{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "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" }, "tool": { "slug": "vela", "name": "Vela 2.0", "vendor": "vLLM Semantic Router project and KR Labs", "vendorUrl": "https://vllm-sr.ai", "kind": "model", "category": "decision-models", "summary": "Vela 2.0 is a family of four open-weight decision models from the vLLM Semantic Router project and KR Labs, released on 6 October 2026 under Apache-2.0 for routing, safety checks, personal-data spans and hallucination checks.", "url": "https://www.anchorterminal.com/tools/vela", "markdownUrl": "https://www.anchorterminal.com/tools/vela.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vela.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vela.json", "repo": "https://github.com/vllm-project/semantic-router", "license": "Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "vllm-sr" } ], "auth": "none", "authNotes": "No account. The weights are public and ungated on Hugging Face. The bundled `vela2_serve.py` binds to 127.0.0.1 and ignores the Authorization header unless `VELA2_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` and answers 401 otherwise. The router's model runtime has no authentication and publishes on 127.0.0.1 unless `--host` is passed.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy and no hosted API. Hardware is the owner's cost. The 0.3B runs on a CPU, and the cards put GPU parameter memory at about 17 GB for the 4B. The router docs list about 32 GB for the 9B (checked 2026-10-08).", "priceSummary": "Free ยท OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Vela 2.0 is software the owner runs, and neither server has a payment route (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 6054, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://huggingface.co/collections/vllm-sr/vela-20", "openapi": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/vllm_srun/api/openapi.yaml", "capabilities": [ "inference.decision", "guard.pii", "guard.injection", "guard.moderation", "guard.self-host" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "openapi" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 66.5, "grade": "B", "agentReady": false, "rank": 237, "ranked": true, "rankOf": 722, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 79, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 78, "security": 60, "transparency": 48 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 57, "points": 11.4, "reason": "Scored on the local-package checklist, since Vela 2.0 is a model the owner runs. There are two routes. The model cards load it with `pip install torch \"transformers\u003e=5.17\"` and `AutoModel.from_pretrained(..., trust_remote_code=True)`, with no Python version stated. The router's `vllm-sr` package on PyPI states Python 3.10 or newer, but serving a model with it is newer than the 0.4.0 stable release and needs the development channel (12 of 20). The semantic-router repository has public CI whose model-runtime suite includes five `test_vela2_*` files, and each model repository ships a parity record against the research scorer with zero decision differences on 230 rows. We couldn't read today's CI result on main, since the GitHub API was rate-limited and the Actions page we got was stale (15 of 25). The router repository showed 408 open issues on 8 October, 23 of them mentioning Vela, against 200 commits between 23 September and 8 October. The four Hub repositories have no discussions. Issue #4668 of 7 October tracks the 0.3B's CPU latency, which the release note puts at 79 ms against 16 ms for Vela 1.0 (14 of 25). The Hub repositories have no version tags, and the 4B and 9B weights were replaced in place on 3 October. The router pins the revisions it loads and publishes a dated release note (6 of 15). Released as 2.0 with no beta label on the cards, though the `vllm-sr` package is classified beta and the family is two days past launch (10 of 15)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 78, "points": 12.68, "reason": "Read for a model the owner serves. The router's model runtime carries an OpenAPI 3.0.3 file, contract version 2.2.0, served at `GET /openapi.yaml`, which covers `/v1/decisions` and its `/v1/systemone` alias. The server bundled in the model repositories has no specification file (22 of 25). vllm-sr.ai has no llms.txt (404). The model cards, USAGE.md, EVALUATION.md and TRAINING.md are Markdown in each repository (5 of 10). Each card states the size's intended place and its evaluation limits, and the router's release note names the signals where the 0.3B is behind Vela 1.0. We found no section on uses to avoid (15 of 20). Five question types with 2 to 255 options, 2 to 10 score levels and 1 to 255 labels, and enums for span head and long-input policy. State is free-form text or named parts (13 of 15). Recorded responses for every example, and error tables for both servers (400, 404, 413, 422, 429 and 503 with codes on the runtime) (14 of 15). The runtime contract is versioned and reports `api_version`, and the router has dated release notes. The models themselves have no tags or changelog (9 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 79, "points": 12.84, "reason": "Read as an API an agent calls for a decision, as with Jev, Clef and Kev. Answers are probabilities and spans, `output_tokens` is always 0, and the decoders read the state once and fork it per question. Input is 16,384 tokens a sequence, or 8,192 on the 0.3B (20 of 25). The caller fixes the output shape with any mix of the five types, a `threshold` per question, a `head` override for spans and `/v1/bundle` for several tasks in one call (18 of 20). The runtime answers with `{error: {code, message}}`, and a failed question carries its own code without failing the others. The bundled server answers 422 with `loc`, `msg` and `type`, and 413 for oversize questions (16 of 20). Calls are stateless and safe to retry. The runtime answers 429 `overloaded` past 256 queued requests a model. We found no `Retry-After` header in the runtime code and no retry guidance (15 of 20). `typesafe-sdk` works against the bundled server per USAGE.md, and loading is one `AutoModel` call. Setup needs `trust_remote_code`, about 17 GB of GPU memory for the 4B, or the router's development channel (10 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 60, "points": 10.5, "reason": "Read as software the owner runs. No account. The bundled `vela2_serve.py` binds to 127.0.0.1 and is open unless `VELA2_API_KEY` is set, after which it requires one bearer key, compared in constant time. The router's model runtime has no authentication, and its docs say to expose it only on a trusted network (13 of 30). A decision model has no write actions (15 of 20). The models are trained to flag prompt attacks, each question sees only the state and its own block, and the router's SECURITY.md names adversarial input to classification models in its threat model. Nothing documents how hostile text in the state can move an answer (10 of 15). The runtime exposes Prometheus metrics and, on request, the revision, digest and timings that answered a call, and its docs say request text is never logged. The bundled server keeps no record of calls (9 of 15). SECURITY.md takes private reports through GitHub Security Advisories, with severity classes and a disclosure policy. Weights are safetensors with a SHA256SUMS manifest in the decoder repositories, and the runtime checks every file's SHA-256 and never runs code from a model repository. The `transformers` route does run repository code through `trust_remote_code=True`, with no tag to pin. No bug bounty, and no security.txt on vllm-sr.ai (13 of 20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up. No payment protocol (0). There is no hosted API. Hardware is the owner's cost." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 84, "points": 7.35, "reason": "Read for an open-weight model. Launched on 6 October 2026, with the four model repositories last changed on 7 October (30). Vela 1.0 on 18 September, the first Vela 2.0 upload on 29 September, re-exported weights on 3 October and the launch on 6 October (20). The router repository's 200 newest commits span 23 September to 8 October from more than eight authors, and the release note links issues the maintainers opened in the same week. 408 issues were open and we didn't check reply times (17 of 25). No SDK of its own. The cards point to `typesafe-sdk`, and the `vllm-sr` CLI on PyPI had a development build dated 8 October (10 of 15). The router repository runs CI, a security scan and a package check, with today's result on main unread (7 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 48, "points": 4.2, "note": "editorial 68, provenance 27", "reason": "Apache-2.0 for the weights, code and documentation, on Apache-2.0 Decision 2.0 and Qwen3.5 bases, with MODIFICATIONS.md and ATTRIBUTIONS.md in each repository. The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data isn't redistributed and keeps its own licences, some CC BY-SA. We found no training code (26 of 30). Self-hosted, so inputs stay on the owner's hardware. The runtime docs say request text is never logged and metrics carry no request content. There's no privacy statement for the project (22 of 30). The router's support matrix defines a Deprecated class and says nothing is in it, and the release note gives the lines that restore each Vela 1.0 model. No policy with notice periods (10 of 20). We found no telemetry statement either way and didn't audit the runtime's code for it. Weights download from the Hugging Face Hub (10 of 20)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Read as an API an agent calls for a decision, as with Jev, Clef and Kev. Answers are probabilities and spans, `output_tokens` is always 0, and the decoders read the state once and fork it per question. Input is 16,384 tokens a sequence, or 8,192 on the 0.3B (20 of 25). The caller fixes the output shape with any mix of the five types, a `threshold` per question, a `head` override for spans and `/v1/bundle` for several tasks in one call (18 of 20). The runtime answers with `{error: {code, message}}`, and a failed question carries its own code without failing the others. The bundled server answers 422 with `loc`, `msg` and `type`, and 413 for oversize questions (16 of 20). Calls are stateless and safe to retry. The runtime answers 429 `overloaded` past 256 queued requests a model. We found no `Retry-After` header in the runtime code and no retry guidance (15 of 20). `typesafe-sdk` works against the bundled server per USAGE.md, and loading is one `AutoModel` call. Setup needs `trust_remote_code`, about 17 GB of GPU memory for the 4B, or the router's development channel (10 of 15).", "maintenance": "Read for an open-weight model. Launched on 6 October 2026, with the four model repositories last changed on 7 October (30). Vela 1.0 on 18 September, the first Vela 2.0 upload on 29 September, re-exported weights on 3 October and the launch on 6 October (20). The router repository's 200 newest commits span 23 September to 8 October from more than eight authors, and the release note links issues the maintainers opened in the same week. 408 issues were open and we didn't check reply times (17 of 25). No SDK of its own. The cards point to `typesafe-sdk`, and the `vllm-sr` CLI on PyPI had a development build dated 8 October (10 of 15). The router repository runs CI, a security scan and a package check, with today's result on main unread (7 of 10).", "payments": "Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up. No payment protocol (0). There is no hosted API. Hardware is the owner's cost.", "reliability": "Scored on the local-package checklist, since Vela 2.0 is a model the owner runs. There are two routes. The model cards load it with `pip install torch \"transformers\u003e=5.17\"` and `AutoModel.from_pretrained(..., trust_remote_code=True)`, with no Python version stated. The router's `vllm-sr` package on PyPI states Python 3.10 or newer, but serving a model with it is newer than the 0.4.0 stable release and needs the development channel (12 of 20). The semantic-router repository has public CI whose model-runtime suite includes five `test_vela2_*` files, and each model repository ships a parity record against the research scorer with zero decision differences on 230 rows. We couldn't read today's CI result on main, since the GitHub API was rate-limited and the Actions page we got was stale (15 of 25). The router repository showed 408 open issues on 8 October, 23 of them mentioning Vela, against 200 commits between 23 September and 8 October. The four Hub repositories have no discussions. Issue #4668 of 7 October tracks the 0.3B's CPU latency, which the release note puts at 79 ms against 16 ms for Vela 1.0 (14 of 25). The Hub repositories have no version tags, and the 4B and 9B weights were replaced in place on 3 October. The router pins the revisions it loads and publishes a dated release note (6 of 15). Released as 2.0 with no beta label on the cards, though the `vllm-sr` package is classified beta and the family is two days past launch (10 of 15).", "schema": "Read for a model the owner serves. The router's model runtime carries an OpenAPI 3.0.3 file, contract version 2.2.0, served at `GET /openapi.yaml`, which covers `/v1/decisions` and its `/v1/systemone` alias. The server bundled in the model repositories has no specification file (22 of 25). vllm-sr.ai has no llms.txt (404). The model cards, USAGE.md, EVALUATION.md and TRAINING.md are Markdown in each repository (5 of 10). Each card states the size's intended place and its evaluation limits, and the router's release note names the signals where the 0.3B is behind Vela 1.0. We found no section on uses to avoid (15 of 20). Five question types with 2 to 255 options, 2 to 10 score levels and 1 to 255 labels, and enums for span head and long-input policy. State is free-form text or named parts (13 of 15). Recorded responses for every example, and error tables for both servers (400, 404, 413, 422, 429 and 503 with codes on the runtime) (14 of 15). The runtime contract is versioned and reports `api_version`, and the router has dated release notes. The models themselves have no tags or changelog (9 of 15).", "security": "Read as software the owner runs. No account. The bundled `vela2_serve.py` binds to 127.0.0.1 and is open unless `VELA2_API_KEY` is set, after which it requires one bearer key, compared in constant time. The router's model runtime has no authentication, and its docs say to expose it only on a trusted network (13 of 30). A decision model has no write actions (15 of 20). The models are trained to flag prompt attacks, each question sees only the state and its own block, and the router's SECURITY.md names adversarial input to classification models in its threat model. Nothing documents how hostile text in the state can move an answer (10 of 15). The runtime exposes Prometheus metrics and, on request, the revision, digest and timings that answered a call, and its docs say request text is never logged. The bundled server keeps no record of calls (9 of 15). SECURITY.md takes private reports through GitHub Security Advisories, with severity classes and a disclosure policy. Weights are safetensors with a SHA256SUMS manifest in the decoder repositories, and the runtime checks every file's SHA-256 and never runs code from a model repository. The `transformers` route does run repository code through `trust_remote_code=True`, with no tag to pin. No bug bounty, and no security.txt on vllm-sr.ai (13 of 20).", "transparency": "Apache-2.0 for the weights, code and documentation, on Apache-2.0 Decision 2.0 and Qwen3.5 bases, with MODIFICATIONS.md and ATTRIBUTIONS.md in each repository. The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data isn't redistributed and keeps its own licences, some CC BY-SA. We found no training code (26 of 30). Self-hosted, so inputs stay on the owner's hardware. The runtime docs say request text is never logged and metrics carry no request content. There's no privacy statement for the project (22 of 30). The router's support matrix defines a Deprecated class and says nothing is in it, and the release note gives the lines that restore each Vela 1.0 model. No policy with notice periods (10 of 20). We found no telemetry statement either way and didn't audit the runtime's code for it. Weights download from the Hugging Face Hub (10 of 20)." }, "sources": [ { "what": "launch post, 6 October 2026", "url": "https://vllm-sr.ai/blog/vela-2-0-open-foundation-routing-models/", "seen": "2026-10-08" }, { "what": "Vela 2.0 collection", "url": "https://huggingface.co/collections/vllm-sr/vela-20", "seen": "2026-10-08" }, { "what": "Vela-2.0-4B model card", "url": "https://huggingface.co/vllm-sr/Vela-2.0-4B", "seen": "2026-10-08" }, { "what": "Vela-2.0-4B usage guide, with the server's protocol table", "url": "https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/USAGE.md", "seen": "2026-10-08" }, { "what": "Vela-2.0-4B evaluation and disclosures", "url": "https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/EVALUATION.md", "seen": "2026-10-08" }, { "what": "Vela-2.0-4B training stages and data licences", "url": "https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/TRAINING.md", "seen": "2026-10-08" }, { "what": "bundled server source", "url": "https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/vela2_serve.py", "seen": "2026-10-08" }, { "what": "repository metadata, files, commits, tags and discussions for the four models", "url": "https://huggingface.co/api/models/vllm-sr/Vela-2.0-4B", "seen": "2026-10-08" }, { "what": "0.3B licence scope and tokeniser terms", "url": "https://huggingface.co/vllm-sr/Vela-2.0-0.3B/blob/main/LICENSING_STATUS.md", "seen": "2026-10-08" }, { "what": "semantic-router repository (cloned), SECURITY.md, workflows and model-runtime tests", "url": "https://github.com/vllm-project/semantic-router", "seen": "2026-10-08" }, { "what": "release note on the 0.3B becoming the built-in signal default", "url": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "seen": "2026-10-08" }, { "what": "model runtime reference, HTTP API, errors, metrics and security", "url": "https://github.com/vllm-project/semantic-router/blob/main/website/docs/model-runtime/reference.md", "seen": "2026-10-08" }, { "what": "model runtime OpenAPI file", "url": "https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/vllm_srun/api/openapi.yaml", "seen": "2026-10-08" }, { "what": "model runtime quickstart and release channel note", "url": "https://github.com/vllm-project/semantic-router/blob/main/website/docs/model-runtime/quickstart.md", "seen": "2026-10-08" }, { "what": "vllm-sr package metadata and release list", "url": "https://pypi.org/pypi/vllm-sr/json", "seen": "2026-10-08" }, { "what": "open issues", "url": "https://github.com/vllm-project/semantic-router/issues", "seen": "2026-10-08" }, { "what": "security.txt (404)", "url": "https://vllm-sr.ai/.well-known/security.txt", "seen": "2026-10-08" }, { "what": "domain registration", "url": "https://rdap.org/domain/vllm-sr.ai", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: today's CI result on the semantic-router main branch. api.github.com answered 403 for the rate limit and the Actions page we were served was stale", "unchecked: reply times on issues and pull requests in vllm-project/semantic-router", "unchecked: PyPI download counts for `vllm-sr`. pypistats.org answered 429", "unchecked: whether the model runtime or the `vllm-sr` CLI sends any telemetry. We found no statement and didn't audit the code", "The accuracy, calibration and latency figures are the authors', on their own harness. We haven't run them", "The listing covers Vela 2.0 only. Decision 2.0 and Vela 1.0 sit in the same Hugging Face organisation and aren't graded here", "The 0.3B repository's LICENSING_STATUS.md is inherited from Decision-1.0-Kai and says no runtime code is bundled, while the repository does ship `vela2_inference.py`", "No legal entity was found. The site footer names the vLLM Semantic Router Team, and KR Labs is credited as co-lead on the model cards" ] }, "negative": 0, "verdict": "One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.", "bestFor": "Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.", "strengths": [ "Five question types in one request (choice, noul, score, set and span), with span answers as labelled character offsets and a probability each", "Apache-2.0 weights, code and documentation, ungated on Hugging Face, with safetensors files and a SHA256SUMS manifest in the three decoder repositories", "Two serving routes. A bundled FastAPI server on `POST /v1/systemone`, and the router's model runtime with an OpenAPI 3.0.3 contract and Prometheus metrics", "The model cards disclose evaluation protocol, including that the 0.3B release selection considered test results and that SQuAD v2 isn't zero-shot", "The router's release note lists where the 0.3B default is behind Vela 1.0, with numbers, and how to restore each Vela 1.0 model" ], "weaknesses": [ "No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026", "Loading with `transformers` needs `trust_remote_code=True`, which runs Python from the model repository", "The router's `vllm-sr serve MODEL` engine mode is newer than the 0.4.0 stable release and needs the development channel", "By the authors' figures the 4B scores 31.63 on the Jev Decision Index 0.2.1 against 42.55 for its Decision 2.0 base", "The model runtime has no authentication, and the bundled server is open unless `VELA2_API_KEY` is set" ], "agentNotes": [ "Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch", "Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name", "Name span questions `pii`, `halu` or `toxic`, or set `\"head\": \"router\"`, to get the trained router head. Other labels go to the broad head", "Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit", "Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network" ], "metrics": { "kind": "local", "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": 66.5 } ], "editorialScores": { "ergonomics": 79, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 78, "security": 60, "transparency": 68 }, "provenanceScore": 27 }, "connect": { "install": "pip install torch \"transformers\u003e=5.17\" safetensors tokenizers numpy fastapi uvicorn\n# from a local snapshot of vllm-sr/Vela-2.0-4B\npython vela2_serve.py --model . --device cuda --port 8001", "http": "curl -s localhost:8001/v1/systemone -H 'content-type: application/json' \\\n -d '{\"model\":\"vllm-sr/Vela-2.0-4B\",\"state\":\"My card was charged twice and the parcel never arrived.\",\"questions\":{\"issues\":{\"type\":\"set\",\"instructions\":\"Which issues does the customer report?\",\"criteria\":{\"billing\":\"payments, charges, refunds or invoices\",\"shipping\":\"delivery of an order or a parcel\",\"login\":\"signing in, passwords or account access\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/vela" }, "notable": [ "Four sizes share one request format. Vela-2.0-0.3B is a 307M encoder for CPU and ONNX with 8,192 tokens of input, and the 0.8B, 4B and 9B are Qwen3.5-based decoders with 16,384 (https://vllm-sr.ai/blog/vela-2-0-open-foundation-routing-models/)", "Not a TypeSafe product. `system_one(state, questions)` accepts the TypeSafe SystemOne request, and USAGE.md shows `typesafe-sdk` pointed at the bundled server (https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/USAGE.md)", "By the authors' figures the 9B scores 41.09 on the Jev Decision Index 0.2.1 against 46.23 for its base Decision-2.0-Lux-9B, and the 4B 31.63 against 42.55. These are the authors' numbers, not ours (https://vllm-sr.ai/blog/vela-2-0-open-foundation-routing-models/)", "The authors report a macro AUC of 0.871, 0.875, 0.921 and 0.921 for the four sizes over 14 public safety and prompt-attack sets, on trained task families (https://vllm-sr.ai/blog/vela-2-0-open-foundation-routing-models/)", "The router made Vela-2.0-0.3B its built-in signal default on 7 October 2026, and its release note says the 0.3B is behind Vela 1.0 on modality, user feedback, domain and fact check, and takes 79 ms against 16 ms on a 12-core CPU (https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals)", "The GitHub stars (6,054) are for the semantic-router repository. The four model repositories showed 371, 87, 67 and 75 downloads on 8 October 2026 (https://huggingface.co/api/models/vllm-sr/Vela-2.0-0.3B)", "The 0.3B card records that its final release selection also considered test results, and that its shipped PII threshold floor was lowered after the test effect was seen (https://huggingface.co/vllm-sr/Vela-2.0-4B/blob/main/EVALUATION.md)" ], "area": "models", "details": [ { "label": "Models", "value": "Vela-2.0-0.3B (307M encoder, from Decision-1.0-Kai), Vela-2.0-0.8B (756M), Vela-2.0-4B (4.2B) and Vela-2.0-9B (7.9B), the last three fine-tuned from Decision 2.0 Eos, Nox and Lux on Qwen3.5 backbones" }, { "label": "Licence", "value": "Apache-2.0 for weights, code and documentation. The 0.3B's tokeniser keeps the Gemma Terms of Use. Training data isn't redistributed and keeps its own licences, some CC BY-SA" }, { "label": "Question types", "value": "choice (2 to 255 options), noul (yes or no), score (2 to 10 ordered levels), set (any number of labels) and span (labelled character offsets), any mix in one request" }, { "label": "Context", "value": "8,192 tokens on the 0.3B and 16,384 a rendered sequence on the decoders. Span targets over 2,048 tokens are read in windows of up to 1,800" }, { "label": "Hardware", "value": "The 0.3B runs on a CPU or through ONNX. GPU with bf16 autocast is the evaluated setting for the decoders, about 17 GB of parameter memory for the 4B. fp16 isn't supported" }, { "label": "Serving", "value": "`AutoModel.from_pretrained(..., trust_remote_code=True)` and `model.system_one(...)`, the bundled `vela2_serve.py` on `POST /v1/systemone`, or the router's model runtime on `POST /v1/decisions` (development channel)" }, { "label": "Span heads", "value": "A router head trained on PII (17 types), unsupported claims and toxic spans, and on the decoders a broad head for open labels. The response names the head that answered" }, { "label": "Errors", "value": "Bundled server 401, 413 and 422 with `detail`. Model runtime 400, 404, 413, 422, 429 and 503 with `{error: {code, message}}`" }, { "label": "Hosted option", "value": "None" }, { "label": "Languages", "value": "17 listed on the cards, among them Arabic, Chinese, English, French, German, Hindi, Japanese, Korean and Spanish" } ], "provenance": { "legalEntity": "", "domain": "vllm-sr.ai", "domainRegistered": "2026-07-13", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "An open-source project with no company named as publisher. The site footer reads vLLM Semantic Router Team, and the model cards credit KR Labs and vLLM Semantic Router.", "RDAP gives 13 July 2026 as the registration date of vllm-sr.ai.", "Software the owner runs, so there's no hosted endpoint, terms or privacy policy. The Apache-2.0 licence stands in for terms.", "vllm-sr.ai/.well-known/security.txt returns 404. SECURITY.md in the repository takes private reports through GitHub Security Advisories.", "The weights are on huggingface.co under the vllm-sr organisation, and the code for the router and its model runtime is at github.com/vllm-project/semantic-router." ], "score": 27, "checks": [ { "check": "Legal entity named", "value": "not found", "points": 0, "max": 20, "state": "no" }, { "check": "Domain age", "value": "vllm-sr.ai, registered 2026-07-13 (under a year)", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vela.json", "live": { "slug": "vela", "versions": [ { "registry": "github", "name": "vllm-project/semantic-router", "version": "v0.4.0", "released": "2026-09-27", "seenAt": "2026-10-08T16:33:55.54175052Z" }, { "registry": "pypi", "name": "vllm-sr", "version": "0.4.0", "released": "2026-09-27", "seenAt": "2026-10-08T16:33:55.414998665Z" } ], "githubStars": 6055, "pypiWeekly": 16024, "securityTxt": { "url": "https://vllm-sr.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:46.503839021Z" }, "pages": [ { "url": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:25:37.750304198Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "247e26c3549e" } ], "updatedAt": "2026-10-08T18:25:37.750304198Z" } } }