Amazon Bedrock vs DeepSeek API

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.

DeepSeek API 35

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). Model reading. One Bearer key per balance, no scoping found (20 of 30). The privacy policy, last updated 10 February 2026, says personal data is used to train models, with an opt-out by email to privacy@deepseek.com (0 of 20). Data kept for as long as needed to provide the services, with no period stated and no zero-retention route (5 of 15). Per-call logs or audit logs not found (5 of 15). Security programme 5 of 20 (was 0). The www.deepseek.com footer carries a Report Security Issue address, security@deepseek.com, per the 21 October reading used for DeepSeek's open-weight listings and its Search and Fetch API listing. No security.txt (404 on 17 October), disclosure policy, certification or bug bounty found. 20 + 0 + 5 + 5 + 5 = 35.

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).

DeepSeek API 49

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). No OpenAPI document and no llms.txt found (0 and 0). API reference covers both the OpenAI and Anthropic formats. The chat completion reference, read on 2 October, describes each parameter with its range and default, such as max_tokens from 1 to 393,216 with 8K by default without thinking, but says little on when not to use one (14 of 20). Strict tool calls are documented, in beta at the /beta base URL, with a JSON Schema subset (object, string, number, integer, boolean, array, enum, anyOf, $ref) where every property must be required. JSON output mode carries no schema guarantee (10 of 15). The error codes page lists seven codes, each with a cause and a fix, but no example bodies (10 of 15). Dated updates page that names model changes (15). 0 + 0 + 14 + 10 + 10 + 15 = 49.

Amazon Bedrock 81

Model reading. The last model or API change is 30 October 2026 (OpenAI model API support and cross-Region inference in GovCloud), after structured outputs for Claude on both endpoints on 18 October (30). Models launched since 7 September 2026 get a 6-month or 45-day Legacy period, but the legacy page, which promises at least 6 months in Legacy, lists Claude 3 Haiku, 3 Sonnet, 3.5 Sonnet, 3.5 Sonnet v2 and 3.7 Sonnet as Legacy from 10 or 13 October with end of life on 13 November in several Regions, about 34 days (6 of 12, down from 10). Six models reached end of life in the 90 days to 6 November on five dates, Command R and R+ on 19 August, Claude 3 Haiku on 10 September, Nova Sonic on 14 September, Nova Canvas and Nova Reel on 30 September and Claude Sonnet 4 on 14 October (3 of 8, down from 4). Dated document history several times a month, What's New and re:Post, with direct support on a paid plan (12 of 15). SDK issue replies not sampled (5 of 10). Current official SDKs, boto3 1.43.125 on 5 November and @aws-sdk/client-bedrock-runtime 3.1163.0 (15). Supported runtimes stated, Python 3.10 or later and Node 20 or later (10). Down from 86 on 6 October.

DeepSeek API 46

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). Model reading. V4.1 Flash was upgraded to DeepSeek-V4.1-Flash-1017 on 17 October under the same deepseek-flash name and price, posted on the updates page the same day, 19 days before this check (30). Later updates entries are unread. No stated notice policy. deepseek-chat and deepseek-reasoner got three months, announced on 24 April for 24 July. One dated notice with no stated period partly meets the line, and the earlier partial award is held (4 of 12). Model churn covers the V4 Flash retirement on 10 September and the V4 Pro shutdown set for 14 September, announced on 13 August and withdrawn on 10 September. The 24 July shutdown has left the 90-day window. A retirement and a withdrawn shutdown inside it keep churn at the bottom of its range (0 of 8). Dated updates page, and the docs list api-service@deepseek.com and a Discord server for support. We didn't test whether either answers (12 of 15). No official SDKs or SDK repository (0 of 15, 0 of 10). 30 + 4 + 0 + 12 + 0 + 0 = 46.

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).

DeepSeek API 70

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through both request formats, and the API reference documents tool_choice as none, auto, required or a named function (20 of 20). Strict schema-enforced tool calls in beta, JSON output without a schema guarantee (10 of 15). Disk cache on by default with cheaper hits, per the listing (15). 1M-token context and up to 384K output (15). No batch API documented (0). No official SDKs, you use the OpenAI or Anthropic client (0). Seven error codes with a fix for each, 402 for an empty balance (10 of 15). 20 + 10 + 15 + 15 + 0 + 0 + 10 = 70.

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).

DeepSeek API 60

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). Status page at status.deepseek.com, run on Flashduty, with per-API components and a readable feed (20). The recorded feed lists 36 incidents from 22 July to 15 October. Four touch only web search, 27 are degraded performance, and five are partial unavailability, one of them (12 October) the web chat only. Of the four that hit the API, 28 July (7 minutes) has left the 90-day window and 2 September lasted 31 minutes. 14 September (18:30 to 21:30 UTC) left the V4.1 Flash API and chat partly unavailable for three hours, and 15 October (00:11 to 05:04 UTC) left the V4 Pro and V4.1 Flash APIs and chat partly unavailable for 4 hours 52 minutes. Two majors in 90 days sit between one (10) and several (0), so 5. 16 October to 5 November is unread and earns nothing beyond the recorded award (5). Concurrency caps published per account, 2,500 on Flash and 500 on V4 Pro, and requests that haven't started inference after 10 minutes are closed (15). The rate-limit and error pages document 429, and advise a brief wait and retry on 500 and 503, with no Retry-After header, backoff schedule or statement that a retried call is safe (10 of 15). No SLA found (0). V4 Pro and V4.1 Flash are GA (10). 20 + 5 + 15 + 10 + 0 + 10 = 60.

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).

DeepSeek API 65

Per the 17 October check, not re-read on 5 November (DeepSeek's terms bar automated access, so nothing on DeepSeek's hosts was requested). Closed service with clear terms under PRC law. The model weights are published, which doesn't change the hosted service (15). The privacy policy of 10 February 2026 is consistent on training by default and storage in the PRC, but publishes no retention period and no DPA (10 of 30). Dated notices on the updates page, undercut by a shutdown announced and withdrawn within a month and a reroute with no prior entry (10 of 20). Data location disclosed as the PRC, third parties named only by category (10 of 20). 15 + 10 + 10 + 10 = 45.