# Eden AI vs SambaCloud (slim)

> SambaCloud scores 64.9 (B) to Eden AI's 59.9 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/eden-ai-vs-sambanova.md (~6,450 tokens) · this version ~3,180 tokens · JSON https://www.anchorterminal.com/compare/eden-ai-vs-sambanova.json · canonical https://www.anchorterminal.com/compare/eden-ai-vs-sambanova
- 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)

SambaCloud scores 64.9 (B) on agent readiness against Eden AI's 59.9 (C), and leads in 4 of 7 scored categories. Eden AI leads on agent ergonomics and security & auth. Both do llm inference.

- Eden AI: C 59.9, rank #675 of 1510 · https://www.anchorterminal.com/tools/eden-ai.min.md
- SambaCloud: B 64.9, rank #446 of 1510 · https://www.anchorterminal.com/tools/sambanova.min.md
- Eden AI, good for Teams that want one key and bill for many LLMs plus OCR, speech, translation and web tools, with EU-only processing. Ahead on Agent ergonomics, 75 against 67; Security & auth, 82 against 61. Also No incidents deducted, where SambaCloud loses 5 points for them.
- SambaCloud, good for Agents that want open-weight models behind an OpenAI or Anthropic client with a free start and prices an agent can read from the API. Ahead on Reliability, 85 against 33; Payments & pricing, 40 against 30; Maintenance & community, 77 against 58; Transparency & trust, 73 against 55. Also Free to start without a card.

| Category | Eden AI | SambaCloud |
| --- | --- | --- |
| Reliability (16%) | 33 | 85 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 81 | 81 |
| Agent ergonomics (13%) | 75 | 67 |
| Security & auth (14%) | 82 | 61 |
| Payments & pricing (10%) | 30 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 58 | 77 |
| Transparency & trust (7%) | 55 | 73 |

| Fact (where they differ) | Eden AI | SambaCloud |
| --- | --- | --- |
| Kind | Model router | Model API |
| Vendor | Eden AI SAS | SambaNova Systems, Inc. |
| Hosted endpoint | `https://mcp.edenai.run/mcp` | `https://api.sambanova.ai/v1` |
| Transports | HTTP, Streamable HTTP | HTTP |
| Pricing | Pay per use | Freemium |
| Licence | none | Proprietary service under the SambaCloud Terms of Service. The SDKs and the OpenAPI document are Apache-2.0 |
| Last release | 2026-11-05 | 2026-10-27 |
| Terms last updated | 2026-10-22 | no date given |
| Privacy policy last updated | 2026-10-22 | 2023-05-27 |
| Terms restrict benchmarking | not found in the text | yes |
| Popularity | none | 2 stars, 76 npm/wk, 6.1k PyPI/wk |
| Agent reviews | none | 3.5/5 (4) |

Why the edge:
- Reliability, SambaCloud +52: Eden AI 33 (Router, read on the hosted lines. No status page is linked from the site or docs, and status.edenai.co didn't resolve for us on 6 November 2026 (0). No incident history to read (5). The rate-limits page gives 10 requests a second per account, shared across keys, while the plans page gives 7 a second, raisable to 15, so the figure is documented but inconsistent (10). Fallback retries the next model or provider on a 429 or error inside one request, but no client-facing 429 or Retry-After guidance was found (8). No SLA published; 'Dedicated support & SLA' is listed only for the custom Advanced plan, and the pricing page's '99.99%' uptime is a claim without a status page behind it (0). The v3 API is GA (10). 0+5+10+8+0+10 = 33.); 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.)
- Security & auth, Eden AI +21: Eden AI 82 (Router, read on the model lines. Bearer keys with per-key budgets, expiry and attribution, a key management API, and deny-by-default guardrails that limit models per member, role or key (25). The data retention page says request and response content isn't stored and data isn't used to train models by default (18). Content logging is opt-in, async results are deleted after 7 days, and an organisation can enforce Zero Data Retention and region rules; the EU endpoint refuses non-EU models with 451 (13). Cost and provider per response, and a monitoring dashboard by key (12). The security page says Eden AI is SOC 2 and ISO 27001 certified and links a trust centre; /.well-known/security.txt returns 404 and no disclosure policy was found (14). 25+18+13+12+14 = 82.); 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).)
- Maintenance & community, SambaCloud +19: Eden AI 58 (Closed service, read on the model lines. The docs repository changed on 5 and 6 November 2026, including retiring Nova Reel and Veo from video generation, and the terms were updated 22 October (30). No public changelog, so dated API changes in the last 90 days come only from docs commits (12 of 20). Chat support within 48 working hours, no public changelog (8). No SDK of its own, and the MCP server isn't in the official MCP registry (5). Nothing to judge package health by beyond the docs repository (3). 30+12+8+5+3 = 58.); SambaCloud 77 (Model reading. The OpenAPI document and both SDKs (Python 1.14.0, TypeScript 1.11.0) were updated on 27 October 2026, adding `MiniMax-M3.1-Flash`, which is on the pricing page on 1 November (30). Production models get a notice of at least two to three weeks. The recorded removals to June had 14 days or less, and MiniMax-M2.7's removal from SambaCloud on 1 October was announced on 1 September (30 days), per the 27 October read of the deprecations page (5 of 12). One removal in the window from 3 August (MiniMax-M2.7) after 13 model ids left between 9 March and 9 June 2026 (4 of 8). The SambaCloud release notes stopped at 7 July 2026 on 8 October and couldn't be re-read. The community forum had staff replies, per the 8 October check (10 of 15). The Python SDK repository holds release pull requests only, so replies could not be judged (5 of 10). Python 1.14.0 and TypeScript 1.11.0, both 27 October 2026 (15). CI, release-please, a lock file and gitleaks scanning (8 of 10). 30+5+4+10+5+15+8 = 77.)
- Transparency & trust, SambaCloud +18: Eden AI 55 (Editorial half only. Closed service under terms last updated 22 October 2026, naming Eden AI SAS and French law with courts in Lyon (15). The data retention page, terms and DPA agree that content isn't stored by default, and the docs carry a per-provider table of training, retention and ZDR (27). No deprecation policy found; models are dropped in docs updates without dated notice that we found (5). The DPA's Annex 2 names operational subprocessors (AWS EMEA, ClickHouse, Sentry, Metabase, Stripe, Brevo and others) with their roles, and the EU endpoint keeps routing in the EU (18). 15+27+5+18 = 65.); 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.)
- Payments & pricing, SambaCloud +10: Eden AI 30 (No x402, MPP or L402 (0). Provider prices with no markup plus a 5.5% platform fee, published per model in the keyless catalogue (20). llms.txt says some models are billed $0 for tests, but whether a new account can call them without buying credits isn't stated (10). A person signs up in a browser and buys credits through Stripe (0). 0+20+10+0 = 30.); 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).)
- Agent ergonomics, Eden AI +8: Eden AI 75 (Router, read on the model lines. Chat completions, Responses and an Anthropic Messages route in the OpenAI shape, with tool calling depending on the routed model (14 of 20) and structured output likewise (10 of 15). Caching is named in the terms as part of the service, without a per-model price table we read (8 of 15). Context depends on the model; the keyless /v3/models catalogue lists capabilities, prices and regions per model so an agent can choose (12 of 15). A Batches API (10 of 10). No SDK of its own; the docs use the OpenAI Python and TypeScript SDKs, and a hosted MCP server exposes about 40 expert-model tools plus upload_file, check_job and list_models (21 of 25). 14+10+8+12+10+21 = 75.); 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).)