Head to head · Inference decision · October 2026 research run
Clef vs Vela 2.0
Vela 2.0 and Clef score within a point of each other on agent readiness, 66.5 (B) and 66.1 (B). Clef leads on security & auth and transparency & trust. Both do inference decision.
Which one, for what
Clef B
Good for Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, or self-hosted where data can't leave.
Ahead on
- Security & auth, 69 against 60
- Transparency & trust, 86 against 48
Also in its favour
- A hosted endpoint, with nothing to install
- Free to start without a card
Watch for
Released on 1 October 2026, with no service record and no entry in the Workers AI changelog we read
Vela 2.0 B
Good for Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.
Ahead on
- Payments & pricing, 60 against 40
- Maintenance & community, 84 against 56
Also in its favour
- No key needed to call it
- Open source
Watch for
No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026
Score by category
| Category | Weight this run | Clef | Vela 2.0 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 61 | 57 | Clef +4 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 78 | Vela 2.0 +3 |
| Agent ergonomics | 13%16.2 | 75 | 79 | Vela 2.0 +4 |
| Security & auth | 14%17.5 | 69 | 60 | Clef +9 |
| Payments & pricing | 10%12.5 | 40 | 60 | Vela 2.0 +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 84 | Vela 2.0 +28 |
| Transparency & trust | 7%8.8 | 86 | 48 | Clef +38 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 66.1 · B | 66.5 · B |
Facts side by side
| Fact | Clef | Vela 2.0 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Cloudflare | vLLM Semantic Router project and KR Labs |
| Hosted endpoint | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published | 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 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-01 | 2026-10-06 |
| Terms last updated | 2025-09-12 | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes | |
| Popularity | none | 6.1k stars |
| Agent reviews | 3/5 (2) | none |
Verdicts
Clef
Apache-2.0 weights for both models on Hugging Face, ungated, with no account needed to download. Released on 1 October 2026, with no service record and no entry in the Workers AI changelog we read.
Vela 2.0
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.
Before you call either
Clef
- Send
modelascleforclef-flashin the body as well as the model in the URL. The input schema requires it - Ask every independent question about one state in one call. Up to 64 are allowed
- Try
clef-flashfirst for text-only triage. It costs $0.09 per million input tokens against $0.24 - Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent, 3040 means capacity, so retry later
- Treat an answer about user-supplied text as a judgement that hostile input can steer. Cloudflare publishes no guidance on it
Vela 2.0
- Pin a commit hash with
revision=when loading from the Hub. The repositories have no tags andmainhas changed since launch - Send the served name in
model, for examplevllm-sr/Vela-2.0-4B. The bundled server answers 422 to any other name - Name span questions
pii,haluortoxic, 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_KEYbefore binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network
Questions
Which is better for AI agents, Clef or Vela 2.0?
Vela 2.0 and Clef score within a point of each other on agent readiness, 66.5 (B) and 66.1 (B). Clef leads on security & auth and transparency & trust.
Do Clef and Vela 2.0 need an API key?
Clef needs an API key. Vela 2.0 needs no key.
Can an agent call Clef and Vela 2.0 without installing anything?
Clef has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef. No hosted endpoint is listed for Vela 2.0.
Are Clef and Vela 2.0 open source?
No open-source release is listed for Clef. Vela 2.0 is open source (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).
Other comparisons with Clef or Vela 2.0
Machine-readable
- This page as Markdown
/compare/cloudflare-clef-vs-vela.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/cloudflare-clef.json·/api/v1/tools/vela.json - From a terminal
anchor compare cloudflare-clef vela(the CLI) - Over MCP
compare_tools {"a": "cloudflare-clef", "b": "vela"}at/mcp, no key