{ "data": { "a": { "slug": "amazon-bedrock", "name": "Amazon Bedrock", "vendor": "Amazon Web Services", "vendorUrl": "https://aws.amazon.com/bedrock/", "kind": "model", "category": "inference", "summary": "AWS's managed API for foundation models from Anthropic, OpenAI, Amazon, Meta, Mistral, DeepSeek, Qwen, xAI and others, called through the Converse API or OpenAI- and Anthropic-compatible endpoints under one AWS account.", "url": "https://www.anchorterminal.com/tools/amazon-bedrock", "markdownUrl": "https://www.anchorterminal.com/tools/amazon-bedrock.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/amazon-bedrock.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/amazon-bedrock.json", "dns": "amazon-bedrock.grade.anchorterminal.com", "repo": "https://github.com/aws/api-models-aws", "license": "Proprietary service under the AWS Customer Agreement and Service Terms. Third-party models carry their providers' licence terms. The AWS SDKs and the Smithy service models are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://bedrock-runtime.us-east-1.amazonaws.com", "packages": [ { "registry": "pypi", "name": "boto3" }, { "registry": "npm", "name": "@aws-sdk/client-bedrock-runtime" } ], "auth": "mixed", "authNotes": "AWS Signature Version 4 with IAM users, roles or short-lived STS credentials, and IAM policies that can name single model or inference-profile ARNs. Bedrock API keys go in an `Authorization: Bearer` header. Short-term keys last up to 12 hours and inherit the caller's IAM permissions; long-term keys create an IAM user and are marked for exploration only. Endpoints are regional, `bedrock-runtime.\u003cregion\u003e.amazonaws.com` and `bedrock-mantle.\u003cregion\u003e.api.aws`.", "pricing": "usage", "pricingNotes": "Per-token prices per model and Region, with Standard, Priority, Flex and Reserved tiers. Claude Opus 5.5 costs $4/$20 per million tokens through global cross-Region inference and $4.40/$22 through geographic or in-Region inference, cache reads $0.20. Cache reads on Claude Sonnet 5.5 were cut by half from 7 October 2026. Batch is half price on supported models but was not shown for Opus 5.5 or Sonnet 5.5. New AWS accounts get up to $200 in Free Tier credits (https://aws.amazon.com/bedrock/pricing/, rates per AWS's price feed of 30 September 2026; the page's tables are drawn by script and were not readable on 6 November).", "priceSummary": "from $0.30 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the pricing page or in the user guide's llms.txt (checked 2026-11-06). Access needs an AWS account.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 21825916, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html", "rateLimitsUrl": "https://docs.aws.amazon.com/general/latest/gr/bedrock.html", "llmsTxt": "https://docs.aws.amazon.com/bedrock/latest/userguide/llms.txt", "capabilities": [ "inference.llm", "inference.open-weights" ], "tags": [ "official", "hosted", "model", "open-weights", "enterprise", "usage-priced", "llms-txt", "python", "typescript", "status-page" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 81.7, "grade": "A", "agentReady": true, "rank": 8, "ranked": true, "rankOf": 1486, "categoryRank": 3, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 92, "maintenance": 81, "payments": 30, "reliability": 80, "schema": 94, "security": 98, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Bedrock reaches Claude, GPT-6, Nova, Llama and other families through one IAM-controlled API, with a 99.9 per cent SLA and a per-Region zero-retention switch. Setup needs an AWS account, IAM permissions and a Region, capabilities vary by model, and some Regions gave five older Claude models about 34 days of notice.", "bestFor": "Teams already on AWS who want Claude, GPT-6, Nova, Llama and other models under one IAM, billing and VPC boundary, with regional data controls and an SLA.", "strengths": [ "One API and one bill for Anthropic, OpenAI, Amazon, Meta, Mistral, DeepSeek, Qwen, xAI and other model families", "IAM policies can limit a caller to named model ARNs, and short-term API keys expire within 12 hours", "A `none` data retention mode per Region blocks any model that would store prompts", "Published SLA of 99.9 per cent a month per Region with service credits", "Per-model token quotas published with default values, for example 30,000,000 tokens a minute for Opus 5.5 global inference" ], "weaknesses": [ "An AWS account, IAM setup and a Region choice come before the first call, and an agent can't sign up alone", "Batch inference isn't shown for Claude Opus 5.5 or Sonnet 5.5, and since 26 October batch completion isn't guaranteed", "Claude Fable 5 and 5.1 retain all traffic up to 30 days, and AWS may review flagged prompts", "Five older Claude models went Legacy on 10 or 13 October 2026 with end of life on 13 November in some Regions, against the 6-month floor the policy states", "The Middle East (UAE) and (Bahrain) Regions have been disrupted since March 2026, and AWS says some data there can't be restored" ], "agentNotes": [ "Use the geographic or global inference ID from the model card, such as `global.anthropic.claude-opus-5-5`. Global routing is cheaper but can process data in any commercial Region", "Set `data_retention_mode` to `none` in each Region before sending sensitive data. Models that need retention then return ValidationException", "Back off with jitter on 429 ThrottlingException, 503 and 529 `overloaded_error`, and honour `Retry-After` when it's sent", "Generate short-term API keys from an IAM role for production. Long-term keys create an IAM user and AWS marks them exploration only", "Call ListFoundationModels in your Region and read `modelLifecycle` before pinning a model ID. Claude 3.x IDs in several Regions stop working on 13 November 2026 and requests don't redirect" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 81.7 } ], "editorialScores": { "ergonomics": 92, "maintenance": 81, "payments": 30, "reliability": 80, "schema": 94, "security": 98, "transparency": 76 }, "provenanceScore": 94, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install boto3 # or: npm i @aws-sdk/client-bedrock-runtime", "http": "curl -X POST \"https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-sonnet-4-6/converse\" \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $AWS_BEARER_TOKEN_BEDROCK\" \\\n -d '{\"messages\": [{\"role\": \"user\", \"content\": [{\"text\": \"Hello\"}]}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/amazon-bedrock" }, "sameCompany": [ "amazon-nova-embeddings", "amazon-bedrock-guardrails", "amazon-transcribe", "amazon-polly", "amazon-nova-sonic", "agentcore-memory", "agentcore-identity", "aws-secrets-manager", "agentcore-web-search", "aws-mcp-servers", "amazon-ses", "amazon-location", "amazon-translate", "amazon-ads-api", "amazon-creators-api" ], "area": "models", "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "amazon.com", "domainRegistered": "1994-11-01", "domainNote": "The endpoints are on amazonaws.com and api.aws, both AWS domains. The security.txt on aws.amazon.com had expired on 2026-09-24 and was renewed, with Expires 2027-10-16, when read on 2026-11-06.", "endpointOnVendorDomain": true, "terms": "https://aws.amazon.com/service-terms/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "https://health.aws.amazon.com/health/status", "changelog": "https://docs.aws.amazon.com/bedrock/latest/userguide/doc-history.html", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "AWS's public history feed (historyevents.json) lists Amazon Bedrock as disrupted in the ME-CENTRAL-1 and ME-SOUTH-1 Regions since March 2026, with a last update on 15 September 2026, and no Bedrock event in other Regions in the 90 days to 6 November 2026. An EU-SOUTH-2 packet-loss event on 4 October 2026 named Bedrock AgentCore, not Bedrock.", "The pricing page fills its tables by script. Prices here come from AWS's public price feed of 30 September 2026; the bedrockfoundationmodels feed read on 6 November (published 12 October) carries only rate codes." ], "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/amazon-bedrock.json", "live": { "slug": "amazon-bedrock", "probe": { "target": "https://bedrock-runtime.us-east-1.amazonaws.com", "method": "get", "lastAt": "2026-11-07T18:20:09.570975096Z", "lastOk": true, "lastStatus": 404, "lastMs": 339, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 269, "p95ms24h": 352, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "npm", "name": "@aws-sdk/client-bedrock-runtime", "version": "3.1164.0", "seenAt": "2026-11-06T23:05:19.602032841Z" }, { "registry": "pypi", "name": "boto3", "version": "1.43.126", "released": "2026-11-06", "seenAt": "2026-11-06T23:05:17.831478687Z" } ], "githubStars": 229, "npmWeekly": 21825916, "pypiWeekly": 637851852, "securityTxt": { "url": "https://amazon.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-07T16:00:18.354437696Z" }, "llmsTxt": { "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:17.63045618Z" }, "pages": [ { "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:05:11.906374144Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dce416908c57" } ], "updatedAt": "2026-11-07T18:20:09.570975096Z" } }, "answer": "Amazon Bedrock scores 81.7 (A) on agent readiness against Jais 3's 52.1 (D), and leads in 6 of 7 scored categories. Jais 3 leads on payments \u0026 pricing.", "b": { "slug": "jais-3", "name": "Jais 3", "vendor": "Institute of Foundation Models (MBZUAI) and Inception42", "vendorUrl": "https://ifm.ai/blog/jais3/", "kind": "model", "category": "inference", "summary": "Jais 3 is an open-weight family of Arabic and English reasoning models from MBZUAI's Institute of Foundation Models and Inception42, from 0.9B to 375B parameters with up to 512K tokens of context, released under Apache-2.0 for self-hosting.", "url": "https://www.anchorterminal.com/tools/jais-3", "markdownUrl": "https://www.anchorterminal.com/tools/jais-3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jais-3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jais-3.json", "dns": "jais-3.grade.anchorterminal.com", "repo": "https://huggingface.co/inception42/Jais-3-375B-A23B", "license": "Apache-2.0, declared in the metadata of every model card read. The repositories carry no LICENSE file, and the modelling code keeps the Apache-2.0 header of the Qwen3-MoE code it was generated from", "transports": [ "http" ], "packages": [], "auth": "none", "authNotes": "No account or key. The inception42 and IFM repositories on Hugging Face are not gated and download anonymously. A local server has whatever authentication the owner adds, such as vLLM's `--api-key`. The cards' examples call the local server with `api_key=\"EMPTY\"`.", "pricing": "free", "pricingNotes": "Free to download and run under Apache-2.0, with the owner's GPUs as the cost. No hosted endpoint from IFM or Inception42 was found, and on 4 November 2026 Hugging Face listed no inference provider for any of the six main repositories.", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Jais 3 is a set of weights the owner serves, with no payment route and no hosted API from the makers found (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://huggingface.co/inception42/Jais-3-375B-A23B", "capabilities": [ "inference.llm", "inference.open-weights", "inference.local" ], "tags": [ "model", "open-weights", "self-hosted", "local", "free", "no-card", "apache-2.0", "openai-compatible", "gpu", "apple-silicon", "mlx", "new" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 52.1, "grade": "D", "agentReady": false, "rank": 992, "ranked": true, "rankOf": 1486, "categoryRank": 34, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 62, "payments": 60, "reliability": 48, "schema": 54, "security": 31, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code and no security contact is published.", "bestFor": "An agent or team that needs Arabic and English reasoning and tool use on its own hardware, from a laptop-sized 0.9B to a cluster-sized 375B, under Apache-2.0.", "strengths": [ "Six checkpoints from 0.9B (2.2 GB) to 375B-A23B (758 GB), with FP8, GGUF and MLX builds from IFM", "Apache-2.0 on every card read, ungated downloads, and the CPT, Cooldown, SFT and FTPO training checkpoints published as branches", "With the `k2_horizon` parsers, reasoning returns in `reasoning_content` and tool calls as `tool_calls`, in JSON, XML or typed XML formats", "Launch recipes in the vLLM and SGLang projects' own docs, and K2 Horizon support in llama.cpp's tagged builds since 6 October 2026", "The chat template validates tool schemas and rejects unknown options with named errors, such as an unsupported `reasoning_effort`" ], "weaknesses": [ "Every documented vLLM, SGLang, Transformers and MLX command passes `--trust-remote-code`, so the repository's Python runs on the host", "The 375B-A23B reference deployment is 16 H100 GPUs across two nodes, or one 8-GPU H200 node", "The code repository is marked 'coming soon', and the technical report, blog and press release on ifm.ai sit behind a bot check", "No LICENSE file in the repositories, no changelog, no deprecation policy and no security contact or security.txt found", "Released on 15 October 2026, with template fixes on 14 and 15 October, and mlx-lm v0.32.2 has no K2 Horizon support of its own" ], "agentNotes": [ "Start vLLM or SGLang with `--reasoning-parser k2_horizon`, and add `--tool-call-parser k2_horizon` (vLLM also `--enable-auto-tool-choice`) for tools, or tool calls come back as raw text", "Pass `reasoning_effort` (`high`, `medium` or `low`) and `tool_call_format` inside `chat_template_kwargs`. Other values return a template error", "Send each earlier assistant turn back with `reasoning_content` as a string, even an empty one. A missing or null thinking field makes the template raise an error", "Send your own system message, or set `default_system_prompt` to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras", "Budget at least 32,768 output tokens at `high` effort, which the cards recommend for every request" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.1 } ], "editorialScores": { "ergonomics": 65, "maintenance": 62, "payments": 60, "reliability": 48, "schema": 54, "security": 31, "transparency": 51 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-10-27", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "vllm serve inception42/Jais-3-32B \\\n --trust-remote-code \\\n --dtype bfloat16 \\\n --tensor-parallel-size 2 \\\n --reasoning-parser k2_horizon \\\n --enable-auto-tool-choice \\\n --tool-call-parser k2_horizon", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\n \"model\": \"inception42/Jais-3-32B\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Summarise this contract in Arabic.\"}],\n \"max_tokens\": 32768,\n \"chat_template_kwargs\": {\"reasoning_effort\": \"high\"}\n }'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/jais-3" }, "area": "models", "provenance": { "legalEntity": "Mohamed bin Zayed University of Artificial Intelligence (Institute of Foundation Models), with Inception42 (a G42 company)", "domain": "ifm.ai", "domainRegistered": "2022-09-06", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "The chat template's default system prompt names the Institute of Foundation Models (IFM) at MBZUAI, with Inception42 (a G42 company) and Cerebras, and gives MBZUAI's Arabic name, Mohamed bin Zayed University of Artificial Intelligence. The citation names the IFM, Inception42 and Cerebras teams. No registered company name for Inception42 was read first-hand.", "RDAP gives a registration date of 6 September 2022 for ifm.ai. The weights are on huggingface.co under the inception42 and IFM organisations.", "The licence is Apache-2.0 in each card's metadata. There is no LICENSE file and no terms or privacy document governing the weights, and no input reaches the makers when the owner serves them.", "ifm.ai answered our reader with a Cloudflare bot check on the press release, the blog post and the sitemap, so they weren't read. inceptionai.ai and mbzuai.ac.ae answered with bot or firewall pages too. ifm.ai/.well-known/security.txt returned 404 on 17 October 2026.", "No hosted endpoint, so no status page. No changelog. The Hugging Face commit history is public and was read." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jais-3.json", "live": { "slug": "jais-3", "securityTxt": { "url": "https://ifm.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:26.731681483Z" }, "domain": { "domain": "ifm.ai", "registered": "2022-09-06", "source": "https://rdap.identitydigital.services/rdap/domain/ifm.ai", "checkedAt": "2026-11-01T14:11:01.629779131Z" }, "updatedAt": "2026-11-07T16:01:26.731681483Z" } }, "edges": [ { "by": 67, "category": "security", "leads": "amazon-bedrock", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. IAM with SigV4, roles and STS session credentials, policies down to a model or inference-profile ARN, short-term API keys that expire within 12 hours, long-term keys with expiry and reset, and condition keys that can deny bearer tokens altogether (30). The security page says customer data isn't shared with model providers or used to improve the base models (20). The abuse detection page says Bedrock stores no inputs or outputs by default, and a per-Region `none` mode blocks models that require retention, but Claude Fable 5 and 5.1 keep all traffic up to 30 days and GPT-6 and GPT-5.x keep flagged traffic up to 30 days (13 of 15, a judgement call; Anthropic's own API got 12 for the same Fable exception without an account-level block). CloudTrail logs API calls, and model invocation logging can send prompts and responses to S3 or CloudWatch Logs (15). Bedrock is in ISO, SOC and CSA STAR Level 2 scope, HIPAA eligible and FedRAMP High in GovCloud (US-West) per its security page, with a vulnerability disclosure programme on HackerOne, and the aws.amazon.com security.txt, expired on 6 October, was renewed with Expires 2027-10-16 when read on 6 November (20). Up from 96 on 6 October for that reason.", "b": "Read as software the owner runs. No account or key, ungated downloads, and server authentication is the owner's to add (12 of 30). A model that calls whatever tools the operator wires in. The cards rule high-stakes decisions without human oversight out of scope, but nothing in the model or template enforces approval (6 of 20). The template renders tool results in their own `tool` role, but string results go in as raw text (only non-string content is serialised with `tojson`), no escaping of special-token sequences in caller or tool text was found, and no injection guidance or results are published (4 of 15). No call log of its own. Visibility depends on the serving stack (5 of 15). Every launch command passes `--trust-remote-code`, so `modeling_k2_horizon.py` from the repository runs on the host. We read it and found only torch and transformers imports. No security.txt on ifm.ai (404 on 17 October, not re-read), no security contact on the cards and no safety evaluation found. Since 25 October the cards link a technical report on ifm.ai, which answered a Cloudflare bot check on 4 November, so what it covers is unread (4 of 20). 12 + 6 + 4 + 5 + 4 = 31." }, "scores": { "a": 98, "b": 31 } }, { "by": 40, "category": "schema", "leads": "amazon-bedrock", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading. No OpenAPI, but the bedrock-runtime and bedrock Smithy models are public in aws/api-models-aws with types, required members and enums, counted as for S3 (25). llms.txt for the user guide with about 2,000 lines, each page with a Markdown twin (10). Model cards state context, output limits, endpoints and supported functions per model, and the guide now recommends `bedrock-runtime` for new work, but support for each API, endpoint and feature changes model by model (16 of 20). Structured outputs compile JSON Schema to a grammar, with `minimum`, `maximum` and string lengths supported, though some inference profiles don't support it, such as Haiku 4.5 through the India profile (13 of 15). Every operation lists typed errors with HTTP codes and links to a troubleshooting page with causes and fixes, and examples run through the guide (15). API version 2023-09-30 and a dated document history with an RSS feed, newest entry 30 October 2026, with structured outputs for Claude on both endpoints added on 18 October (15).", "b": "Read for a model the owner serves. No specification of its own. The contract is the Jinja chat template, which validates tool JSON Schemas (required fields must exist in properties) and rejects unknown options, plus the OpenAI-compatible servers in vLLM and SGLang with the `k2_horizon` parsers (10 of 25). The cards are Markdown on Hugging Face, and SGLang's docs have an llms.txt, but no llms.txt or Markdown docs from IFM were found and ifm.ai couldn't be read (5 of 10). Each card states intended use, four out-of-scope uses, limitations and per-size serving advice (15 of 20). `reasoning_effort` and `tool_call_format` are enums enforced with errors, and tools take JSON Schema. The 375B card describes `low` as no reasoning and omits `medium`, which the template accepts, and structured output isn't documented (10 of 15). Python examples for a reasoning call and a tool loop, commands for five runtimes, and named template errors, but no error reference for a served model (11 of 15). No changelog or version scheme. Training-stage branches and public commit history (3 of 15). 10 + 5 + 15 + 10 + 11 + 3 = 54." }, "scores": { "a": 94, "b": 54 } }, { "by": 32, "category": "reliability", "leads": "amazon-bedrock", "name": "Reliability", "reasons": { "a": "AWS Health Dashboard with per-service, per-Region feeds and a public history file (20). The history lists Amazon Bedrock as disrupted in ME-CENTRAL-1 (UAE) and ME-SOUTH-1 (Bahrain) since March 2026, where AWS said on 15 September 2026 (still inside the 90-day window on 6 November) that it can't restore resources held only there. No other Bedrock event appears in the history in the 90 days to 6 November; an EU-SOUTH-2 packet-loss event on 4 October named Bedrock AgentCore, not Bedrock. This counts as one major event (10). StatusGator's third-party mirror shows 'Increased Error Rates' warnings on 24, 26 and 27 August and 10 September that we couldn't find in AWS's own history, so we didn't score them. Per-model token quotas with default values in the AWS General Reference, such as 30,000,000 tokens a minute for Opus 5.5 global inference (15). The error guide gives exponential backoff with jitter for 429, 503 and 529 and says to honour `Retry-After`, and the SDKs retry ModelNotReadyException up to five times (15). SLA of 99.9 per cent a month per Region for the model APIs, last updated 4 October 2023 (10). Converse and the current Claude, GPT-6 and Nova 2 Lite models are GA (10).", "b": "Read with the local-software lines, since the owner serves the weights. Ungated weights on Hugging Face with stated runtimes (vLLM 0.30.0 or later, SGLang 0.5.20 or later, Transformers validated at 5.15.0, mlx-lm with shipped model code), but every launch command trusts remote code. The GGUF card still says to build llama.cpp from master or wait for a release, though llama.cpp's own tags carry K2 Horizon support from b11454 (6 October 2026) (16 of 20, held). No CI or test suite of the makers' was found, and the code repository is 'coming soon'. SGLang's cookbook reports a validation pass of the tool-call parser on all six checkpoints, and IFM's MLX cards describe conversion checks against the PyTorch code (3 of 25). No crash reports. On 4 November the six main repositories held seven discussions, six of them closed citation updates and one open MoVA-36B-A4B thread from 26 October with no reply yet. Two template fixes for OpenAI-style message history landed on 14 October, before the launch (15 of 25). No changelog or version tags, only public commit messages (2 of 15). Released as named final checkpoints with no preview label, though mlx-lm v0.32.2 still has no K2 Horizon model code of its own (12 of 15). 16 + 3 + 15 + 2 + 12 = 48." }, "scores": { "a": 80, "b": 48 } }, { "by": 30, "category": "payments", "leads": "jais-3", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-token prices per model, tier and Region on the public pricing page, filled from AWS's public price feed (20). New accounts get up to $200 in Free Tier credits and the Free Tier page lists Bedrock among eligible services, and the Free Tier FAQ says most new customers don't need a payment method, but AWS may still ask for one, so half, as for S3 (10). A person signs up for AWS in a browser and sets up IAM before any key exists (0).", "b": "Self-hosted rule. Apache-2.0 weights with nothing to buy and no hosted option from the makers (20). Free to run with no card (20). Downloads are ungated and anonymous, so an agent can fetch the weights with no sign-up (20). No payment protocol (0). 20 + 20 + 20 + 0 = 60." }, "scores": { "a": 30, "b": 60 } }, { "by": 30, "category": "transparency", "leads": "amazon-bedrock", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the AWS Customer Agreement and Service Terms, with the SDKs and Smithy models under Apache-2.0 (18, as for S3). The data retention, abuse detection and security pages agree that Bedrock stores nothing by default, name the models that retain traffic and for how long, and say retained data isn't shared with providers. The retention page's `default` mode says AWS 'may retain the data for safety and abuse-prevention purposes' without a period, and a legacy `provider_data_share` mode is kept though sharing isn't supported (25 of 30). A written lifecycle policy with Legacy and EOL dates per model, but the legacy table's 34-day Legacy periods for five Claude models in some Regions contradict its own 6-month floor (15 of 20, down from 18). AWS's sub-processor list, per the 4 October S3 check, and per-Region, geographic and global inference options, with global routing able to process data in any commercial Region (18 of 20).", "b": "Apache-2.0 in every card's metadata, with staged training checkpoints as branches and training logs linked on Weights \u0026 Biases (not opened). There is no LICENSE file and the code repository is still 'coming soon'. A technical report is linked from 25 October but sits behind a bot check, so its data description is unread (24 of 30). Inputs stay on the owner's hardware because nothing is hosted, but no statement says so and no privacy document governs the weights (15 of 30). No deprecation policy, dated notices or version scheme (0 of 20). Safetensors weights carry no code, and the remote modelling and configuration code we read imports only torch, transformers and huggingface_hub, with no network calls. No telemetry statement (12 of 20). 24 + 15 + 0 + 12 = 51." }, "scores": { "a": 85, "b": 55 } }, { "by": 27, "category": "ergonomics", "leads": "amazon-bedrock", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Converse takes tools with `toolChoice` auto, any or a named tool and `strict: true`, but forced choice depends on the model behind it (17 of 20). Structured outputs on supported models only (13 of 15). Explicit and implicit prompt caching, cache reads at $0.20 per million on Opus 5.5, 0.05x input, with 5-minute and 1-hour TTLs (15). 1M-token context on Opus 5.5, Sonnet 5.5 and Nova 2 Lite, a judgement call since Bedrock has no default model (15). Batch at half price on supported models, but the pricing page shows none for Opus 5.5 or Sonnet 5.5, while Flex is half price on Nova (7 of 10). AWS SDKs in every major language plus token generators for Python, JavaScript and Java (10). Typed errors with recovery advice per code (15).", "b": "Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools come back as `tool_calls` in three selectable wire formats, with a multi-turn loop example. Forced `tool_choice` and parallel calls aren't documented (15 of 20). JSON mode and schemas only through each runtime's guided decoding, not documented by the makers (5 of 15). Prefix caching is the runtime's, and SGLang's page covers HiCache (7 of 10). 524,288 tokens on five of six models, 131,072 on the 0.9B (14 of 15). Uno adapters claim 2.15 times faster decoding for 0.9B to 32B but need IFM's own engine. SGLang lists n-gram speculative decoding and PD disaggregation. No batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, and the 0.9B to 7B fit one GPU. But the cards ask for high effort and 32,768 output tokens on every request, the template inserts an identity system prompt when none is sent, and earlier assistant turns must carry a string thinking field (8 of 15). The template raises named errors for bad options, string-encoded tool arguments and malformed schemas. Server errors are the runtime's (9 of 15). 15 + 5 + 7 + 14 + 7 + 8 + 9 = 65." }, "scores": { "a": 92, "b": 65 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Amazon Web Services", "b": "Institute of Foundation Models (MBZUAI) and Inception42", "name": "Vendor" }, { "a": "https://bedrock-runtime.us-east-1.amazonaws.com", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the AWS Customer Agreement and Service Terms. Third-party models carry their providers' licence terms. The AWS SDKs and the Smithy service models are Apache-2.0", "b": "Apache-2.0, declared in the metadata of every model card read. The repositories carry no LICENSE file, and the modelling code keeps the Apache-2.0 header of the Qwen3-MoE code it was generated from", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-15", "name": "Last release" }, { "a": "2026-10-01", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-05-18", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "21.8M npm/wk", "b": "none", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Amazon Bedrock scores 81.7 (A) on agent readiness against Jais 3's 52.1 (D), and leads in 6 of 7 scored categories. Jais 3 leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Amazon Bedrock or Jais 3?" }, { "answer": "Amazon Bedrock takes an API key or an OAuth sign-in. Jais 3 needs no key.", "question": "Do Amazon Bedrock and Jais 3 need an API key?" }, { "answer": "Amazon Bedrock has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com. No hosted endpoint is listed for Jais 3.", "question": "Can an agent call Amazon Bedrock and Jais 3 without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 80 against 48", "Schema \u0026 documentation, 94 against 54", "Agent ergonomics, 92 against 65", "Security \u0026 auth, 98 against 31", "Maintenance \u0026 community, 81 against 62", "Transparency \u0026 trust, 85 against 55" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install" ], "goodFor": "Teams already on AWS who want Claude, GPT-6, Nova, Llama and other models under one IAM, billing and VPC boundary, with regional data controls and an SLA.", "slug": "amazon-bedrock", "watchFor": "An AWS account, IAM setup and a Region choice come before the first call, and an agent can't sign up alone" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 30" ], "also": [ "No key needed to call it", "Free to start without a card" ], "goodFor": "An agent or team that needs Arabic and English reasoning and tool use on its own hardware, from a laptop-sized 0.9B to a cluster-sized 375B, under Apache-2.0.", "slug": "jais-3", "watchFor": "Every documented vLLM, SGLang, Transformers and MLX command passes `--trust-remote-code`, so the repository's Python runs on the host" } ], "history": { "amazon-bedrock": null, "jais-3": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.4, "from": 51.7, "fromGrade": "D", "to": 52.1, "toGrade": "D" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-anthropic-api.json", "title": "Amazon Bedrock vs Claude API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-anthropic-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-antseed.json", "title": "Amazon Bedrock vs Antseed", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-antseed" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai.json", "title": "Amazon Bedrock vs Azure OpenAI in Foundry Models", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-blockrun-ai.json", "title": "Amazon Bedrock vs BlockRun.AI", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-blockrun-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cerebras-inference.json", "title": "Amazon Bedrock vs Cerebras Inference", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cerebras-inference" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway.json", "title": "Amazon Bedrock vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-workers-ai.json", "title": "Amazon Bedrock vs Cloudflare Workers AI", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-workers-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.json", "title": "Amazon Bedrock vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepinfra.json", "title": "Amazon Bedrock vs DeepInfra", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepinfra" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepseek-api.json", "title": "Amazon Bedrock vs DeepSeek API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepseek-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-eden-ai.json", "title": "Amazon Bedrock vs Eden AI", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-eden-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-elorian-glimpse.json", "title": "Amazon Bedrock vs Glimpse", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-elorian-glimpse" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference.json", "title": "Amazon Bedrock vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-api.json", "title": "Amazon Bedrock vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-groq.json", "title": "Amazon Bedrock vs GroqCloud", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers.json", "title": "Amazon Bedrock vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-inkling-2-small.json", "title": "Amazon Bedrock vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-meta-model-api.json", "title": "Amazon Bedrock vs Meta Model API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-minimax-api.json", "title": "Amazon Bedrock vs MiniMax API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api.json", "title": "Amazon Bedrock vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open.json", "title": "Amazon Bedrock vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.json", "title": "Amazon Bedrock vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-novita-ai.json", "title": "Amazon Bedrock vs Novita AI", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-openai-api.json", "title": "Amazon Bedrock vs OpenAI API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-openrouter.json", "title": "Amazon Bedrock vs OpenRouter", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-prism-inference.json", "title": "Amazon Bedrock vs Prism Inference", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-ramp-router.json", "title": "Amazon Bedrock vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-reflection-beam.json", "title": "Amazon Bedrock vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-routerplus.json", "title": "Amazon Bedrock vs RouterPlus", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-sambanova.json", "title": "Amazon Bedrock vs SambaCloud", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-siliconflow.json", "title": "Amazon Bedrock vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-simplismart.json", "title": "Amazon Bedrock vs Simplismart", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api.json", "title": "Amazon Bedrock vs StepFun API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash.json", "title": "Amazon Bedrock vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-tencent-tokenhub.json", "title": "Amazon Bedrock vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-together-inference.json", "title": "Amazon Bedrock vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway.json", "title": "Amazon Bedrock vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vertex-ai.json", "title": "Amazon Bedrock vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api.json", "title": "Amazon Bedrock vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3.json", "title": "Claude API vs Jais 3", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-jais-3.json", "title": "Antseed vs Jais 3", "url": "https://www.anchorterminal.com/compare/antseed-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-jais-3.json", "title": "Azure OpenAI in Foundry Models vs Jais 3", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-jais-3.json", "title": "BlockRun.AI vs Jais 3", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-jais-3.json", "title": "Cerebras Inference vs Jais 3", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3.json", "title": "Cloudflare AI Gateway vs Jais 3", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-jais-3.json", "title": "Cloudflare Workers AI vs Jais 3", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3.json", "title": "Cohere Chat API (Command models) vs Jais 3", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-jais-3.json", "title": "DeepInfra vs Jais 3", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-jais-3.json", "title": "DeepSeek API vs Jais 3", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-jais-3.json", "title": "Eden AI vs Jais 3", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-jais-3.json", "title": "Glimpse vs Jais 3", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3.json", "title": "Fireworks AI Inference vs Jais 3", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-jais-3.json", "title": "Gemini Developer API vs Jais 3", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-jais-3.json", "title": "GroqCloud vs Jais 3", "url": "https://www.anchorterminal.com/compare/groq-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3.json", "title": "Hugging Face Inference Providers vs Jais 3", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3.json", "title": "Inkling 2 Small vs Jais 3", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api.json", "title": "Jais 3 vs Meta Model API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-minimax-api.json", "title": "Jais 3 vs MiniMax API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-mistral-api.json", "title": "Jais 3 vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open.json", "title": "Jais 3 vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.json", "title": "Jais 3 vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-novita-ai.json", "title": "Jais 3 vs Novita AI", "url": "https://www.anchorterminal.com/compare/jais-3-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-openai-api.json", "title": "Jais 3 vs OpenAI API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-openrouter.json", "title": "Jais 3 vs OpenRouter", "url": "https://www.anchorterminal.com/compare/jais-3-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-prism-inference.json", "title": "Jais 3 vs Prism Inference", "url": "https://www.anchorterminal.com/compare/jais-3-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-ramp-router.json", "title": "Jais 3 vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/jais-3-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-reflection-beam.json", "title": "Jais 3 vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/jais-3-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-routerplus.json", "title": "Jais 3 vs RouterPlus", "url": "https://www.anchorterminal.com/compare/jais-3-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-sambanova.json", "title": "Jais 3 vs SambaCloud", "url": "https://www.anchorterminal.com/compare/jais-3-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-siliconflow.json", "title": "Jais 3 vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/jais-3-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-simplismart.json", "title": "Jais 3 vs Simplismart", "url": "https://www.anchorterminal.com/compare/jais-3-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api.json", "title": "Jais 3 vs StepFun API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash.json", "title": "Jais 3 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.json", "title": "Jais 3 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-together-inference.json", "title": "Jais 3 vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/jais-3-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway.json", "title": "Jais 3 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-vertex-ai.json", "title": "Jais 3 vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/jais-3-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-xai-api.json", "title": "Jais 3 vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/jais-3-vs-xai-api" } ], "panel": null, "scores": [ { "amazon-bedrock": 80, "by": 32, "edge": "amazon-bedrock", "jais-3": 48, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "amazon-bedrock": 94, "by": 40, "edge": "amazon-bedrock", "jais-3": 54, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "amazon-bedrock": 92, "by": 27, "edge": "amazon-bedrock", "jais-3": 65, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "amazon-bedrock": 98, "by": 67, "edge": "amazon-bedrock", "jais-3": 31, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "amazon-bedrock": 30, "by": 30, "edge": "jais-3", "jais-3": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "amazon-bedrock": 81, "by": 19, "edge": "amazon-bedrock", "jais-3": 62, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "amazon-bedrock": 85, "by": 30, "edge": "amazon-bedrock", "jais-3": 55, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Amazon Bedrock scores 81.7 (A) on agent readiness against Jais 3's 52.1 (D), and leads in 6 of 7 scored categories. Jais 3 leads on payments \u0026 pricing. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "amazon-bedrock": "Bedrock reaches Claude, GPT-6, Nova, Llama and other families through one IAM-controlled API, with a 99.9 per cent SLA and a per-Region zero-retention switch. Setup needs an AWS account, IAM permissions and a Region, capabilities vary by model, and some Regions gave five older Claude models about 34 days of notice.", "jais-3": "Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code and no security contact is published." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3", "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3.min.md" }, "markdown": "Amazon Bedrock scores 81.7 (A) on agent readiness against Jais 3's 52.1 (D), and leads in 6 of 7 scored categories. Jais 3 leads on payments \u0026 pricing. Both do llm inference.\n\n- Amazon Bedrock: grade A, 81.7/100, rank #8 of 1486. Markdown https://www.anchorterminal.com/tools/amazon-bedrock.md · JSON https://www.anchorterminal.com/api/v1/tools/amazon-bedrock.json\n- Jais 3: grade D, 52.1/100, rank #992 of 1486. Markdown https://www.anchorterminal.com/tools/jais-3.md · JSON https://www.anchorterminal.com/api/v1/tools/jais-3.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 830 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Amazon Bedrock (A)\n\nGood for: Teams already on AWS who want Claude, GPT-6, Nova, Llama and other models under one IAM, billing and VPC boundary, with regional data controls and an SLA.\n\nAhead on:\n- Reliability, 80 against 48\n- Schema \u0026 documentation, 94 against 54\n- Agent ergonomics, 92 against 65\n- Security \u0026 auth, 98 against 31\n- Maintenance \u0026 community, 81 against 62\n- Transparency \u0026 trust, 85 against 55\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: An AWS account, IAM setup and a Region choice come before the first call, and an agent can't sign up alone\n\n### Jais 3 (D)\n\nGood for: An agent or team that needs Arabic and English reasoning and tool use on its own hardware, from a laptop-sized 0.9B to a cluster-sized 375B, under Apache-2.0.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 30\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n\nWatch for: Every documented vLLM, SGLang, Transformers and MLX command passes `--trust-remote-code`, so the repository's Python runs on the host\n\n\n## Why the edge\n\n### Security \u0026 auth: Amazon Bedrock +67\n\n- Amazon Bedrock (98): Model reading. IAM with SigV4, roles and STS session credentials, policies down to a model or inference-profile ARN, short-term API keys that expire within 12 hours, long-term keys with expiry and reset, and condition keys that can deny bearer tokens altogether (30). The security page says customer data isn't shared with model providers or used to improve the base models (20). The abuse detection page says Bedrock stores no inputs or outputs by default, and a per-Region `none` mode blocks models that require retention, but Claude Fable 5 and 5.1 keep all traffic up to 30 days and GPT-6 and GPT-5.x keep flagged traffic up to 30 days (13 of 15, a judgement call; Anthropic's own API got 12 for the same Fable exception without an account-level block). CloudTrail logs API calls, and model invocation logging can send prompts and responses to S3 or CloudWatch Logs (15). Bedrock is in ISO, SOC and CSA STAR Level 2 scope, HIPAA eligible and FedRAMP High in GovCloud (US-West) per its security page, with a vulnerability disclosure programme on HackerOne, and the aws.amazon.com security.txt, expired on 6 October, was renewed with Expires 2027-10-16 when read on 6 November (20). Up from 96 on 6 October for that reason.\n- Jais 3 (31): Read as software the owner runs. No account or key, ungated downloads, and server authentication is the owner's to add (12 of 30). A model that calls whatever tools the operator wires in. The cards rule high-stakes decisions without human oversight out of scope, but nothing in the model or template enforces approval (6 of 20). The template renders tool results in their own `tool` role, but string results go in as raw text (only non-string content is serialised with `tojson`), no escaping of special-token sequences in caller or tool text was found, and no injection guidance or results are published (4 of 15). No call log of its own. Visibility depends on the serving stack (5 of 15). Every launch command passes `--trust-remote-code`, so `modeling_k2_horizon.py` from the repository runs on the host. We read it and found only torch and transformers imports. No security.txt on ifm.ai (404 on 17 October, not re-read), no security contact on the cards and no safety evaluation found. Since 25 October the cards link a technical report on ifm.ai, which answered a Cloudflare bot check on 4 November, so what it covers is unread (4 of 20). 12 + 6 + 4 + 5 + 4 = 31.\n\n### Schema \u0026 documentation: Amazon Bedrock +40\n\n- Amazon Bedrock (94): Model reading. No OpenAPI, but the bedrock-runtime and bedrock Smithy models are public in aws/api-models-aws with types, required members and enums, counted as for S3 (25). llms.txt for the user guide with about 2,000 lines, each page with a Markdown twin (10). Model cards state context, output limits, endpoints and supported functions per model, and the guide now recommends `bedrock-runtime` for new work, but support for each API, endpoint and feature changes model by model (16 of 20). Structured outputs compile JSON Schema to a grammar, with `minimum`, `maximum` and string lengths supported, though some inference profiles don't support it, such as Haiku 4.5 through the India profile (13 of 15). Every operation lists typed errors with HTTP codes and links to a troubleshooting page with causes and fixes, and examples run through the guide (15). API version 2023-09-30 and a dated document history with an RSS feed, newest entry 30 October 2026, with structured outputs for Claude on both endpoints added on 18 October (15).\n- Jais 3 (54): Read for a model the owner serves. No specification of its own. The contract is the Jinja chat template, which validates tool JSON Schemas (required fields must exist in properties) and rejects unknown options, plus the OpenAI-compatible servers in vLLM and SGLang with the `k2_horizon` parsers (10 of 25). The cards are Markdown on Hugging Face, and SGLang's docs have an llms.txt, but no llms.txt or Markdown docs from IFM were found and ifm.ai couldn't be read (5 of 10). Each card states intended use, four out-of-scope uses, limitations and per-size serving advice (15 of 20). `reasoning_effort` and `tool_call_format` are enums enforced with errors, and tools take JSON Schema. The 375B card describes `low` as no reasoning and omits `medium`, which the template accepts, and structured output isn't documented (10 of 15). Python examples for a reasoning call and a tool loop, commands for five runtimes, and named template errors, but no error reference for a served model (11 of 15). No changelog or version scheme. Training-stage branches and public commit history (3 of 15). 10 + 5 + 15 + 10 + 11 + 3 = 54.\n\n### Reliability: Amazon Bedrock +32\n\n- Amazon Bedrock (80): AWS Health Dashboard with per-service, per-Region feeds and a public history file (20). The history lists Amazon Bedrock as disrupted in ME-CENTRAL-1 (UAE) and ME-SOUTH-1 (Bahrain) since March 2026, where AWS said on 15 September 2026 (still inside the 90-day window on 6 November) that it can't restore resources held only there. No other Bedrock event appears in the history in the 90 days to 6 November; an EU-SOUTH-2 packet-loss event on 4 October named Bedrock AgentCore, not Bedrock. This counts as one major event (10). StatusGator's third-party mirror shows 'Increased Error Rates' warnings on 24, 26 and 27 August and 10 September that we couldn't find in AWS's own history, so we didn't score them. Per-model token quotas with default values in the AWS General Reference, such as 30,000,000 tokens a minute for Opus 5.5 global inference (15). The error guide gives exponential backoff with jitter for 429, 503 and 529 and says to honour `Retry-After`, and the SDKs retry ModelNotReadyException up to five times (15). SLA of 99.9 per cent a month per Region for the model APIs, last updated 4 October 2023 (10). Converse and the current Claude, GPT-6 and Nova 2 Lite models are GA (10).\n- Jais 3 (48): Read with the local-software lines, since the owner serves the weights. Ungated weights on Hugging Face with stated runtimes (vLLM 0.30.0 or later, SGLang 0.5.20 or later, Transformers validated at 5.15.0, mlx-lm with shipped model code), but every launch command trusts remote code. The GGUF card still says to build llama.cpp from master or wait for a release, though llama.cpp's own tags carry K2 Horizon support from b11454 (6 October 2026) (16 of 20, held). No CI or test suite of the makers' was found, and the code repository is 'coming soon'. SGLang's cookbook reports a validation pass of the tool-call parser on all six checkpoints, and IFM's MLX cards describe conversion checks against the PyTorch code (3 of 25). No crash reports. On 4 November the six main repositories held seven discussions, six of them closed citation updates and one open MoVA-36B-A4B thread from 26 October with no reply yet. Two template fixes for OpenAI-style message history landed on 14 October, before the launch (15 of 25). No changelog or version tags, only public commit messages (2 of 15). Released as named final checkpoints with no preview label, though mlx-lm v0.32.2 still has no K2 Horizon model code of its own (12 of 15). 16 + 3 + 15 + 2 + 12 = 48.\n\n### Payments \u0026 pricing: Jais 3 +30\n\n- Amazon Bedrock (30): No x402, MPP or L402 (0). Per-token prices per model, tier and Region on the public pricing page, filled from AWS's public price feed (20). New accounts get up to $200 in Free Tier credits and the Free Tier page lists Bedrock among eligible services, and the Free Tier FAQ says most new customers don't need a payment method, but AWS may still ask for one, so half, as for S3 (10). A person signs up for AWS in a browser and sets up IAM before any key exists (0).\n- Jais 3 (60): Self-hosted rule. Apache-2.0 weights with nothing to buy and no hosted option from the makers (20). Free to run with no card (20). Downloads are ungated and anonymous, so an agent can fetch the weights with no sign-up (20). No payment protocol (0). 20 + 20 + 20 + 0 = 60.\n\n### Transparency \u0026 trust: Amazon Bedrock +30\n\n- Amazon Bedrock (85): Closed service under the AWS Customer Agreement and Service Terms, with the SDKs and Smithy models under Apache-2.0 (18, as for S3). The data retention, abuse detection and security pages agree that Bedrock stores nothing by default, name the models that retain traffic and for how long, and say retained data isn't shared with providers. The retention page's `default` mode says AWS 'may retain the data for safety and abuse-prevention purposes' without a period, and a legacy `provider_data_share` mode is kept though sharing isn't supported (25 of 30). A written lifecycle policy with Legacy and EOL dates per model, but the legacy table's 34-day Legacy periods for five Claude models in some Regions contradict its own 6-month floor (15 of 20, down from 18). AWS's sub-processor list, per the 4 October S3 check, and per-Region, geographic and global inference options, with global routing able to process data in any commercial Region (18 of 20).\n- Jais 3 (55): Apache-2.0 in every card's metadata, with staged training checkpoints as branches and training logs linked on Weights \u0026 Biases (not opened). There is no LICENSE file and the code repository is still 'coming soon'. A technical report is linked from 25 October but sits behind a bot check, so its data description is unread (24 of 30). Inputs stay on the owner's hardware because nothing is hosted, but no statement says so and no privacy document governs the weights (15 of 30). No deprecation policy, dated notices or version scheme (0 of 20). Safetensors weights carry no code, and the remote modelling and configuration code we read imports only torch, transformers and huggingface_hub, with no network calls. No telemetry statement (12 of 20). 24 + 15 + 0 + 12 = 51.\n\n### Agent ergonomics: Amazon Bedrock +27\n\n- Amazon Bedrock (92): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Converse takes tools with `toolChoice` auto, any or a named tool and `strict: true`, but forced choice depends on the model behind it (17 of 20). Structured outputs on supported models only (13 of 15). Explicit and implicit prompt caching, cache reads at $0.20 per million on Opus 5.5, 0.05x input, with 5-minute and 1-hour TTLs (15). 1M-token context on Opus 5.5, Sonnet 5.5 and Nova 2 Lite, a judgement call since Bedrock has no default model (15). Batch at half price on supported models, but the pricing page shows none for Opus 5.5 or Sonnet 5.5, while Flex is half price on Nova (7 of 10). AWS SDKs in every major language plus token generators for Python, JavaScript and Java (10). Typed errors with recovery advice per code (15).\n- Jais 3 (65): Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools come back as `tool_calls` in three selectable wire formats, with a multi-turn loop example. Forced `tool_choice` and parallel calls aren't documented (15 of 20). JSON mode and schemas only through each runtime's guided decoding, not documented by the makers (5 of 15). Prefix caching is the runtime's, and SGLang's page covers HiCache (7 of 10). 524,288 tokens on five of six models, 131,072 on the 0.9B (14 of 15). Uno adapters claim 2.15 times faster decoding for 0.9B to 32B but need IFM's own engine. SGLang lists n-gram speculative decoding and PD disaggregation. No batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, and the 0.9B to 7B fit one GPU. But the cards ask for high effort and 32,768 output tokens on every request, the template inserts an identity system prompt when none is sent, and earlier assistant turns must carry a string thinking field (8 of 15). The template raises named errors for bad options, string-encoded tool arguments and malformed schemas. Server errors are the runtime's (9 of 15). 15 + 5 + 7 + 14 + 7 + 8 + 9 = 65.\n\n## Score by category\n\n| Category | Weight | Amazon Bedrock | Jais 3 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 48 | Amazon Bedrock +32 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 94 | 54 | Amazon Bedrock +40 |\n| Agent ergonomics | 13% (16.2 this run) | 92 | 65 | Amazon Bedrock +27 |\n| Security \u0026 auth | 14% (17.5 this run) | 98 | 31 | Amazon Bedrock +67 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | Jais 3 +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 81 | 62 | Amazon Bedrock +19 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 85 | 55 | Amazon Bedrock +30 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **81.7 · A** | **52.1 · D** | |\n\n## Facts side by side\n\n| Fact | Amazon Bedrock | Jais 3 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Amazon Web Services | Institute of Foundation Models (MBZUAI) and Inception42 |\n| Hosted endpoint | `https://bedrock-runtime.us-east-1.amazonaws.com` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Customer Agreement and Service Terms. Third-party models carry their providers' licence terms. The AWS SDKs and the Smithy service models are Apache-2.0 | Apache-2.0, declared in the metadata of every model card read. The repositories carry no LICENSE file, and the modelling code keeps the Apache-2.0 header of the Qwen3-MoE code it was generated from |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-30 | 2026-10-15 |\n| Terms last updated | 2026-10-01 | no document linked |\n| Privacy policy last updated | 2026-05-18 | no document linked |\n| Customer content may train models | yes, with an opt-out | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | 21.8M npm/wk | none |\n| Agent reviews | none | 2.5/5 (4) |\n\n## How the scores have moved\n\n### Amazon Bedrock\n\nNo score change since it was listed.\n\n### Jais 3\n\n- +0.4 on 27 October 2026: checklist\n\n## Verdicts\n\n**Amazon Bedrock.** Bedrock reaches Claude, GPT-6, Nova, Llama and other families through one IAM-controlled API, with a 99.9 per cent SLA and a per-Region zero-retention switch. Setup needs an AWS account, IAM permissions and a Region, capabilities vary by model, and some Regions gave five older Claude models about 34 days of notice.\n\n**Jais 3.** Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code and no security contact is published.\n\n## Before you call either\n\n### Amazon Bedrock\n\n1. Use the geographic or global inference ID from the model card, such as `global.anthropic.claude-opus-5-5`. Global routing is cheaper but can process data in any commercial Region\n2. Set `data_retention_mode` to `none` in each Region before sending sensitive data. Models that need retention then return ValidationException\n3. Back off with jitter on 429 ThrottlingException, 503 and 529 `overloaded_error`, and honour `Retry-After` when it's sent\n4. Generate short-term API keys from an IAM role for production. Long-term keys create an IAM user and AWS marks them exploration only\n5. Call ListFoundationModels in your Region and read `modelLifecycle` before pinning a model ID. Claude 3.x IDs in several Regions stop working on 13 November 2026 and requests don't redirect\n\n### Jais 3\n\n1. Start vLLM or SGLang with `--reasoning-parser k2_horizon`, and add `--tool-call-parser k2_horizon` (vLLM also `--enable-auto-tool-choice`) for tools, or tool calls come back as raw text\n2. Pass `reasoning_effort` (`high`, `medium` or `low`) and `tool_call_format` inside `chat_template_kwargs`. Other values return a template error\n3. Send each earlier assistant turn back with `reasoning_content` as a string, even an empty one. A missing or null thinking field makes the template raise an error\n4. Send your own system message, or set `default_system_prompt` to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras\n5. Budget at least 32,768 output tokens at `high` effort, which the cards recommend for every request\n\n## Questions\n\n### Which is better for AI agents, Amazon Bedrock or Jais 3?\n\nAmazon Bedrock scores 81.7 (A) on agent readiness against Jais 3's 52.1 (D), and leads in 6 of 7 scored categories. Jais 3 leads on payments \u0026 pricing.\n\n### Do Amazon Bedrock and Jais 3 need an API key?\n\nAmazon Bedrock takes an API key or an OAuth sign-in. Jais 3 needs no key.\n\n### Can an agent call Amazon Bedrock and Jais 3 without installing anything?\n\nAmazon Bedrock has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com. No hosted endpoint is listed for Jais 3.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"amazon-bedrock\", \"b\": \"jais-3\"}`. From a terminal: `anchor compare amazon-bedrock jais-3`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amazon-bedrock.json and https://www.anchorterminal.com/api/v1/tools/jais-3.json\n\n## Other comparisons with Amazon Bedrock or Jais 3\n\n- [Amazon Bedrock vs Claude API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-anthropic-api.md)\n- [Amazon Bedrock vs Antseed](https://www.anchorterminal.com/compare/amazon-bedrock-vs-antseed.md)\n- [Amazon Bedrock vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai.md)\n- [Amazon Bedrock vs BlockRun.AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-blockrun-ai.md)\n- [Amazon Bedrock vs Cerebras Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cerebras-inference.md)\n- [Amazon Bedrock vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway.md)\n- [Amazon Bedrock vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-workers-ai.md)\n- [Amazon Bedrock vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.md)\n- [Amazon Bedrock vs DeepInfra](https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepinfra.md)\n- [Amazon Bedrock vs DeepSeek API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-deepseek-api.md)\n- [Amazon Bedrock vs Eden AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-eden-ai.md)\n- [Amazon Bedrock vs Glimpse](https://www.anchorterminal.com/compare/amazon-bedrock-vs-elorian-glimpse.md)\n- [Amazon Bedrock vs Fireworks AI Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference.md)\n- [Amazon Bedrock vs Gemini Developer API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-api.md)\n- [Amazon Bedrock vs GroqCloud](https://www.anchorterminal.com/compare/amazon-bedrock-vs-groq.md)\n- [Amazon Bedrock vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers.md)\n- [Amazon Bedrock vs Inkling 2 Small](https://www.anchorterminal.com/compare/amazon-bedrock-vs-inkling-2-small.md)\n- [Amazon Bedrock vs Meta Model API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-meta-model-api.md)\n- [Amazon Bedrock vs MiniMax API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-minimax-api.md)\n- [Amazon Bedrock vs Mistral AI API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api.md)\n- [Amazon Bedrock vs Muse Spark Open](https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open.md)\n- [Amazon Bedrock vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.md)\n- [Amazon Bedrock vs Novita AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-novita-ai.md)\n- [Amazon Bedrock vs OpenAI API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-openai-api.md)\n- [Amazon Bedrock vs OpenRouter](https://www.anchorterminal.com/compare/amazon-bedrock-vs-openrouter.md)\n- [Amazon Bedrock vs Prism Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-prism-inference.md)\n- [Amazon Bedrock vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-ramp-router.md)\n- [Amazon Bedrock vs Beam 1.0](https://www.anchorterminal.com/compare/amazon-bedrock-vs-reflection-beam.md)\n- [Amazon Bedrock vs RouterPlus](https://www.anchorterminal.com/compare/amazon-bedrock-vs-routerplus.md)\n- [Amazon Bedrock vs SambaCloud](https://www.anchorterminal.com/compare/amazon-bedrock-vs-sambanova.md)\n- [Amazon Bedrock vs SiliconFlow](https://www.anchorterminal.com/compare/amazon-bedrock-vs-siliconflow.md)\n- [Amazon Bedrock vs Simplismart](https://www.anchorterminal.com/compare/amazon-bedrock-vs-simplismart.md)\n- [Amazon Bedrock vs StepFun API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api.md)\n- [Amazon Bedrock vs SWE-2 Flash](https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash.md)\n- [Amazon Bedrock vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/amazon-bedrock-vs-tencent-tokenhub.md)\n- [Amazon Bedrock vs Together AI Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-together-inference.md)\n- [Amazon Bedrock vs Vercel AI Gateway](https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway.md)\n- [Amazon Bedrock vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-vertex-ai.md)\n- [Amazon Bedrock vs xAI API (Grok)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api.md)\n- [Claude API vs Jais 3](https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3.md)\n- [Antseed vs Jais 3](https://www.anchorterminal.com/compare/antseed-vs-jais-3.md)\n- [Azure OpenAI in Foundry Models vs Jais 3](https://www.anchorterminal.com/compare/azure-openai-vs-jais-3.md)\n- [BlockRun.AI vs Jais 3](https://www.anchorterminal.com/compare/blockrun-ai-vs-jais-3.md)\n- [Cerebras Inference vs Jais 3](https://www.anchorterminal.com/compare/cerebras-inference-vs-jais-3.md)\n- [Cloudflare AI Gateway vs Jais 3](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3.md)\n- [Cloudflare Workers AI vs Jais 3](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-jais-3.md)\n- [Cohere Chat API (Command models) vs Jais 3](https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3.md)\n- [DeepInfra vs Jais 3](https://www.anchorterminal.com/compare/deepinfra-vs-jais-3.md)\n- [DeepSeek API vs Jais 3](https://www.anchorterminal.com/compare/deepseek-api-vs-jais-3.md)\n- [Eden AI vs Jais 3](https://www.anchorterminal.com/compare/eden-ai-vs-jais-3.md)\n- [Glimpse vs Jais 3](https://www.anchorterminal.com/compare/elorian-glimpse-vs-jais-3.md)\n- [Fireworks AI Inference vs Jais 3](https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3.md)\n- [Gemini Developer API vs Jais 3](https://www.anchorterminal.com/compare/gemini-api-vs-jais-3.md)\n- [GroqCloud vs Jais 3](https://www.anchorterminal.com/compare/groq-vs-jais-3.md)\n- [Hugging Face Inference Providers vs Jais 3](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3.md)\n- [Inkling 2 Small vs Jais 3](https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3.md)\n- [Jais 3 vs Meta Model API](https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api.md)\n- [Jais 3 vs MiniMax API](https://www.anchorterminal.com/compare/jais-3-vs-minimax-api.md)\n- [Jais 3 vs Mistral AI API](https://www.anchorterminal.com/compare/jais-3-vs-mistral-api.md)\n- [Jais 3 vs Muse Spark Open](https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open.md)\n- [Jais 3 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.md)\n- [Jais 3 vs Novita AI](https://www.anchorterminal.com/compare/jais-3-vs-novita-ai.md)\n- [Jais 3 vs OpenAI API](https://www.anchorterminal.com/compare/jais-3-vs-openai-api.md)\n- [Jais 3 vs OpenRouter](https://www.anchorterminal.com/compare/jais-3-vs-openrouter.md)\n- [Jais 3 vs Prism Inference](https://www.anchorterminal.com/compare/jais-3-vs-prism-inference.md)\n- [Jais 3 vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/jais-3-vs-ramp-router.md)\n- [Jais 3 vs Beam 1.0](https://www.anchorterminal.com/compare/jais-3-vs-reflection-beam.md)\n- [Jais 3 vs RouterPlus](https://www.anchorterminal.com/compare/jais-3-vs-routerplus.md)\n- [Jais 3 vs SambaCloud](https://www.anchorterminal.com/compare/jais-3-vs-sambanova.md)\n- [Jais 3 vs SiliconFlow](https://www.anchorterminal.com/compare/jais-3-vs-siliconflow.md)\n- [Jais 3 vs Simplismart](https://www.anchorterminal.com/compare/jais-3-vs-simplismart.md)\n- [Jais 3 vs StepFun API](https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api.md)\n- [Jais 3 vs SWE-2 Flash](https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash.md)\n- [Jais 3 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.md)\n- [Jais 3 vs Together AI Inference](https://www.anchorterminal.com/compare/jais-3-vs-together-inference.md)\n- [Jais 3 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway.md)\n- [Jais 3 vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/jais-3-vs-vertex-ai.md)\n- [Jais 3 vs xAI API (Grok)](https://www.anchorterminal.com/compare/jais-3-vs-xai-api.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Amazon Bedrock vs Jais 3", "url": "" } ], "description": "Amazon Bedrock scores 81.7 (A) to Jais 3's 52.1 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Amazon Bedrock A 81.7", "Jais 3 D 52.1", "scores" ], "h1": "Amazon Bedrock vs Jais 3", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/amazon-bedrock-vs-jais-3", "published": "2026-10-01", "section": "tools", "title": "Amazon Bedrock vs Jais 3 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-jais-3" }, "tokens": { "markdown": 7200, "slim": 3830 }, "version": 1 }