# Iris-3B vs Seedream on BytePlus ModelArk

> Seedream on BytePlus ModelArk scores 53.8 (D) to Iris-3B's 50.9 (D) for image generation. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark
- Markdown: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.md (~2,800 tokens)
- Slim: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-15

Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Iris-3B's 50.9 (D), and leads in 5 of 7 scored categories. Iris-3B leads on payments & pricing. Both do image generation.

- Iris-3B: grade D, 50.9/100, rank #826 of 1094. Markdown https://www.anchorterminal.com/tools/iris-3b.md · JSON https://www.anchorterminal.com/api/v1/tools/iris-3b.json
- Seedream on BytePlus ModelArk: grade D, 53.8/100, rank #750 of 1094. Markdown https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark.md · JSON https://www.anchorterminal.com/api/v1/tools/seedream-on-byteplus-modelark.json
- Best image generation for AI agents: https://www.anchorterminal.com/best/image-generation/index.md
- All 91 image comparisons: https://www.anchorterminal.com/compare/image-generation/index.md

## Which one, for what

### Iris-3B (D)

Good for: An agent on a machine with a CUDA GPU that needs Apache-2.0 image generation, relative depth or 4x restoration without a vendor account.

Ahead on:
- Payments & pricing, 60 against 20

Also in its favour:
- No key needed to call it
- Free to start without a card
- Open source
- No incidents deducted, where Seedream on BytePlus ModelArk loses 3 points for them

Watch for: No package on PyPI, no version tags, no changelog and no CI workflow. Install is a git clone and `pip install -e .`

### Seedream on BytePlus ModelArk (D)

Good for: Agents that need ByteDance's Seedream models first-hand, multi-reference edits, 4K output or layered PNG output at a published per-image price, for users outside the United States.

Ahead on:
- Schema & documentation, 62 against 47
- Agent ergonomics, 72 against 54
- Security & auth, 70 against 44
- Transparency & trust, 60 against 47

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: No status page, incident history or ModelArk SLA was found in the pages read


## Score by category

| Category | Weight | Iris-3B | Seedream on BytePlus ModelArk | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 45 | 43 | Iris-3B +2 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 47 | 62 | Seedream on BytePlus ModelArk +15 |
| Agent ergonomics | 13% (16.2 this run) | 54 | 72 | Seedream on BytePlus ModelArk +18 |
| Security & auth | 14% (17.5 this run) | 44 | 70 | Seedream on BytePlus ModelArk +26 |
| Payments & pricing | 10% (12.5 this run) | 60 | 20 | Iris-3B +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 70 | 73 | Seedream on BytePlus ModelArk +3 |
| Transparency & trust | 7% (8.8 this run) | 47 | 60 | Seedream on BytePlus ModelArk +13 |
| Negative events | ≤15 | 0 | -3 | |
| **Total** | | **50.9 · D** | **53.8 · D** | |

## Facts side by side

| Fact | Iris-3B | Seedream on BytePlus ModelArk |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Speridlabs | BytePlus Pte. Ltd. (ByteDance) |
| Hosted endpoint | no (local only) | `https://ark.ap-southeast.bytepluses.com/api/v3` |
| Transports |  | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (code and weights) | Proprietary service under the BytePlus Customer Agreement and Service Specific Terms. The Go and Python SDK repositories are Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-12 | 2026-09-17 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | 175 stars | none |

## Verdicts

**Iris-3B.** Code and weights are Apache-2.0, and one Python package runs text-to-image, a 4-step Turbo, depth and 4x restoration from a documented CLI. It is ten days old, with no PyPI package, version tags, changelog or CI, needs an NVIDIA GPU and about 12 GB of weights, and has no server or API of its own.

**Seedream on BytePlus ModelArk.** Per-image prices from $0.018 are public, and API keys can be limited to named models and an IP allowlist. No status page, SLA or OpenAPI file was found, onboarding needs a browser sign-up, and BytePlus says its model services are not available in the United States.

## Before you call either

### Iris-3B

1. Check for an NVIDIA GPU with CUDA and Python 3.11 or newer before downloading. The base weights are about 12 GB, and Qwen3-VL-4B downloads on the first run
2. Exclude `depth/*`, `upscaler/*` and `turbo/*` in `hf download` unless those models are needed. Each of the first two adds about 12 GB
3. Don't pass `--steps`, `--cfg-scale`, `--negative-prompt`, `--order` or `--shift` with a Turbo checkpoint. The script exits with an error
4. Pass `--seed` to reproduce an image, and set `--outdir`, since files are named after the prompt and a repeat run overwrites them
5. Load only exported directories (`model.safetensors` and `config.yaml`). A training `.pth` is read with `torch.load(weights_only=False)`, so never load one from an untrusted source

### Seedream on BytePlus ModelArk

1. POST to `https://ark.ap-southeast.bytepluses.com/api/v3/images/generations` with `Authorization: Bearer $ARK_API_KEY`. Keys and model activation are per region
2. Set `watermark` to false if the image must not carry the AI-generated mark. The default is true
3. Download `data[].url` within 24 hours, or ask for `response_format` `b64_json`
4. Check each `data[].error` in a sequential batch. One moderated image does not fail the others, and only `usage.generated_images` is billed
5. Stay under 500 images a minute per model and back off with jitter on 429. Layer decomposition reserves 17 against that limit per request

## Questions

### Which is better for AI agents, Iris-3B or Seedream on BytePlus ModelArk?

Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Iris-3B's 50.9 (D), and leads in 5 of 7 scored categories. Iris-3B leads on payments & pricing.

### Do Iris-3B and Seedream on BytePlus ModelArk need an API key?

Iris-3B needs no key. Seedream on BytePlus ModelArk needs an API key.

### Can an agent call Iris-3B and Seedream on BytePlus ModelArk without installing anything?

No hosted endpoint is listed for Iris-3B. Seedream on BytePlus ModelArk has a hosted endpoint at https://ark.ap-southeast.bytepluses.com/api/v3.

### Are Iris-3B and Seedream on BytePlus ModelArk open source?

Iris-3B is open source (Apache-2.0 (code and weights)). No open-source release is listed for Seedream on BytePlus ModelArk.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.json, and with the fewest tokens: https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "iris-3b", "b": "seedream-on-byteplus-modelark"}`. From a terminal: `anchor compare iris-3b seedream-on-byteplus-modelark`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/iris-3b.json and https://www.anchorterminal.com/api/v1/tools/seedream-on-byteplus-modelark.json

## Other comparisons with Iris-3B or Seedream on BytePlus ModelArk

- [Adobe Firefly API vs Iris-3B](https://www.anchorterminal.com/compare/adobe-firefly-vs-iris-3b.md)
- [Adobe Firefly API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/adobe-firefly-vs-seedream-on-byteplus-modelark.md)
- [Black Forest Labs FLUX API vs Iris-3B](https://www.anchorterminal.com/compare/black-forest-labs-vs-iris-3b.md)
- [Black Forest Labs FLUX API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/black-forest-labs-vs-seedream-on-byteplus-modelark.md)
- [Bria API vs Iris-3B](https://www.anchorterminal.com/compare/bria-vs-iris-3b.md)
- [Bria API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/bria-vs-seedream-on-byteplus-modelark.md)
- [fal image models vs Iris-3B](https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.md)
- [fal image models vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark.md)
- [Google Imagen vs Iris-3B](https://www.anchorterminal.com/compare/google-imagen-vs-iris-3b.md)
- [Google Imagen vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.md)
- [Ideogram API vs Iris-3B](https://www.anchorterminal.com/compare/ideogram-vs-iris-3b.md)
- [Ideogram API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/ideogram-vs-seedream-on-byteplus-modelark.md)
- [Iris-3B vs Leonardo.Ai API](https://www.anchorterminal.com/compare/iris-3b-vs-leonardo-ai.md)
- [Iris-3B vs OpenAI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-openai-image-api.md)
- [Iris-3B vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.md)
- [Iris-3B vs Recraft API](https://www.anchorterminal.com/compare/iris-3b-vs-recraft.md)
- [Iris-3B vs Replicate image models](https://www.anchorterminal.com/compare/iris-3b-vs-replicate-image.md)
- [Iris-3B vs Stability AI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-stability-ai-image.md)
- [Leonardo.Ai API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/leonardo-ai-vs-seedream-on-byteplus-modelark.md)
- [OpenAI Image API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/openai-image-api-vs-seedream-on-byteplus-modelark.md)
- [Qwen-Image 2.1 (Model Studio) vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/qwen-image-2-1-vs-seedream-on-byteplus-modelark.md)
- [Recraft API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/recraft-vs-seedream-on-byteplus-modelark.md)
- [Replicate image models vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/replicate-image-vs-seedream-on-byteplus-modelark.md)
- [Seedream on BytePlus ModelArk vs Stability AI Image API](https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-stability-ai-image.md)