{ "data": { "a": { "slug": "iris-3b", "name": "Iris-3B", "vendor": "Speridlabs", "vendorUrl": "https://speridlabs.com", "kind": "model", "category": "image-generation", "summary": "Iris-3B is an Apache-2.0 open-weight text-to-image model from Speridlabs that generates pixels directly, with no VAE. The release adds a 4-step Turbo version and fine-tunes for monocular depth and 4x image restoration.", "url": "https://www.anchorterminal.com/tools/iris-3b", "markdownUrl": "https://www.anchorterminal.com/tools/iris-3b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/iris-3b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/iris-3b.json", "repo": "https://github.com/speridlabs/iris-3b", "license": "Apache-2.0 (code and weights)", "transports": [], "packages": [], "auth": "none", "authNotes": "No account or key. Weights download from a public, ungated Hugging Face repository, and the frozen Qwen3-VL-4B-Instruct text encoder downloads from its publisher on the first run. The software opens no network service.", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with nothing to buy. Speridlabs has no hosted API or paid plan. The owner pays for an NVIDIA GPU. The demo Spaces run on Hugging Face ZeroGPU.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the model card or the project page (checked 2026-10-15). There is no paid tier or hosted endpoint.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 175, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-15" }, "docsUrl": "https://huggingface.co/speridlabs/iris-3b", "capabilities": [ "image.generate", "image.upscale" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "no-card", "apache-2.0", "python", "gpu", "new" ], "lastRelease": "2026-10-12", "graded": true, "anchor": { "graded": true, "score": 50.9, "grade": "D", "agentReady": false, "rank": 826, "ranked": true, "rankOf": 1094, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 54, "maintenance": 70, "payments": 60, "reliability": 45, "schema": 47, "security": 44, "transparency": 47 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-15" }, "negative": 0, "verdict": "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.", "bestFor": "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.", "strengths": [ "Code, training recipe and all four checkpoints are under Apache-2.0, with a NOTICE file and a table of third-party licences", "One CLI, `scripts/sample.py`, with typed flags and documented defaults (1024x1024, 100 steps, CFG 3), plus Python classes for depth and restoration", "Turbo samples a 1024x1024 image in 4 steps, which the vendor times at about 0.7 s on one H100 at batch 4", "Released weights are safetensors, and a published benchmark table covers GenEval, DPG-Bench, LongText-Bench and OneIG-Bench", "Three dated weight releases in eight days (5, 8 and 12 October 2026), and two outside pull requests merged within two days" ], "weaknesses": [ "No package on PyPI, no version tags, no changelog and no CI workflow. Install is a git clone and `pip install -e .`", "Needs an NVIDIA GPU with CUDA. All three models together take about 45 GB of GPU memory, or about 20 GB peak with offloading", "No HTTP server, OpenAPI or MCP interface. The only hosted route is the Gradio demo Spaces on Hugging Face ZeroGPU", "No safety filter in the code, no SECURITY.md or security.txt, and no privacy or terms pages on speridlabs.com", "Training defaults to reporting runs to Weights \u0026 Biases (`report_to: wandb`), which the README doesn't mention" ], "agentNotes": [ "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", "Exclude `depth/*`, `upscaler/*` and `turbo/*` in `hf download` unless those models are needed. Each of the first two adds about 12 GB", "Don't pass `--steps`, `--cfg-scale`, `--negative-prompt`, `--order` or `--shift` with a Turbo checkpoint. The script exits with an error", "Pass `--seed` to reproduce an image, and set `--outdir`, since files are named after the prompt and a repeat run overwrites them", "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" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.9 } ], "editorialScores": { "ergonomics": 54, "maintenance": 70, "payments": 60, "reliability": 45, "schema": 47, "security": 44, "transparency": 50 }, "provenanceScore": 44 }, "connect": { "install": "git clone https://github.com/speridlabs/iris-3b.git \u0026\u0026 cd iris-3b \u0026\u0026 pip install -e .\nhf download speridlabs/iris-3b --local-dir iris-3b --exclude \"depth/*\" \"upscaler/*\" \"turbo/*\"\npython scripts/sample.py --checkpoint iris-3b --prompt \"a red fox sleeping in fresh snow, golden hour\"" }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/iris-3b" }, "area": "content", "provenance": { "legalEntity": "Speridlabs", "domain": "speridlabs.com", "domainRegistered": "2025-02-25", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-15", "notes": [ "The NOTICE file reads Copyright 2026 Speridlabs. The site's schema.org data names the organisation Sperid Labs, founded 2024, with contact@speridlabs.com. No registered company name or address was found on speridlabs.com.", "RDAP at Verisign gives a registration date of 2025-02-25 for speridlabs.com.", "speridlabs.com has no terms or privacy page. /privacy, /terms, /legal and /privacy-policy returned 404 on 15 October 2026, and the sitemap lists none. The Apache-2.0 licence stands in for terms for the code and weights.", "speridlabs.com/.well-known/security.txt returned 404 on 15 October 2026. The repository has no SECURITY.md.", "No changelog, release notes or tags. Dated commits on GitHub and on the Hugging Face model repository are the only record of changes.", "Software the owner runs, so there is no vendor endpoint or status page. The demo Spaces run on Hugging Face infrastructure." ], "score": 44 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/iris-3b.json" }, "answer": "Qwen-Image 2.1 (Model Studio) scores 64.6 (B) on agent readiness against Iris-3B's 50.9 (D), and leads in 6 of 7 scored categories. Iris-3B leads on payments \u0026 pricing.", "b": { "slug": "qwen-image-2-1", "name": "Qwen-Image 2.1 (Model Studio)", "vendor": "Alibaba Cloud", "vendorUrl": "https://www.alibabacloud.com", "kind": "model", "category": "image-generation", "summary": "Qwen-Image 2.1 is Alibaba's image model for text-to-image and image editing with up to 10 reference images and transparent output, callable as qwen-image-2.1-pro through Alibaba Cloud Model Studio's DashScope and OpenAI-compatible APIs.", "url": "https://www.anchorterminal.com/tools/qwen-image-2-1", "markdownUrl": "https://www.anchorterminal.com/tools/qwen-image-2-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/qwen-image-2-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/qwen-image-2-1.json", "repo": "https://huggingface.co/Qwen/Qwen-Image-2.1", "license": "Closed API under Alibaba Cloud's product terms. Qwen-Image-2.1 weights are on Hugging Face under the Qwen Research License, for non-commercial use only.", "transports": [ "http" ], "remoteUrl": "https://dashscope-intl.aliyuncs.com/api/v1", "packages": [ { "registry": "pypi", "name": "dashscope" } ], "auth": "api-key", "authNotes": "Bearer Model Studio API key, created per region in the console by an account or RAM user with API-Key permission. Keys can be limited to chosen models and an IP allow-list of up to 20 entries, and reset. The model, endpoint and key must be in the same region. Async calls add `X-DashScope-Async: enable`.", "pricing": "usage", "pricingNotes": "qwen-image-2.1-pro is $0.04 an image in Singapore (International) and $0.035333 in Beijing, Virginia, Frankfurt, Tokyo and Hong Kong, list prices without promotions (model page, checked 10 October 2026). New Singapore users get a 90-day free quota, but whether it covers this model was not confirmed.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Model Studio llms.txt, the Qwen image API reference or the model page, checked 10 October 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-10" }, "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/qwen-image-generation-and-editing-api-reference", "llmsTxt": "https://docs.modelstudio.console.alibabacloud.com/llms.txt", "capabilities": [ "image.generate", "image.edit", "image.reference" ], "tags": [ "official", "hosted", "usage-priced", "open-weights", "llms-txt", "openai-compatible", "async-jobs", "python", "sla", "soc2" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 64.6, "grade": "B", "agentReady": false, "rank": 374, "ranked": true, "rankOf": 1094, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 77, "payments": 20, "reliability": 70, "schema": 66, "security": 75, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": 0, "verdict": "qwen-image-2.1-pro generates and edits images with up to 10 references and transparent output, at $0.04 an image in Singapore, through an OpenAI-compatible endpoint or DashScope. Model Studio publishes a 99.9 per cent SLA and a no-training statement. The model allows 20 requests a minute, has no OpenAPI file, and its open weights are for non-commercial use only.", "bestFor": "Low-cost image generation and multi-reference editing with transparent PNG output, for agents already on Model Studio or using the OpenAI Images protocol.", "strengths": [ "Text-to-image and editing in one model, with 1 to 10 reference images and transparent output decided from the prompt", "$0.04 an image in Singapore and $0.035333 in five other regions, published without a login", "OpenAI-compatible /images/generations endpoint beside DashScope sync and async calls", "Keys can be limited to chosen models and an IP allow-list, and the audit log records each call", "The Model Studio privacy notice says customer data is never used for training" ], "weaknesses": [ "20 requests a minute in every region", "No OpenAPI or other machine-readable contract for the image endpoints", "Result URLs expire after 24 hours, and the OpenAI-compatible mode ignores `b64_json`", "`negative_prompt` works only on the qwen-image-3.0 series, not on qwen-image-2.1-pro", "Qwen-Image-2.1 weights are under a non-commercial research licence, so self-hosting is not an option for commercial work" ], "agentNotes": [ "Use the same region for the key, the model and the endpoint. Cross-region calls fail", "Download each result within 24 hours. The URL expires and the image is purged", "With the OpenAI SDK, pass `image`, `seed`, `prompt_extend` and `watermark` through `extra_body`, and write size as `1024x1024`, not `1024*1024`", "Set a client timeout of up to 600 seconds for several outputs, or use the async DashScope call and poll the task id", "Do not send `prompt_extend_mode: agent` with input images. It returns 400" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.6 } ], "editorialScores": { "ergonomics": 73, "maintenance": 77, "payments": 20, "reliability": 70, "schema": 66, "security": 75, "transparency": 60 }, "provenanceScore": 69 }, "connect": { "install": "pip install dashscope", "http": "curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/images/generations' \\\n --header 'Content-Type: application/json' \\\n --header \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n --data '{\"model\":\"qwen-image-2.1-pro\",\"prompt\":\"A paper boat sticker on a transparent background\",\"n\":1}'" }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/qwen-image-2-1" }, "sameCompany": [ "alibaba-wan" ], "area": "content", "unitPrices": [ { "item": "qwen-image-2.1-pro, Singapore", "unit": "image", "usd": 0.04, "note": "International scope, list price" }, { "item": "qwen-image-2.1-pro, Beijing, Virginia, Frankfurt, Tokyo, Hong Kong", "unit": "image", "usd": 0.035333, "note": "list price" } ], "provenance": { "legalEntity": "Alibaba Cloud (Singapore) Private Limited", "domain": "alibabacloud.com", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0", "privacy": "https://www.alibabacloud.com/help/en/model-studio/privacy-notice", "statusPage": "https://status.alibabacloud.com", "changelog": "https://www.alibabacloud.com/help/en/model-studio/newly-released-models", "securityTxt": "none", "checked": "2026-10-10", "notes": [ "The endpoints are on aliyuncs.com, Alibaba Cloud's service domain (dashscope-intl.aliyuncs.com and per-workspace maas.aliyuncs.com hosts), as in the alibaba-wan listing.", "www.alibabacloud.com/.well-known/security.txt returns an HTML not-found page.", "status.alibabacloud.com renders in the browser only and its incident history was not read.", "The legal entity and terms URL follow the alibaba-wan listing and were not re-read on 10 October." ], "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/qwen-image-2-1.json", "live": { "slug": "qwen-image-2-1", "probe": { "target": "https://dashscope-intl.aliyuncs.com/api/v1", "method": "get", "lastAt": "2026-10-15T11:30:07.424831122Z", "lastOk": true, "lastStatus": 404, "lastMs": 238, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 230, "p95ms24h": 250, "samples24h": 254, "samples30d": 1115, "days": [ { "date": "2026-10-10", "probes": 1, "ok": 1 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 123, "ok": 123 } ] }, "versions": [ { "registry": "pypi", "name": "dashscope", "version": "1.27.7", "released": "2026-09-24", "seenAt": "2026-10-15T00:16:49.649593915Z" } ], "pypiWeekly": 789059, "securityTxt": { "url": "https://alibabacloud.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-14T15:47:19.1390926Z" }, "llmsTxt": { "url": "https://docs.modelstudio.console.alibabacloud.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-14T14:14:55.204288408Z" }, "domain": { "domain": "alibabacloud.com", "registered": "2009-09-08", "source": "https://rdap.verisign.com/com/v1/domain/alibabacloud.com", "checkedAt": "2026-10-11T13:18:09.085515064Z" }, "pages": [ { "url": "https://www.alibabacloud.com/help/en/model-studio/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-10-14T21:10:12.744965678Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "034608ed3843" } ], "updatedAt": "2026-10-15T11:30:07.424831122Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Speridlabs", "b": "Alibaba Cloud", "name": "Vendor" }, { "a": "no (local only)", "b": "https://dashscope-intl.aliyuncs.com/api/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (code and weights)", "b": "Closed API under Alibaba Cloud's product terms. Qwen-Image-2.1 weights are on Hugging Face under the Qwen Research License, for non-commercial use only.", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-12", "b": "2026-10-02", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "175 stars", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Qwen-Image 2.1 (Model Studio) scores 64.6 (B) on agent readiness against Iris-3B's 50.9 (D), and leads in 6 of 7 scored categories. Iris-3B leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Iris-3B or Qwen-Image 2.1 (Model Studio)?" }, { "answer": "Iris-3B needs no key. Qwen-Image 2.1 (Model Studio) needs an API key.", "question": "Do Iris-3B and Qwen-Image 2.1 (Model Studio) need an API key?" }, { "answer": "No hosted endpoint is listed for Iris-3B. Qwen-Image 2.1 (Model Studio) has a hosted endpoint at https://dashscope-intl.aliyuncs.com/api/v1.", "question": "Can an agent call Iris-3B and Qwen-Image 2.1 (Model Studio) without installing anything?" }, { "answer": "Iris-3B is open source (Apache-2.0 (code and weights)). No open-source release is listed for Qwen-Image 2.1 (Model Studio).", "question": "Are Iris-3B and Qwen-Image 2.1 (Model Studio) open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 20" ], "also": [ "No key needed to call it", "Free to start without a card", "Open source" ], "goodFor": "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.", "slug": "iris-3b", "watchFor": "No package on PyPI, no version tags, no changelog and no CI workflow. Install is a git clone and `pip install -e .`" }, { "aheadOn": [ "Reliability, 70 against 45", "Schema \u0026 documentation, 66 against 47", "Agent ergonomics, 73 against 54", "Security \u0026 auth, 75 against 44", "Maintenance \u0026 community, 77 against 70", "Transparency \u0026 trust, 65 against 47" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Low-cost image generation and multi-reference editing with transparent PNG output, for agents already on Model Studio or using the OpenAI Images protocol.", "slug": "qwen-image-2-1", "watchFor": "20 requests a minute in every region" } ], "job": { "capability": "image.generate", "name": "Image generation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-iris-3b.json", "title": "Adobe Firefly API vs Iris-3B", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-qwen-image-2-1.json", "title": "Adobe Firefly API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-iris-3b.json", "title": "Black Forest Labs FLUX API vs Iris-3B", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-qwen-image-2-1.json", "title": "Black Forest Labs FLUX API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-iris-3b.json", "title": "Bria API vs Iris-3B", "url": "https://www.anchorterminal.com/compare/bria-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-qwen-image-2-1.json", "title": "Bria API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/bria-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.json", "title": "fal image models vs Iris-3B", "url": "https://www.anchorterminal.com/compare/fal-image-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1.json", "title": "fal image models vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-iris-3b.json", "title": "Google Imagen vs Iris-3B", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-qwen-image-2-1.json", "title": "Google Imagen vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/ideogram-vs-iris-3b.json", "title": "Ideogram API vs Iris-3B", "url": "https://www.anchorterminal.com/compare/ideogram-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/ideogram-vs-qwen-image-2-1.json", "title": "Ideogram API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/ideogram-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-leonardo-ai.json", "title": "Iris-3B vs Leonardo.Ai API", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-leonardo-ai" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-openai-image-api.json", "title": "Iris-3B vs OpenAI Image API", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-openai-image-api" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-recraft.json", "title": "Iris-3B vs Recraft API", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-recraft" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-replicate-image.json", "title": "Iris-3B vs Replicate image models", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-replicate-image" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.json", "title": "Iris-3B vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-stability-ai-image.json", "title": "Iris-3B vs Stability AI Image API", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-stability-ai-image" }, { "json": "https://www.anchorterminal.com/compare/leonardo-ai-vs-qwen-image-2-1.json", "title": "Leonardo.Ai API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/leonardo-ai-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/openai-image-api-vs-qwen-image-2-1.json", "title": "OpenAI Image API vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/openai-image-api-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-recraft.json", "title": "Qwen-Image 2.1 (Model Studio) vs Recraft API", "url": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-recraft" }, { "json": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-replicate-image.json", "title": "Qwen-Image 2.1 (Model Studio) vs Replicate image models", "url": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-replicate-image" }, { "json": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-seedream-on-byteplus-modelark.json", "title": "Qwen-Image 2.1 (Model Studio) vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-stability-ai-image.json", "title": "Qwen-Image 2.1 (Model Studio) vs Stability AI Image API", "url": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-stability-ai-image" } ], "scores": [ { "by": 25, "edge": "qwen-image-2-1", "iris-3b": 45, "key": "reliability", "name": "Reliability", "qwen-image-2-1": 70, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 19, "edge": "qwen-image-2-1", "iris-3b": 47, "key": "schema", "name": "Schema \u0026 documentation", "qwen-image-2-1": 66, "weight": 13 }, { "by": 19, "edge": "qwen-image-2-1", "iris-3b": 54, "key": "ergonomics", "name": "Agent ergonomics", "qwen-image-2-1": 73, "weight": 13 }, { "by": 31, "edge": "qwen-image-2-1", "iris-3b": 44, "key": "security", "name": "Security \u0026 auth", "qwen-image-2-1": 75, "weight": 14 }, { "by": 40, "edge": "iris-3b", "iris-3b": 60, "key": "payments", "name": "Payments \u0026 pricing", "qwen-image-2-1": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "qwen-image-2-1", "iris-3b": 70, "key": "maintenance", "name": "Maintenance \u0026 community", "qwen-image-2-1": 77, "weight": 7 }, { "by": 18, "edge": "qwen-image-2-1", "iris-3b": 47, "key": "transparency", "name": "Transparency \u0026 trust", "qwen-image-2-1": 65, "weight": 7 } ], "summary": "Qwen-Image 2.1 (Model Studio) scores 64.6 (B) on agent readiness against Iris-3B's 50.9 (D), and leads in 6 of 7 scored categories. Iris-3B leads on payments \u0026 pricing. Both do image generation.", "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.", "qwen-image-2-1": "qwen-image-2.1-pro generates and edits images with up to 10 references and transparent output, at $0.04 an image in Singapore, through an OpenAI-compatible endpoint or DashScope. Model Studio publishes a 99.9 per cent SLA and a no-training statement. The model allows 20 requests a minute, has no OpenAPI file, and its open weights are for non-commercial use only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1", "json": "https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.md", "slim": "https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.min.md" }, "markdown": "Qwen-Image 2.1 (Model Studio) scores 64.6 (B) on agent readiness against Iris-3B's 50.9 (D), and leads in 6 of 7 scored categories. Iris-3B leads on payments \u0026 pricing. Both do image generation.\n\n- 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\n- Qwen-Image 2.1 (Model Studio): grade B, 64.6/100, rank #374 of 1094. Markdown https://www.anchorterminal.com/tools/qwen-image-2-1.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen-image-2-1.json\n- Best image generation for AI agents: https://www.anchorterminal.com/best/image-generation/index.md\n- All 91 image comparisons: https://www.anchorterminal.com/compare/image-generation/index.md\n\n## Which one, for what\n\n### Iris-3B (D)\n\nGood 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.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 20\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\n\nWatch for: No package on PyPI, no version tags, no changelog and no CI workflow. Install is a git clone and `pip install -e .`\n\n### Qwen-Image 2.1 (Model Studio) (B)\n\nGood for: Low-cost image generation and multi-reference editing with transparent PNG output, for agents already on Model Studio or using the OpenAI Images protocol.\n\nAhead on:\n- Reliability, 70 against 45\n- Schema \u0026 documentation, 66 against 47\n- Agent ergonomics, 73 against 54\n- Security \u0026 auth, 75 against 44\n- Maintenance \u0026 community, 77 against 70\n- Transparency \u0026 trust, 65 against 47\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: 20 requests a minute in every region\n\n\n## Score by category\n\n| Category | Weight | Iris-3B | Qwen-Image 2.1 (Model Studio) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 45 | 70 | Qwen-Image 2.1 (Model Studio) +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 47 | 66 | Qwen-Image 2.1 (Model Studio) +19 |\n| Agent ergonomics | 13% (16.2 this run) | 54 | 73 | Qwen-Image 2.1 (Model Studio) +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 75 | Qwen-Image 2.1 (Model Studio) +31 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Iris-3B +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 70 | 77 | Qwen-Image 2.1 (Model Studio) +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 47 | 65 | Qwen-Image 2.1 (Model Studio) +18 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **50.9 · D** | **64.6 · B** | |\n\n## Facts side by side\n\n| Fact | Iris-3B | Qwen-Image 2.1 (Model Studio) |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Speridlabs | Alibaba Cloud |\n| Hosted endpoint | no (local only) | `https://dashscope-intl.aliyuncs.com/api/v1` |\n| Transports | | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 (code and weights) | Closed API under Alibaba Cloud's product terms. Qwen-Image-2.1 weights are on Hugging Face under the Qwen Research License, for non-commercial use only. |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-12 | 2026-10-02 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | 175 stars | none |\n\n## Verdicts\n\n**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.\n\n**Qwen-Image 2.1 (Model Studio).** qwen-image-2.1-pro generates and edits images with up to 10 references and transparent output, at $0.04 an image in Singapore, through an OpenAI-compatible endpoint or DashScope. Model Studio publishes a 99.9 per cent SLA and a no-training statement. The model allows 20 requests a minute, has no OpenAPI file, and its open weights are for non-commercial use only.\n\n## Before you call either\n\n### Iris-3B\n\n1. 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\n2. Exclude `depth/*`, `upscaler/*` and `turbo/*` in `hf download` unless those models are needed. Each of the first two adds about 12 GB\n3. Don't pass `--steps`, `--cfg-scale`, `--negative-prompt`, `--order` or `--shift` with a Turbo checkpoint. The script exits with an error\n4. Pass `--seed` to reproduce an image, and set `--outdir`, since files are named after the prompt and a repeat run overwrites them\n5. 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\n\n### Qwen-Image 2.1 (Model Studio)\n\n1. Use the same region for the key, the model and the endpoint. Cross-region calls fail\n2. Download each result within 24 hours. The URL expires and the image is purged\n3. With the OpenAI SDK, pass `image`, `seed`, `prompt_extend` and `watermark` through `extra_body`, and write size as `1024x1024`, not `1024*1024`\n4. Set a client timeout of up to 600 seconds for several outputs, or use the async DashScope call and poll the task id\n5. Do not send `prompt_extend_mode: agent` with input images. It returns 400\n\n## Questions\n\n### Which is better for AI agents, Iris-3B or Qwen-Image 2.1 (Model Studio)?\n\nQwen-Image 2.1 (Model Studio) scores 64.6 (B) on agent readiness against Iris-3B's 50.9 (D), and leads in 6 of 7 scored categories. Iris-3B leads on payments \u0026 pricing.\n\n### Do Iris-3B and Qwen-Image 2.1 (Model Studio) need an API key?\n\nIris-3B needs no key. Qwen-Image 2.1 (Model Studio) needs an API key.\n\n### Can an agent call Iris-3B and Qwen-Image 2.1 (Model Studio) without installing anything?\n\nNo hosted endpoint is listed for Iris-3B. Qwen-Image 2.1 (Model Studio) has a hosted endpoint at https://dashscope-intl.aliyuncs.com/api/v1.\n\n### Are Iris-3B and Qwen-Image 2.1 (Model Studio) open source?\n\nIris-3B is open source (Apache-2.0 (code and weights)). No open-source release is listed for Qwen-Image 2.1 (Model Studio).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"iris-3b\", \"b\": \"qwen-image-2-1\"}`. From a terminal: `anchor compare iris-3b qwen-image-2-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/iris-3b.json and https://www.anchorterminal.com/api/v1/tools/qwen-image-2-1.json\n\n## Other comparisons with Iris-3B or Qwen-Image 2.1 (Model Studio)\n\n- [Adobe Firefly API vs Iris-3B](https://www.anchorterminal.com/compare/adobe-firefly-vs-iris-3b.md)\n- [Adobe Firefly API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/adobe-firefly-vs-qwen-image-2-1.md)\n- [Black Forest Labs FLUX API vs Iris-3B](https://www.anchorterminal.com/compare/black-forest-labs-vs-iris-3b.md)\n- [Black Forest Labs FLUX API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/black-forest-labs-vs-qwen-image-2-1.md)\n- [Bria API vs Iris-3B](https://www.anchorterminal.com/compare/bria-vs-iris-3b.md)\n- [Bria API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/bria-vs-qwen-image-2-1.md)\n- [fal image models vs Iris-3B](https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.md)\n- [fal image models vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1.md)\n- [Google Imagen vs Iris-3B](https://www.anchorterminal.com/compare/google-imagen-vs-iris-3b.md)\n- [Google Imagen vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/google-imagen-vs-qwen-image-2-1.md)\n- [Ideogram API vs Iris-3B](https://www.anchorterminal.com/compare/ideogram-vs-iris-3b.md)\n- [Ideogram API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/ideogram-vs-qwen-image-2-1.md)\n- [Iris-3B vs Leonardo.Ai API](https://www.anchorterminal.com/compare/iris-3b-vs-leonardo-ai.md)\n- [Iris-3B vs OpenAI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-openai-image-api.md)\n- [Iris-3B vs Recraft API](https://www.anchorterminal.com/compare/iris-3b-vs-recraft.md)\n- [Iris-3B vs Replicate image models](https://www.anchorterminal.com/compare/iris-3b-vs-replicate-image.md)\n- [Iris-3B vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.md)\n- [Iris-3B vs Stability AI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-stability-ai-image.md)\n- [Leonardo.Ai API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/leonardo-ai-vs-qwen-image-2-1.md)\n- [OpenAI Image API vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/openai-image-api-vs-qwen-image-2-1.md)\n- [Qwen-Image 2.1 (Model Studio) vs Recraft API](https://www.anchorterminal.com/compare/qwen-image-2-1-vs-recraft.md)\n- [Qwen-Image 2.1 (Model Studio) vs Replicate image models](https://www.anchorterminal.com/compare/qwen-image-2-1-vs-replicate-image.md)\n- [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)\n- [Qwen-Image 2.1 (Model Studio) vs Stability AI Image API](https://www.anchorterminal.com/compare/qwen-image-2-1-vs-stability-ai-image.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "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.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-15", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Iris-3B vs Qwen-Image 2.1 (Model Studio)", "url": "" } ], "description": "Qwen-Image 2.1 scores 64.6 (B) to Iris-3B's 50.9 (D) for image generation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Iris-3B D 50.9", "Qwen-Image 2.1 (Model Studio) B 64.6", "scores" ], "h1": "Iris-3B vs Qwen-Image 2.1 (Model Studio)", "image": "https://www.anchorterminal.com/assets/og/compare-iris-3b-vs-qwen-image-2-1.png", "path": "/compare/iris-3b-vs-qwen-image-2-1", "published": "2026-10-01", "section": "tools", "title": "Iris-3B vs Qwen-Image 2.1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-15", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1" }, "tokens": { "markdown": 2700, "slim": 780 }, "version": 1 }