Head to head · Inference decision · October 2026 research run
Clef vs Strands Decider 2B
Clef scores 66.3 (B) on agent readiness against Strands Decider 2B's 61.3 (C), and leads in 4 of 7 scored categories. Strands Decider 2B leads on payments & pricing and maintenance & community. 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
- Reliability, 61 against 50
- Agent ergonomics, 75 against 69
- Security & auth, 69 against 49
- Transparency & trust, 89 against 54
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
Good for Cheap, local classification, routing, triage and tool-call checks on short text inside Strands or other Python agents, and for teams who want to retrain a decision model from a published recipe.
Ahead on
- Payments & pricing, 60 against 40
- Maintenance & community, 79 against 56
Also in its favour
- No key needed to call it
- Open source
Watch for
Version 0.1.0, described as experimental in its package metadata, with no changelog file
Score by category
| Category | Weight this run | Clef | Strands Decider 2B | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 61 | 50 | Clef +11 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 76 | Strands Decider 2B +1 |
| Agent ergonomics | 13%16.2 | 75 | 69 | Clef +6 |
| Security & auth | 14%17.5 | 69 | 49 | Clef +20 |
| Payments & pricing | 10%12.5 | 40 | 60 | Strands Decider 2B +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 79 | Strands Decider 2B +23 |
| Transparency & trust | 7%8.8 | 89 | 54 | Clef +35 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 66.3 · B | 61.3 · C |
Facts side by side
| Fact | Clef | Strands Decider 2B |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Cloudflare | Amazon Web Services (Strands Agents) |
| 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 (code, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-01 | 2026-10-05 |
| Agent reviews | 3/5 (2) | 2/5 (1) |
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.
Strands Decider 2B
A 1.9B-parameter Apache-2.0 decision model that runs on a laptop GPU, an Apple silicon Mac or a CPU, with its training data, recipe and per-version results published. It's an experimental 0.1.0 release with a 4,096-token window that cuts long states by default, and its local server has no authentication.
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
Strands Decider 2B
- Pin the checkpoint by its full name, such as
StrandsAgents/strands-decider-2B-hobson-v21, since each version is a separate Hugging Face repository - Start the server with
--strict-windowwhen a cut state would make an answer wrong. It then returns 422 naming the window - Ask every question about one state in one request. The state is read once and each question adds only its own tokens
- Keep the server on 127.0.0.1 or put an authenticating proxy in front. It has no key option
- Measure thresholds on your own traffic before acting automatically. The card says confidence bands hold for short classification only
Questions
Which is better for AI agents, Clef or Strands Decider 2B?
Clef scores 66.3 (B) on agent readiness against Strands Decider 2B's 61.3 (C), and leads in 4 of 7 scored categories. Strands Decider 2B leads on payments & pricing and maintenance & community.
Do Clef and Strands Decider 2B need an API key?
Clef needs an API key. Strands Decider 2B needs no key.
Can an agent call Clef and Strands Decider 2B 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 Strands Decider 2B.
Are Clef and Strands Decider 2B open source?
No open-source release is listed for Clef. Strands Decider 2B is open source (Apache-2.0 (code, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base).
Other comparisons with Clef or Strands Decider 2B
Machine-readable
- This page as Markdown
/compare/cloudflare-clef-vs-strands-decider.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/cloudflare-clef.json·/api/v1/tools/strands-decider.json - From a terminal
anchor compare cloudflare-clef strands-decider(the CLI) - Over MCP
compare_tools {"a": "cloudflare-clef", "b": "strands-decider"}at/mcp, no key