPEG or WebP only. SVG, animated GIF, complexity and markup controls from other provider interfaces are not exposed here.
  • Streaming is not supported; response_format is b64_json. Use n from 1 to 4 and a prompt of 1 to 4,000 UTF-8 bytes.
  • Each dimension must be divisible by 16 and at most 3,840 pixels. Aspect ratio is at most 3:1 and total pixels must be 655,360–8,294,400.
  • Edits require one to four reference images; references plus the optional PNG mask total at most 8 MiB. Edit quality accepts low, medium and high only.
  • Cached-image usage and cache-retention controls have not been accepted for this route.

Use cases

Visual concept drafts

Reference-image revisions

Illustration and composition experiments

New arrivals

Explore the models selected for New Arrivals, with API pricing, supported capabilities and integration guides.

View new arrivals
GoogleNew

Gemini 4 Hydrogen

gemini/gemini-4-hydrogen

Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.

Launched on IteraCompute

Input
$1.50
Output
$7.50

USD / 1M tokens

OpenAINew

GPT-6.2 Astra

openai/gpt-6.2-astra

OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.

Launched on IteraCompute

Input
$8.00
Output
$40.00

USD / 1M tokens

OpenAINew

GPT-6.2 Sol

openai/gpt-6.2-sol

OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.

Launched on IteraCompute

Input
$2.00
Output
$10.00

USD / 1M tokens