Seedream 5.0 Pro Image Generation: API, Pricing, Examples, and Integration Guide

Menu

• Agent Skill First
• Installation
• Agent Auto-Install
• Getting an API Key
• API Quick Start
• Full First-Run Flow
• API Reference
• Showcase
• Troubleshooting
• Compatibility
• Community
• License

Agent Skill First

Install the agent skill before running a live request. The skill guides setup, asks for an EvoLink key only when needed, validates the key through a non-generating endpoint, and then runs the first generation call only after the user confirms the prompt and cost boundary.

Installation

npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen

Fallback when the skills registry CLI is unavailable:

npx evolink-seedream-5-pro@latest -y --path ~/.claude/skills

Run directly from npm after publication:

npx evolink-seedream-5-pro "Create a serene lake at sunset in 16:9, quality 2K"

Agent Auto-Install

Install the Seedream 5.0 Pro Image Generation skill by running:

npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen

Then read the installed seedream-5-pro-image-gen/SKILL.md. If the skills registry CLI is unavailable, use fallback: npx evolink-seedream-5-pro@latest -y --path ~/.claude/skills.

Getting an API Key

Create or select an EvoLink key from the API key dashboard. If you are not signed in, that page handles sign-in/sign-up and returns you to key management.

API Quick Start

export EVOLINK_API_KEY="your_key_here"

curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header "Authorization: Bearer ${EVOLINK_API_KEY}" \
  --header "Content-Type: application/json" \
  --header "X-EvoLink-Source: skill" \
  --header "X-EvoLink-Skill: seedream-5-pro-image-gen" \
  --header "X-EvoLink-Package: evolink-seedream-5-pro" \
  --header "X-EvoLink-Campaign: seedream-5-pro-image-gen" \
  --header "X-EvoLink-Touchpoint: first-run" \
  --data '{
  "model": "doubao-seedream-5.0-pro",
  "prompt": "A serene lake reflecting the beautiful sunset",
  "size": "16:9",
  "quality": "2K",
  "n": 1,
  "prompt_priority": "standard",
  "model_params": {
    "output_format": "jpeg"
  }
}'

Example response:

{
  "id": "task_example",
  "status": "pending"
}

Full First-Run Flow

Seedream 5.0 Pro is open for live EvoLink API calls. This repository includes audited examples, install flow, request payloads, polling, callbacks, package hygiene, and a completed real create-and-poll smoke test. Run live generation only with an EvoLink key and an approved cost boundary.

1. Create a task with POST /v1/images/generations.
2. Store the returned task ID.
3. Poll GET /v1/tasks/{task_id} until the task is completed, or pass callback_url.
4. Save the final media URL from results or result_data before it expires.

See the complete examples:

• cURL complete flow
• Python complete flow
• JavaScript complete flow

API Reference

Seedream 5.0 Pro uses POST /v1/images/generations and returns an asynchronous image task. Use GET /v1/tasks/{task_id} to poll until completed or failed.

What Is Seedream 5.0 Pro Image Generation?

Seedream 5.0 Pro Image Generation is available here as a live EvoLink API integration and installable agent skill. Check the EvoLink model page and returned usage object for current pricing before high-volume use.

Supported Models / Workflows

| Model | ID | |---|---| | Seedream 5.0 Pro Image Generation | doubao-seedream-5.0-pro |

Choose the Right Model or Workflow

| Workflow | Use when | |---|---| | API | You need direct developer integration. | | Skill | You want an agent to install and run the workflow. |

Endpoints

| Purpose | Method | Path | |---|---|---| | Create task | POST | /v1/images/generations | | Query task | GET | /v1/tasks/{task_id} |

Request Parameters

| Parameter | Type | Required | Notes | |---|---:|---:|---| | model | string | yes | Must be doubao-seedream-5.0-pro. | | prompt | string | yes | Text prompt or edit instruction, up to 2000 tokens. | | n | integer | no | Pro supports 1 only. | | size | string | no | auto, ratio values such as 1:1 or 16:9, or pixel sizes within the documented range. | | quality | string | no | 1K or 2K; default is 1K for Pro. | | prompt_priority | string | no | standard. | | image_urls | string array | no | Up to 10 direct-viewable reference images for image-to-image or editing. | | model_params.output_format | string | no | Output image format when supported by the backend. | | callback_url | string | no | HTTPS callback URL; internal IP targets are blocked. |

Response Schema

Read Response Schema.

Error Handling

Read Errors.

Callback / Webhook

Read Callbacks.

Pricing

EvoLink returns usage details in the task creation response. Check the returned usage object and the EvoLink dashboard for the current account-specific charge before high-volume use.

Read Pricing.

Examples by Language

• cURL
• Python
• JavaScript

Production Notes

• All requests require Bearer token authentication.
• Generation APIs are asynchronous.
• Store task IDs and final asset URLs.
• Save generated assets promptly because media URLs may expire.
• Prefer callbacks for production systems that should avoid long polling.

Use Cases

• First-run API validation
• Agent skill installation
• Published package and public README review

FAQ

• How is billing calculated? The create-task response includes a usage object with the billing rule and reserved credits. Treat the live API response and EvoLink dashboard as the source of truth.
• How long do result URLs last? Generated media links may expire. Save outputs promptly after completion.
• Can I use callbacks instead of polling? Yes. Pass callback_url when the API supports webhook delivery.

Documentation

• API Reference
• Task Lifecycle
• Response Schema
• Errors
• Callbacks
• Pricing

Related Repositories

• Guide / Prompt surface: https://github.com/Evolink-AI/awesome-seedream-5.0-pro-prompts
• API / Skill surface: seedream-5-pro-image-generate-api-skill

Agent Skill

This repository also contains an installable agent skill for seedream-5-pro-image-gen.

• Skill definition
• Agent install guide
• Local CLI installer

Run the local installer after review:

npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen

Fallback when the skills registry CLI is unavailable:

npx evolink-seedream-5-pro@latest -y --path ~/.claude/skills

AI Agent? Skip the README, go straight to llms-install.md for step-by-step installation instructions designed for agents.

Installation

Quick Install

npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen

If the skills registry CLI is unavailable, use fallback:

npx evolink-seedream-5-pro@latest -y --path ~/.claude/skills

Run Directly

npx evolink-seedream-5-pro "Create a short Seedream 5.0 Pro Image Generation demo"

Agent Auto-Install

Install the Seedream 5.0 Pro Image Generation skill by running:

npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen

Then read the installed seedream-5-pro-image-gen/SKILL.md and run a dry run before calling the real API. If the `skills` registry CLI is unavailable, use fallback: `npx evolink-seedream-5-pro@latest -y --path ~/.claude/skills`.

Manual Install

git clone https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill.git
cd seedream-5-pro-image-generate-api-skill
npm install
node bin/cli.js -y --path ~/.claude/skills

🖼️ Showcase

| Example | Result | |---|---| | First successful API call | Polls until completed and prints the final URL / text / file. | | Agent skill install | Installs SKILL.md, _meta.json, scripts/, and references/. | | Dry run | Prints the request payload without spending API credits. |

Troubleshooting

| Issue | Fix | |---|---| | EVOLINK_API_KEY is missing | Export EVOLINK_API_KEY before running the script. | | Skill installed but agent cannot see it | Re-run with the correct --path for Claude Code, Codex, OpenClaw, or Hermes. | | jq or curl is missing | Install the missing binary, then rerun npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen, or fallback to npx evolink-seedream-5-pro@latest -y --path <skills-dir>. | | API returns 401 or 403 | Verify the EvoLink key and account access. | | API returns 429 or 5xx | Retry within the approved test budget and record the failure output. | | Polling times out | Keep the task id, inspect the dashboard, and do not resubmit blindly. |

Compatibility

| Agent | Install command | |---|---| | Claude Code | npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen | | Codex | npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen | | OpenClaw | npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen | | Hermes | npx skills add https://github.com/Evolink-AI/seedream-5-pro-image-generate-api-skill/tree/main/skills/seedream-5-pro-image-gen |

Community

• Contributing
• Security
• Code of Conduct
• API bug report
• Docs fix report

License

MIT