Openai Gpt Image 2.6 Flare Text To Image API Documentation

Openai Gpt Image 2.6 Flare Text To Image API Documentation

Playground

GPT Image 2.6 Flare Text-to-Image generates high-quality images from natural-language prompts with a focus on fast generation and rapid creative iteration, making it suitable for everyday image creation, concept development, marketing visuals, and production workflows. Ready-to-use REST inference API.

Features

OpenAI GPT Image 2.6 Flare Text-to-Image turns natural-language prompts into high-quality images. Flare is the fast GPT Image 2.6 tier, returning images in seconds for everyday generation and quick iteration.

• Need to edit an existing image instead? Try OpenAI GPT Image 2.6 Flare Edit.
• Need extra fidelity on intricate detail? Try OpenAI GPT Image 2.6 Sunburst Text-to-Image.

Why Choose This?

• Strong prompt fidelity Generate images that closely follow detailed natural-language instructions, including scene layout, visual style, and composition.

• Accurate text rendering Create images with clearer, more usable in-image text for posters, ads, packaging, and interface mockups.

• Quality and complexity controls quality sets the rendering detail you pay for; complexity sets how much the model plans the layout before drawing, at no extra cost.

• Animated GIF and vector SVG output Set output_format to gif for a looping animation of 2 to 16 frames, or to svg for a scalable vector file — icons, logos, flat illustrations.

• Up to 4K output and flexible aspect ratios Square, portrait, landscape, and panoramic outputs at 1k, 2k, or 4k.

• Production-ready API Access the model through a ready-to-use REST inference API for fast integration into applications and workflows.

Parameters

How to Use

1. Write your prompt — describe the image in detail, including subject, style, lighting, composition, and any text you want to appear.
2. Pick quality and resolution (optional) — medium / 1k is the default; raise quality for more detail or resolution for larger output.
3. Lower complexity for simple requests (optional) — high is the default; low or medium returns a little faster on short, simple prompts.
4. Choose aspect ratio (optional) — 1:1 for square, 2:3 or 9:16 for portrait, 3:2 or 16:9 for landscape, up to 3:1 / 1:3 panoramas.
5. Submit — run the model and download your generated image.

Example Prompt

A cinematic product photo of an unbranded perfume bottle on a marble surface, soft golden-hour lighting, shallow depth of field, elegant reflections, premium editorial photography style

Pricing

Pricing varies by quality and resolution. complexity does not change the price.

• GIF: the image price × (1 + frame_count / 16) — for example $0.117 for 9 frames at medium 1k.
• SVG: the image price + $0.015.

Notes

• prompt is the only required field.
• GIF and SVG output are available on text-to-image only.
• Requests containing sexual content are rejected before generation and are not charged.

Related Models

• OpenAI GPT Image 2.6 Flare Edit — Edit one or more reference images using natural-language instructions.
• OpenAI GPT Image 2.6 Sunburst Text-to-Image — The Sunburst tier of the same model.
• OpenAI GPT Image 2.5 Flare Text-to-Image — The previous generation.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "quality": "medium",
  "complexity": "high",
  "output_format": "png",
  "frame_count": 9,
  "frame_duration_ms": 200
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-2.6-flare/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters