Compare model

Image

ByteDance logoSeedream 5 Pro

seedream-5-pro

Best for: Poster-style images and reference-guided edits with up to 10 ordered references

Share

Catalog status

Enabled

Research checked

2026-11-11

Benchmark results

1 reported results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

1 of 1 results

AA-Image-T2I

Image · Third-party report

Test conditions and source

Listed as Seedream 5.0 Pro. Pairwise blind human-preference Elo, ±11 (95% interval 1091–1113), 12,137 votes; 20th overall when checked. Not a TokenRex run.

Tested model: seedream-5-pro

Artificial Analysis · Text-to-Image Arena · Checked 2026-11-11

1102Elo

Model specifications

Images per request

Exactly one

Documented capability

Reference images

1–10, order preserved

Documented capability

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image

Output

Image (JPEG)
Exact model ID
seedream-5-pro
Model type
Image
Images per request
Exactly one
Reference images
1–10, order preserved
Sizes
1K, 2K or WIDTHxHEIGHT
Streaming
Completed image only (image_generation.completed)

Exact token limits are not published in the reviewed sources, so no estimated limits are shown.

Versions and image configurations

One enabled version is currently listed for this model.

Seedream 5 ProSelected$0.0315 per image

Pricing and controls

ByteDance logoMade by ByteDance

Output image$0.045 per imageTokenRex price $0.0315
Each reference image$0.03 per imageTokenRex price $0.021

cost = $0.045 + $0.03 × reference images (text only $0.045, one reference $0.075, ten $0.345). Same price for 1K and 2K; no token, size or watermark fees.

Market list prices in USD before the TokenRex discount; your wallet is charged in its own currency using TokenRex's standard conversion. A hold is placed before the job starts, settled once when it finishes, and released if it fails. No cache discounts apply.

Controls TokenRex accepts

  • prompt — required.
  • image — one URL/data URL or an ordered list of 1–10; all are kept in order. Editing requires at least one.
  • size — 1K, 2K or WIDTHxHEIGHT (for example 1536x864). watermark — boolean.
  • Always one JPEG (n omitted or 1). Not supported: quality, masks, transparency, output format, GIF/SVG, seed, negative prompt.
  • POST /v1/images/edits accepts the same JSON or multipart (model, prompt, size, watermark, repeated image[] files).

Send controls inside input (preferred) or flat beside model — never both. Unknown fields are refused.

Create a Seedream 5 Pro image

curl https://tokenrex.ai/api/public/v1/images/generations \
  -H "Authorization: Bearer $TOKENREX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-5-pro",
  "input": {
    "prompt": "An editorial tea poster. Exact headline: TIFFIN TEA.",
    "size": "2K",
    "watermark": false
  },
  "stream": false
}'

Edit with ordered references

{
  "model": "seedream-5-pro",
  "input": {
    "prompt": "Keep the layout. Change the headline colour to teal.",
    "image": [
      "https://example.com/poster.jpg",
      "https://example.com/palette.png"
    ],
    "size": "2K",
    "watermark": false
  },
  "stream": false
}

Send to POST /v1/images/generations or /v1/images/edits. The image is returned in data[0].b64_json. With stream: true you receive one image_generation.completed event with the finished image.

Errors

400 invalid_request_errorA control is missing, out of range or not supported (unknown fields are refused, never ignored). Nothing is charged.
402 insufficient_balanceYour wallet cannot cover the hold. Nothing is sent to the model.
502 outcome_unknownThe connection broke while creating the job, so TokenRex cannot tell whether it started. It is never retried automatically; check your wallet history before sending again.

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

Prompt plus up to 10 ordered reference images on POST /v1/images/generations or /v1/images/edits (JSON or multipart).

Output through TokenRex

Available

Exactly one JPEG as base64. Functional tests: text-to-image and a one-reference edit both returned images.

Quality, masks, transparency, formats

Not exposed

Not supported by this model and refused if sent.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (3)
  • Functional test through TokenRex (2026-11-11): a 1K text-to-image request returned an 832×1248 JPEG poster with the requested headline, and a one-reference edit returned the edited JPEG. These are working checks, not quality benchmarks.
  • 1K and 2K set the output scale and are not exact squares; a custom WIDTHxHEIGHT size such as 1536x864 is accepted.
  • Quality, masks, transparency, output format, seed, negative prompts and multiple outputs are not supported and are refused.