{ "data": { "a": { "slug": "strands-decider", "name": "Strands Decider 2B", "vendor": "Amazon Web Services (Strands Agents)", "vendorUrl": "https://strandsagents.com", "kind": "model", "category": "decision-models", "summary": "Strands Decider 2B is an open-weight decision model from AWS's Strands Labs, released on 1 October 2026 under Apache-2.0. It answers typed yes or no, choice and score questions with probabilities, and runs locally from a Python package.", "url": "https://www.anchorterminal.com/tools/strands-decider", "markdownUrl": "https://www.anchorterminal.com/tools/strands-decider.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/strands-decider.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/strands-decider.json", "repo": "https://github.com/strands-labs/strands-decider", "license": "Apache-2.0 (code, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "strands-decider" } ], "auth": "none", "authNotes": "No account. `strands-decider serve` binds to 127.0.0.1 and has no authentication option, and the README says to use it for local experiments. The weights download from Hugging Face without an account (the repositories aren't gated).", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy. You pay for your own hardware. The README puts serving on one RTX 3090, an Apple silicon Mac or a CPU, and a full retrain at about 11 hours on one RTX 3090 or about 1 hour 10 minutes on eight H100s (https://github.com/strands-labs/strands-decider). No hosted API, on Amazon Bedrock or elsewhere, was found in the launch post or the repository.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Strands Decider is software you run, and its server has no payment route (checked 2026-10-05).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-05" }, "docsUrl": "https://github.com/strands-labs/strands-decider#readme", "capabilities": [ "inference.decision" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "pre-1.0" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 61.3, "grade": "C", "agentReady": false, "rank": 235, "ranked": true, "rankOf": 460, "categoryRank": 5, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 79, "payments": 60, "reliability": 50, "schema": 76, "security": 49, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-05" }, "negative": 0, "verdict": "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.", "bestFor": "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.", "strengths": [ "Apache-2.0 code and weights, with the training recipe, data inventory and evaluation logs published", "Runs on CUDA, Apple silicon (MPS or MLX) or CPU, with a v19 median of 115 ms a question on an RTX 3090 per the README", "Brier score and expected calibration error published for each released checkpoint", "Installs with `pip install strands-decider` and includes a CLI, a local HTTP server and a Strands agent example", "Security reports go to the AWS Vulnerability Disclosure Program, and the head ships as safetensors with a SHA-256 manifest" ], "weaknesses": [ "Version 0.1.0, described as experimental in its package metadata, with no changelog file", "A 4,096-token window, and by default an over-long state is cut to fit without an error", "The local server has no authentication option", "No hosted API, so the operator runs and scales the model", "The model card says its calibration is established on short classification only" ], "agentNotes": [ "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-window` when 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" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 1, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.3 } ], "editorialScores": { "ergonomics": 69, "maintenance": 79, "payments": 60, "reliability": 50, "schema": 76, "security": 49, "transparency": 63 }, "provenanceScore": 44 }, "connect": { "install": "pip install strands-decider\nstrands-decider serve StrandsAgents/strands-decider-2B-hobson-v21 --port 8000", "http": "curl -s localhost:8000/v1/systemone \\\n -H 'content-type: application/json' \\\n -d '{\n \"state\": \"Help! My payouts have been failing for 3 days!\",\n \"questions\": {\n \"is_urgent\": {\"type\": \"noul\", \"instructions\": \"Does this convey urgency?\"}\n }\n }'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/strands-decider" }, "area": "models", "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "strandsagents.com", "domainRegistered": "2025-05-15", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-05", "notes": [ "The repository's SECURITY.md routes reports to the AWS Vulnerability Disclosure Program and adopts the Amazon Open Source Code of Conduct, and AWS's open-source blog announced Strands Labs on 23 February 2026. The legal entity is inferred from those pages. The licence names no copyright holder.", "strandsagents.com was registered on 15 May 2025 per RDAP. Its /.well-known/security.txt returned 404.", "Software you run, so there's no hosted endpoint, terms or privacy policy to check. The Apache-2.0 licence stands in for terms.", "No changelog file or GitHub release tags in the repository. Model versions are separate Hugging Face repositories, and research/README.md in the repository lists each training run." ], "score": 44 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/strands-decider.json" }, "answer": "Jev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "typesafe-jev", "name": "Jev", "vendor": "TypeSafe AI", "vendorUrl": "https://typesafe.ai", "kind": "model", "category": "decision-models", "summary": "Jev is TypeSafe AI's first System One model, a closed decision model behind an HTTP API.", "url": "https://www.anchorterminal.com/tools/typesafe-jev", "markdownUrl": "https://www.anchorterminal.com/tools/typesafe-jev.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/typesafe-jev.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json", "repo": "https://github.com/typesafe-ai/typesafe-sdk-python", "license": "Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT", "transports": [ "http" ], "remoteUrl": "https://api.typesafe.ai/v1/systemone", "packages": [ { "registry": "pypi", "name": "typesafe-sdk" }, { "registry": "npm", "name": "@typesafe-ai/sdk" } ], "auth": "api-key", "authNotes": "Bearer API key in the `Authorization` header, created at console.typesafe.ai/keys after signing in. The SDKs read `TYPESAFE_API_KEY`. We found no documentation of key scopes, expiry or rotation.", "pricing": "usage", "pricingNotes": "Jev 1.13 costs $0.042 per million input tokens ($42 per billion), and output tokens are free (https://docs.typesafe.ai/models). Jev is in early access with a waitlist, and we found no free tier or free credits. Credits bought under the Master Customer Agreement expire 12 months after purchase and aren't refunded on termination (https://typesafe.ai/legal/mca). Higher rate limits come with custom and enterprise plans, and zero data retention is arranged with sales.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI document or the SDKs (checked 2026-10-02).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 15, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://docs.typesafe.ai/introduction", "llmsTxt": "https://docs.typesafe.ai/llms.txt", "openapi": "https://api.typesafe.ai/openapi.json", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "closed-source", "openapi", "llms-txt", "python", "typescript", "usage-priced", "status-page", "beta" ], "lastRelease": "2026-09-26", "graded": true, "anchor": { "graded": true, "score": 62.2, "grade": "B", "agentReady": false, "rank": 224, "ranked": true, "rankOf": 460, "categoryRank": 4, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 84, "maintenance": 64, "payments": 20, "reliability": 60, "schema": 87, "security": 53, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Typed answers with probabilities for `noul`, `choice` and `score` questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found.", "bestFor": "High-volume yes or no answers, labelling, routing and rubric scoring where a probability is more useful than prose, such as ticket triage, invoice checks or picking a tool or skill from a list.", "strengths": [ "Typed answers with probabilities for `noul`, `choice` and `score` questions, many per call, with no text to parse", "$0.042 per million input tokens, with output tokens free", "A public OpenAPI 3.1 document, llms.txt with Markdown twins, and Python and TypeScript SDKs that retry 408, 429 and 5xx with backoff", "A known-limitations page that warns injected instructions can move an answer and lists what Jev can't do, such as counting, arithmetic and date comparison", "The privacy policy, DPA and customer agreement agree that customer data isn't used for training" ], "weaknesses": [ "Early access behind a waitlist, with no free tier or free credits found", "No SLA, and the customer agreement promises only commercially reasonable efforts to give notice of API changes", "Published limits of 40 requests a second can change without notice", "No security.txt and no stated retention period, and the trust centre and subprocessor list render only with JavaScript", "Closed and text only, with 32,000 tokens for state plus the longest question" ], "agentNotes": [ "Put every independent question about one state into a single call. They run in parallel and the state is billed once", "Pin `jev-1.13.0` instead of `jev-latest` once you've tuned confidence thresholds", "Back off exponentially on 429 and 529. The limits move with demand", "Keep state to what the decision needs. Accuracy falls as unrelated content grows, and state plus the longest question must fit in 32,000 tokens", "Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.2 } ], "editorialScores": { "ergonomics": 84, "maintenance": 64, "payments": 20, "reliability": 60, "schema": 87, "security": 53, "transparency": 41 }, "provenanceScore": 75 }, "connect": { "install": "pip install typesafe-sdk # or: npm install @typesafe-ai/sdk", "http": "curl https://api.typesafe.ai/v1/systemone \\\n -H \"Authorization: Bearer $TYPESAFE_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"jev-latest\",\"state\":\"Checkout has failed for every customer for an hour.\",\"questions\":{\"urgent\":{\"type\":\"noul\",\"instructions\":\"Is this request urgent?\"},\"team\":{\"type\":\"choice\",\"criteria\":{\"billing\":\"Payments and refunds\",\"technical\":\"Outages and errors\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/typesafe-jev" }, "area": "models", "unitPrices": [ { "item": "Jev 1.13 input", "unit": "1m-tokens", "usd": 0.042, "note": "Output tokens free" } ], "provenance": { "legalEntity": "TypeSafe AI, Inc.", "domain": "typesafe.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://typesafe.ai/legal/mca", "privacy": "https://typesafe.ai/legal/privacy-policy", "statusPage": "https://status.typesafe.ai", "changelog": "https://docs.typesafe.ai/sdk/python/changelog", "securityTxt": "none", "checked": "2026-10-01", "notes": [ "The Master Customer Agreement (updated 23 September 2026) governs use of the API. The site's terms of use (19 September 2026) name TypeSafe AI, Inc. and Delaware law.", "typesafe.ai/.well-known/security.txt returns 404.", "We couldn't read the domain's registration date, since RDAP refused our reader.", "The changelog is the Python SDK's. We found no changelog for the API or the model." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/typesafe-jev.json", "live": { "slug": "typesafe-jev", "probe": { "target": "https://api.typesafe.ai/v1/systemone", "method": "get", "lastAt": "2026-10-06T01:46:37.592588347Z", "lastOk": true, "lastStatus": 405, "lastMs": 164, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 186, "p95ms24h": 263, "samples24h": 273, "samples30d": 936, "days": [ { "date": "2026-10-02", "probes": 100, "ok": 100 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 21, "ok": 21 } ] }, "vendorStatus": { "page": "https://status.typesafe.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-06T01:26:23.337402757Z" }, "versions": [ { "registry": "github", "name": "typesafe-ai/typesafe-sdk-python", "version": "v0.7.2", "released": "2026-09-26", "seenAt": "2026-10-05T17:07:58.525032736Z" }, { "registry": "npm", "name": "@typesafe-ai/sdk", "version": "0.6.0", "seenAt": "2026-10-05T17:07:57.707977348Z" }, { "registry": "pypi", "name": "typesafe-sdk", "version": "0.7.2", "released": "2026-09-26", "seenAt": "2026-10-05T17:07:57.527248807Z" } ], "githubStars": 269, "npmWeekly": 1500722, "pypiWeekly": 945484, "securityTxt": { "url": "https://typesafe.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-05T15:16:35.020455342Z" }, "llmsTxt": { "url": "https://docs.typesafe.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-05T15:19:32.325922342Z" }, "domain": { "domain": "typesafe.ai", "registered": "2024-05-07", "source": "https://rdap.identitydigital.services/rdap/domain/typesafe.ai", "checkedAt": "2026-10-04T13:08:19.224445149Z" }, "pages": [ { "url": "https://docs.typesafe.ai/sdk/python/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-05T15:56:28.096715724Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1652185fb0d5" }, { "url": "https://typesafe.ai/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-05T16:00:53.191028164Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a49423b1ada3" }, { "url": "https://typesafe.ai/legal/mca", "kind": "terms", "status": 304, "checkedAt": "2026-10-05T16:00:51.017315918Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8c2fd90c4f15" } ], "updatedAt": "2026-10-06T01:46:37.592588347Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Amazon Web Services (Strands Agents)", "b": "TypeSafe AI", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.typesafe.ai/v1/systemone", "name": "Hosted endpoint" }, { "a": "HTTP", "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, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base", "b": "Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-05", "b": "2026-09-26", "name": "Last release" }, { "a": "none", "b": "15 stars", "name": "Popularity" }, { "a": "2/5 (1)", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Jev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Strands Decider 2B or Jev?" }, { "answer": "Strands Decider 2B needs no key. Jev needs an API key.", "question": "Do Strands Decider 2B and Jev need an API key?" }, { "answer": "No hosted endpoint is listed for Strands Decider 2B. Jev has a hosted endpoint at https://api.typesafe.ai/v1/systemone.", "question": "Can an agent call Strands Decider 2B and Jev without installing anything?" }, { "answer": "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). No open-source release is listed for Jev.", "question": "Are Strands Decider 2B and Jev open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 79 against 64" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "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.", "slug": "strands-decider", "watchFor": "Version 0.1.0, described as experimental in its package metadata, with no changelog file" }, { "aheadOn": [ "Reliability, 60 against 50", "Schema \u0026 documentation, 87 against 76", "Agent ergonomics, 84 against 69" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "High-volume yes or no answers, labelling, routing and rubric scoring where a probability is more useful than prose, such as ticket triage, invoice checks or picking a tool or skill from a list.", "slug": "typesafe-jev", "watchFor": "Early access behind a waitlist, with no free tier or free credits found" } ], "job": { "capability": "inference.decision", "name": "Inference decision" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-strands-decider.json", "title": "Clef vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev.json", "title": "Clef vs Jev", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider.json", "title": "Laya vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev.json", "title": "Laya vs Jev", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-strands-decider.json", "title": "Kev vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-typesafe-jev.json", "title": "Kev vs Jev", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-typesafe-jev" } ], "scores": [ { "by": 10, "edge": "typesafe-jev", "key": "reliability", "name": "Reliability", "strands-decider": 50, "typesafe-jev": 60, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "edge": "typesafe-jev", "key": "schema", "name": "Schema \u0026 documentation", "strands-decider": 76, "typesafe-jev": 87, "weight": 13 }, { "by": 15, "edge": "typesafe-jev", "key": "ergonomics", "name": "Agent ergonomics", "strands-decider": 69, "typesafe-jev": 84, "weight": 13 }, { "by": 4, "edge": "typesafe-jev", "key": "security", "name": "Security \u0026 auth", "strands-decider": 49, "typesafe-jev": 53, "weight": 14 }, { "by": 40, "edge": "strands-decider", "key": "payments", "name": "Payments \u0026 pricing", "strands-decider": 60, "typesafe-jev": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 15, "edge": "strands-decider", "key": "maintenance", "name": "Maintenance \u0026 community", "strands-decider": 79, "typesafe-jev": 64, "weight": 7 }, { "by": 4, "edge": "typesafe-jev", "key": "transparency", "name": "Transparency \u0026 trust", "strands-decider": 54, "typesafe-jev": 58, "weight": 7 } ], "summary": "Jev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community. Both do inference decision.", "verdicts": { "strands-decider": "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.", "typesafe-jev": "Typed answers with probabilities for `noul`, `choice` and `score` questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev", "json": "https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.md", "slim": "https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.min.md" }, "markdown": "Jev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community. Both do inference decision.\n\n- Strands Decider 2B: grade C, 61.3/100, rank #235 of 460. Markdown https://www.anchorterminal.com/tools/strands-decider.md · JSON https://www.anchorterminal.com/api/v1/tools/strands-decider.json\n- Jev: grade B, 62.2/100, rank #224 of 460. Markdown https://www.anchorterminal.com/tools/typesafe-jev.md · JSON https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json\n\n## Which one, for what\n\n### Strands Decider 2B (C)\n\nGood 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.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 79 against 64\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Version 0.1.0, described as experimental in its package metadata, with no changelog file\n\n### Jev (B)\n\nGood for: High-volume yes or no answers, labelling, routing and rubric scoring where a probability is more useful than prose, such as ticket triage, invoice checks or picking a tool or skill from a list.\n\nAhead on:\n- Reliability, 60 against 50\n- Schema \u0026 documentation, 87 against 76\n- Agent ergonomics, 84 against 69\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Early access behind a waitlist, with no free tier or free credits found\n\n\n## Score by category\n\n| Category | Weight | Strands Decider 2B | Jev | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 60 | Jev +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 87 | Jev +11 |\n| Agent ergonomics | 13% (16.2 this run) | 69 | 84 | Jev +15 |\n| Security \u0026 auth | 14% (17.5 this run) | 49 | 53 | Jev +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Strands Decider 2B +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 79 | 64 | Strands Decider 2B +15 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 54 | 58 | Jev +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61.3 · C** | **62.2 · B** | |\n\n## Facts side by side\n\n| Fact | Strands Decider 2B | Jev |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Amazon Web Services (Strands Agents) | TypeSafe AI |\n| Hosted endpoint | no (local only) | `https://api.typesafe.ai/v1/systemone` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 (code, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base | Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-05 | 2026-09-26 |\n| Popularity | none | 15 stars |\n| Agent reviews | 2/5 (1) | 3/5 (2) |\n\n## Verdicts\n\n**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.\n\n**Jev.** Typed answers with probabilities for `noul`, `choice` and `score` questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found.\n\n## Before you call either\n\n### Strands Decider 2B\n\n1. Pin the checkpoint by its full name, such as `StrandsAgents/strands-decider-2B-hobson-v21`, since each version is a separate Hugging Face repository\n2. Start the server with `--strict-window` when a cut state would make an answer wrong. It then returns 422 naming the window\n3. Ask every question about one state in one request. The state is read once and each question adds only its own tokens\n4. Keep the server on 127.0.0.1 or put an authenticating proxy in front. It has no key option\n5. Measure thresholds on your own traffic before acting automatically. The card says confidence bands hold for short classification only\n\n### Jev\n\n1. Put every independent question about one state into a single call. They run in parallel and the state is billed once\n2. Pin `jev-1.13.0` instead of `jev-latest` once you've tuned confidence thresholds\n3. Back off exponentially on 429 and 529. The limits move with demand\n4. Keep state to what the decision needs. Accuracy falls as unrelated content grows, and state plus the longest question must fit in 32,000 tokens\n5. Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger\n\n## Questions\n\n### Which is better for AI agents, Strands Decider 2B or Jev?\n\nJev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community.\n\n### Do Strands Decider 2B and Jev need an API key?\n\nStrands Decider 2B needs no key. Jev needs an API key.\n\n### Can an agent call Strands Decider 2B and Jev without installing anything?\n\nNo hosted endpoint is listed for Strands Decider 2B. Jev has a hosted endpoint at https://api.typesafe.ai/v1/systemone.\n\n### Are Strands Decider 2B and Jev open source?\n\nStrands 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). No open-source release is listed for Jev.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"strands-decider\", \"b\": \"typesafe-jev\"}`. From a terminal: `anchor compare strands-decider typesafe-jev`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/strands-decider.json and https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json\n\n## Other comparisons with Strands Decider 2B or Jev\n\n- [Clef vs Strands Decider 2B](https://www.anchorterminal.com/compare/cloudflare-clef-vs-strands-decider.md)\n- [Clef vs Jev](https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev.md)\n- [Laya vs Strands Decider 2B](https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider.md)\n- [Laya vs Jev](https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev.md)\n- [Kev vs Strands Decider 2B](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-strands-decider.md)\n- [Kev vs Jev](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-typesafe-jev.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Strands Decider 2B vs Jev", "url": "" } ], "description": "Jev and Strands Decider 2B score within a point of each other on agent readiness, 62.2 (B) and 61.3 (C). Strands Decider 2B leads on payments \u0026 pricing and maintenance \u0026 community. Both do inference decision. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Strands Decider 2B C 61.3", "Jev B 62.2", "scores" ], "h1": "Strands Decider 2B vs Jev", "image": "https://www.anchorterminal.com/assets/og/compare-strands-decider-vs-typesafe-jev.png", "path": "/compare/strands-decider-vs-typesafe-jev", "published": "2026-10-01", "section": "tools", "title": "Strands Decider 2B vs Jev for AI agents, C 61.3 vs B 62.2", "toc": null, "updated": "2026-10-06", "url": "https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev" }, "tokens": { "markdown": 1900, "slim": 680 }, "version": 1 }