Amazon Bedrock vs SambaCloud

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.

SambaCloud 61

Model reading. Bearer keys from the console, up to 25 per user and shown once. No scopes, project limits or rotation guidance were found, and the key travels in a header, never in the URL (18 of 30). The terms let SambaNova access, store and process Customer Content solely to supply the service and for no other purposes, which rules out training without naming it (18 of 20). The DPA's Annex I, read on 1 November, keeps prompts, inputs and completions no more than 30 days for security, fraud and abuse monitoring. No zero-retention option was found in the pages read, and the product page says SambaCloud never sees or collects prompts, against that retention and terms that grant a right to store content and to use query logs (10 of 15, between deepseek-api's 5 and siliconflow's 6 with no period stated and the 15 groq, mistral-api and xai-api take for 30 days with a zero-retention route). The console has a Usage page. No request logs or audit log were found in the docs (5 of 15). The trust centre states SOC 2 Type 2 and ISO 27001. No security.txt, disclosure policy or bug bounty was found, and the SDK's SECURITY.md sends service reports to a general address (10 of 20).

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).

SambaCloud 67

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling with tool_choice to force a function, on six listed models, and a July 2026 fix for tool calls that were buffered when streaming (17 of 20). json_object and json_schema output, best effort only, with a known failure on DeepSeek-V3.2 recorded in July 2026 (8 of 15). Automatic prompt caching on the MiniMax models only, with cached input on MiniMax-M3.1-Flash at a tenth of the input price on the 1 November pricing page, a 4,096-token minimum and no guaranteed persistence (10 of 15). 131,072-token context on four of six models, 1M on the MiniMax-M3 preview, and output capped at 7,168 tokens on DeepSeek and 3,072 on Llama 3.3 70B (8 of 15). No batch API found in the docs index or the OpenAPI document (0 of 10). Official SDKs for Python and TypeScript, and the OpenAI and Anthropic clients work with a changed base URL (10). Errors carry type, param, code and request_id (14 of 15).

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).

SambaCloud 81

Public OpenAPI 3.1.1 document, still labelled version 1.2.0 though its content changed on 27 October 2026, with 10 operations and 165 schemas (25). llms.txt at docs.sambanova.ai/docs/llms.txt and a Markdown copy of each page, per the 8 October check (docs.sambanova.ai answered robots.txt with a bot check on 1 November, so it wasn't read) (10). 718 descriptions in the document, with pages for function calling, Responses, Messages and caching. When not to use a route is rarely stated (15 of 20). Typed parameters with 150 enums, and request bodies now declare additionalProperties: false, but JSON schema output is best effort and strict: true has no effect (10 of 15). Code examples in Python and TypeScript, and an errors page with 13 codes and a recovery suggestion for each, per the 8 October check (13 of 15). The spec is versioned in its repository, but the version label didn't move with the 27 October changes, the newest SambaCloud release note seen is 7 July 2026, and the models page disagreed with /v1/models on 8 October (8 of 15). 25+10+15+10+13+8 = 81.

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).

SambaCloud 73

Closed service with clear terms that name the entity and the governing law, and Apache-2.0 SDKs and OpenAPI document (15). The privacy policy is still dated 27 May 2023 and doesn't name SambaCloud or API inputs. A Data Processing Addendum, part of the Terms of Service, is now linked from the legal page (undated). It limits processing of customer personal data to the agreement, its Annex I says prompts, inputs and completions are processed transiently and kept no more than 30 days for security, fraud and abuse monitoring, then deleted, and it deletes customer personal data within 30 days of termination and from backups within 90. The product page's claim, re-read on 1 November, that SambaCloud 'never sees or collects any of your data or user prompts' sits beside that 30-day retention and terms that allow storing content and using query logs (16 of 30, as novita-ai's stated retention periods, below mistral-api's 18 where the DPA and other pages agree). A deprecations page with notice and removal dates back to April 2025, recording MiniMax-M2.7's 1 October removal with a 1 September notice per the 27 October read, though nothing for Mistral Large 3, per the 8 October check (14 of 20). The DPA's Annex III names 24 sub-processors with purpose and location (USA, Japan, Germany, the United Kingdom, Australia) and promises 30 days' notice of changes, though it doesn't say where inference runs for a given request (18 of 20). 15+16+14+18 = 63.

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).

SambaCloud 40

No machine payment protocol (0). Per-token prices on the pricing page, read without a login on 1 November, such as gpt-oss-120b at $0.22 in and $0.59 out per 1M tokens (20). Free tier with no payment method, per the 8 October check (20). A person signs up in the console to get a key (0).

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).

SambaCloud 85

Hosted reading. Status page at status.sambanova.ai on Statuspage, with components for the API gateway, the Playground and each model, read from the page itself on 1 November (20). Its history.atom feed, read on 1 November (the 8 October reading came from the /api/ path, which robots.txt disallows, and is struck), has nothing newer than an 8-minute Playground login fault on 25 June 2026, so nothing is posted for the window from 3 August (30). Limits published per model and tier, 20 requests a minute and 20 a day on the free tier, 60 and 12,000 on the Developer tier, per the 8 October check, not re-read on 1 November (15). x-ratelimit-* headers on every response, the error table says to retry queue_full after a delay, and the SDKs retry 429 and server errors twice with backoff, per the 8 October check. No Retry-After header was found in the docs or the OpenAPI document (10 of 15). No SLA found on the legal page, re-read on 1 November, or in the terms (0). Three production models are generally available, the rest previews, per the 8 October check (10). 20+30+15+10+0+10 = 85.