# Amazon Bedrock vs Cohere Chat API (Command models) (slim)

> Amazon Bedrock scores 81.7 (A) to Cohere Chat's 65.6 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.md (~7,850 tokens) · this version ~4,080 tokens · JSON https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.json · canonical https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Amazon Bedrock scores 81.7 (A) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 6 of 7 scored categories. Cohere Chat API (Command models) leads on payments & pricing. Both do llm inference.

- Amazon Bedrock: A 81.7, rank #8 of 1486 · https://www.anchorterminal.com/tools/amazon-bedrock.min.md
- Cohere Chat API (Command models): B 65.6, rank #407 of 1486 · https://www.anchorterminal.com/tools/cohere-chat.min.md
- Amazon Bedrock, good 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. Ahead on Reliability, 80 against 67; Schema & documentation, 94 against 84; Agent ergonomics, 92 against 72; Security & auth, 98 against 55; Maintenance & community, 81 against 72; Transparency & trust, 85 against 75. Also Agent-ready, a grade of BB or better.
- Cohere Chat API (Command models), good for Teams that want Command models for RAG with citations, tool use and multilingual work, and that may later move to a private deployment or Model Vault. Ahead on Payments & pricing, 35 against 30. Also Free to start without a card.

| Category | Amazon Bedrock | Cohere Chat API (Command models) |
| --- | --- | --- |
| Reliability (16%) | 80 | 67 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 94 | 84 |
| Agent ergonomics (13%) | 92 | 72 |
| Security & auth (14%) | 98 | 55 |
| Payments & pricing (10%) | 30 | 35 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 81 | 72 |
| Transparency & trust (7%) | 85 | 75 |

| Fact (where they differ) | Amazon Bedrock | Cohere Chat API (Command models) |
| --- | --- | --- |
| Vendor | Amazon Web Services | Cohere |
| Hosted endpoint | `https://bedrock-runtime.us-east-1.amazonaws.com` | `https://api.cohere.com/v2/chat` |
| Auth | OAuth or key | API key |
| Pricing | Pay per use | Freemium |
| 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 | Proprietary service under Cohere's Commercial SaaS Agreement. The SDKs are MIT |
| Last release | 2026-10-30 | 2026-09-09 |
| Terms last updated | 2026-10-01 | 2025-04-08 |
| Privacy policy last updated | 2026-05-18 | 2026-05-01 |
| Customer content may train models | yes, with an opt-out | yes |
| Terms restrict automated access | yes | not found in the text |
| Popularity | 21.8M npm/wk | none |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Security & auth, Amazon Bedrock +43: 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.); Cohere Chat API (Command models) 55 (Model reading. Bearer keys of two kinds, trial and production. Team roles are Owner and User, only Owners delete production keys, and a production key is shown in full once. No scopes, expiry or per-model restriction was found (18 of 30). Paying customers can switch training off under Data Controls, which implies it is on until they do, trial keys fall under the website terms, and the SaaS agreement grants an irrevocable right to use API data to improve the services and share it with third parties (8 of 20). Logged prompts and generations are deleted after 30 days unless flagged, and zero data retention needs approval (12 of 15). The dashboard shows usage history, and no customer audit log was found (2 of 15). The trust centre lists SOC 2 Type II, ISO 27001, ISO 42001, UK Cyber Essentials, penetration tests on request and a responsible disclosure policy with a bug bounty, per the 9 October check. cohere.com/.well-known/security.txt still answers 404 on 2 November and no public advisories were found, so the line takes 15, as cohere-embed and cohere-north read the same programme (15 of 20).)
- Agent ergonomics, Amazon Bedrock +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).); Cohere Chat API (Command models) 72 (Model reading. Function calling with `tool_choice` REQUIRED or NONE and `strict_tools`, which the reference marks beta (17 of 20). `response_format` takes `json_object` or a JSON Schema, with limits documented and no support in RAG mode (13 of 15). The usage object reports `cached_tokens`, and no guide or price for prompt caching was found (5 of 15). Context is 256,000 tokens on Command A and Command A Reasoning and 128,000 on Command A+ (10 of 15). `/v2/batches` runs a batch from an uploaded dataset, with no price or discount found (6 of 10). Official SDKs for Python, TypeScript, Java and Go (10). Error messages are specific and readable, with no stable error codes (11 of 15).)
- Reliability, Amazon Bedrock +13: 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).); Cohere Chat API (Command models) 67 (Hosted lines. status.cohere.com (incident.io) lists each Command model and the endpoints as components (20). Its feed, read on 2 November 2026, shows two incidents in the 90 days from 4 August. 'Multiple Endpoint Disruptions' on 1 September 2026, from 15:41 to 19:47 UTC, degraded the embeddings endpoint, embed-v4.0, two rerank models and `command-a-reasoning-08-2025` during a Google Cloud outage, rated minor and partial, and docs loading failed on 5 August. Nothing has been posted since 1 September, so minor incidents only (20). Chat limits are published per model, 20 requests a minute and 1,000 calls a month on a trial key and 500 a minute on a production key for Command A, R, R+ and R7B, while the four newest variants say contact sales (12 of 15). The errors page documents 429 with example messages that say to wait and try again later and links to the rate limits, with no Retry-After header, backoff timing or idempotency key, the reading cohere-embed takes of the same page (8 of 15). cohere.com/slo is titled Service Level Objective and its text is script-drawn, so it was unread and scores as absent (0). The v2 chat endpoint is the default docs version, but the sample response on the chat guide still carries `is_experimental` and the newest models are not open to production keys (7 of 10).)
- Schema & documentation, Amazon Bedrock +10: 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).); Cohere Chat API (Command models) 84 (Model reading. Public OpenAPI 3.1 file `cohere-openapi.yaml` in cohere-ai/cohere-developer-experience, 43 operations, last changed 29 September 2026 (25). docs.cohere.com/llms.txt and a Markdown twin of every page by adding `.md`, though the llms.txt files list no pages (8 of 10). The v2 chat operation describes each of its 21 request fields with defaults and limits, and says less about when to prefer one option (16 of 20). Enums on `tool_choice`, `safety_mode` and `thinking.type`, numeric bounds on `temperature`, `k`, `p` and `priority`, with penalties bounded only in prose (12 of 15). Eight request examples on the operation and an errors page with sample messages for each status code, with error bodies carrying a message and no machine code (12 of 15). v1 and v2 live side by side in the path and the changelog is dated, but the OpenAPI file is version 1.0 throughout and its changes are committed as 'Add spec changes' with no per-change note (11 of 15).)
- Transparency & trust, Amazon Bedrock +10: 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).); Cohere Chat API (Command models) 75 (Closed service under a published SaaS agreement, MIT SDKs, and the docs say Command A+ weights are on Hugging Face under Apache 2.0, which we did not open (15 of 30). The Enterprise Data Commitments (5 December 2025) and the privacy policy (1 May 2026) agree on 30-day retention and a training opt-out. The SaaS agreement (8 April 2025) does not mention the opt-out and grants an irrevocable right to use and share API data, and the DPA is sent on request (16 of 30). Deprecations page with dated history back to 2024 and lifecycle terms, no minimum notice, and nothing newer than 4 April 2026 on 2 November, read at 15 as cohere-embed reads the same page (15 of 20). The trust centre names nine sub-processors with a location for each, all in the US, and Google Cloud US-Central as the data location, read at 20 as cohere-embed reads the same list (20 of 20).)
- Maintenance & community, Amazon Bedrock +9: 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.); Cohere Chat API (Command models) 72 (Model reading. The last dated release on the Chat endpoint is still North Small Translate on 9 September 2026, 54 days before this check. The last Command model is Command A+ on 20 May 2026. Rerank 5 (21 October) and Embed 5 (30 September) aren't chat changes, so we score the 90-day band (20 of 30). The deprecations page defines Active, Legacy, Deprecated and Shutdown and promises email notice, with no minimum notice period (6 of 12). No chat model was retired or announced for retirement in the last 90 days. The newest entry on the page is still two Aya models retired on 4 April 2026 (8 of 8). Dated changelog with four entries since 4 August (27 August, 9 September, 30 September, 21 October), one of them for a chat model (12 of 15). SDK issue replies not sampled (5 of 10). Python SDK 7.2.0 and 7.3.0, TypeScript 8.2.0 (19 October) and 8.3.0, and Go v2.20.0 tagged on 21 October 2026, Java at 1.12.0 (15). The Python SDK is generated from the OpenAPI file and has a CI workflow, whose runs we did not read (6 of 10).)

| Task | Amazon Bedrock | Cohere Chat API (Command models) |
| --- | --- | --- |
| Research a product and write a sourced report | $43.88 | $27.31 |
| Build a small four-page website | $10.03 | $6.17 |
| Find and fix a bug in a large codebase | $2.16 | $1.35 |