{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/groq.json", "name": "GroqCloud", "score": 75.6, "shared": [ "inference.llm", "inference.fast", "inference.open-weights" ], "slug": "groq" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/prism-inference.json", "name": "Prism Inference", "score": 60.1, "shared": [ "inference.fast", "inference.open-weights", "inference.llm" ], "slug": "prism-inference" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/mistral-api.json", "name": "Mistral AI API", "score": 71.2, "shared": [ "inference.llm", "inference.open-weights" ], "slug": "mistral-api" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/deepinfra.json", "name": "DeepInfra", "score": 63, "shared": [ "inference.llm", "inference.open-weights" ], "slug": "deepinfra" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/docker-model-runner.json", "name": "Docker Model Runner", "score": 57.1, "shared": [ "inference.open-weights", "inference.llm" ], "slug": "docker-model-runner" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/ollama.json", "name": "Ollama", "score": 56.3, "shared": [ "inference.open-weights", "inference.llm" ], "slug": "ollama" } ], "tool": { "slug": "sambanova", "name": "SambaCloud", "vendor": "SambaNova Systems, Inc.", "vendorUrl": "https://sambanova.ai", "kind": "model", "category": "inference", "summary": "SambaCloud is SambaNova's hosted inference API for open-weight models running on its own RDU processors. It answers OpenAI-style chat, completions and Responses calls and Anthropic-style Messages calls, with Python and TypeScript SDKs.", "url": "https://www.anchorterminal.com/tools/sambanova", "markdownUrl": "https://www.anchorterminal.com/tools/sambanova.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/sambanova.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/sambanova.json", "repo": "https://github.com/sambanova/sambanova-python", "license": "Proprietary service under the SambaCloud Terms of Service. The SDKs and the OpenAPI document are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.sambanova.ai/v1", "packages": [ { "registry": "pypi", "name": "sambanova" }, { "registry": "npm", "name": "sambanova" } ], "auth": "api-key", "authNotes": "Self-serve Bearer key from the SambaCloud console at https://cloud.sambanova.ai/apis after a browser sign-up. The Messages routes also take the same key in `x-api-key`. Up to 25 keys per user, shown once, with no scopes.", "pricing": "freemium", "pricingNotes": "Free tier with no payment method, at 20 requests a minute, 20 requests a day and 200,000 tokens a day per model. Linking a card moves the account to the Developer tier, billed per token through Stripe, from $0.22 in and $0.59 out per 1M tokens on gpt-oss-120b (https://cloud.sambanova.ai/plans/pricing, checked 2026-10-08).", "priceSummary": "from $0.22 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI document or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 2, "npmWeekly": 76, "pypiWeekly": 6129, "asOf": "2026-10-08" }, "docsUrl": "https://docs.sambanova.ai/docs/en/get-started/overview", "rateLimitsUrl": "https://docs.sambanova.ai/docs/en/models/rate-limits", "llmsTxt": "https://docs.sambanova.ai/docs/llms.txt", "openapi": "https://raw.githubusercontent.com/sambanova/sambanova-inference-api-spec/refs/heads/main/openapi.documented.json", "capabilities": [ "inference.llm", "inference.open-weights", "inference.fast" ], "tags": [ "hosted", "model", "open-weights", "free-tier", "no-card", "openapi", "llms-txt", "openai-compatible", "anthropic-compatible", "python", "typescript", "status-page", "soc2" ], "lastRelease": "2026-09-17", "graded": true, "anchor": { "graded": true, "score": 66.4, "grade": "B", "agentReady": false, "rank": 269, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 77, "payments": 40, "reliability": 85, "schema": 81, "security": 58, "transparency": 63 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 85, "points": 17, "reason": "Hosted reading. Status page at status.sambanova.ai on Statuspage, with components for the API gateway, the Playground and each model (20). The incident feed lists 25 incidents since launch, the latest an 8-minute Playground login fault on 25 June 2026, so nothing is posted for the last 90 days (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 (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. No `Retry-After` header was found in the docs or the OpenAPI document (10 of 15). No SLA found on the legal page or in the terms (0). Three production models are generally available, three are previews (10)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 81, "points": 13.16, "reason": "Public OpenAPI 3.1.1 document, version 1.2.0, with 10 operations and 169 schemas, last updated 17 September 2026 (25). `llms.txt` at docs.sambanova.ai/docs/llms.txt and a Markdown copy of each page (10). 717 descriptions in the document, with feature pages for function calling, Responses, Messages and caching. When not to use a route is rarely stated (15 of 20). Typed parameters with 152 enums, 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 (13 of 15). The spec is versioned and release notes are dated, but the newest SambaCloud entry is 7 July 2026 and the models page disagrees with `/v1/models` (8 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 67, "points": 10.89, "reason": "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 at a tenth of the input price, 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)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 58, "points": 10.15, "reason": "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). No retention period is published. The product page says SambaCloud never sees or collects prompts, while the terms grant a right to store content and to use query logs (7 of 15). 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)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "No machine payment protocol (0). Per-token prices on the pricing page and in `/v1/models`, both read without a login, such as gpt-oss-120b at $0.22 in and $0.59 out per 1M tokens (20). Free tier with no payment method (20). A person signs up in the console to get a key (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 77, "points": 6.74, "reason": "Model reading. The OpenAPI document and both SDKs were updated on 17 September 2026, and a MiniMax-M3 component joined the status page on 1 September (30). Production models get a notice of at least two to three weeks, and the recorded removals had 14 days or less (5 of 12). No removal is recorded in the last 90 days, but 13 model ids left between 9 March and 9 June 2026, and MiniMax-M2.7 is in the docs but not in the live catalogue (4 of 8). The SambaCloud release notes stop at 7 July 2026. The community forum has staff replies and a post dated 8 October 2026 (10 of 15). The Python SDK repository has no open issues and holds release pull requests only, so replies could not be judged (5 of 10). Python 1.13.0 and TypeScript 1.10.0, both 17 September 2026 (15). CI, release-please, a lock file and gitleaks scanning (8 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 63, "points": 5.51, "note": "editorial 44, provenance 81", "reason": "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 dated 27 May 2023 and does not name SambaCloud or API inputs, no DPA or retention period is published, and the product page's claim that prompts are never seen or collected sits beside terms that allow storing content and using query logs (10 of 30). A deprecations page with notice and removal dates back to April 2025, though it has no entry for Mistral Large 3 or MiniMax-M2.7 (14 of 20). The terms name Stripe as payment processor and the privacy policy names regions in general terms. No sub-processor list or data location for inference was found (5 of 20)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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 at a tenth of the input price, 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).", "maintenance": "Model reading. The OpenAPI document and both SDKs were updated on 17 September 2026, and a MiniMax-M3 component joined the status page on 1 September (30). Production models get a notice of at least two to three weeks, and the recorded removals had 14 days or less (5 of 12). No removal is recorded in the last 90 days, but 13 model ids left between 9 March and 9 June 2026, and MiniMax-M2.7 is in the docs but not in the live catalogue (4 of 8). The SambaCloud release notes stop at 7 July 2026. The community forum has staff replies and a post dated 8 October 2026 (10 of 15). The Python SDK repository has no open issues and holds release pull requests only, so replies could not be judged (5 of 10). Python 1.13.0 and TypeScript 1.10.0, both 17 September 2026 (15). CI, release-please, a lock file and gitleaks scanning (8 of 10).", "payments": "No machine payment protocol (0). Per-token prices on the pricing page and in `/v1/models`, both read without a login, such as gpt-oss-120b at $0.22 in and $0.59 out per 1M tokens (20). Free tier with no payment method (20). A person signs up in the console to get a key (0).", "reliability": "Hosted reading. Status page at status.sambanova.ai on Statuspage, with components for the API gateway, the Playground and each model (20). The incident feed lists 25 incidents since launch, the latest an 8-minute Playground login fault on 25 June 2026, so nothing is posted for the last 90 days (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 (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. No `Retry-After` header was found in the docs or the OpenAPI document (10 of 15). No SLA found on the legal page or in the terms (0). Three production models are generally available, three are previews (10).", "schema": "Public OpenAPI 3.1.1 document, version 1.2.0, with 10 operations and 169 schemas, last updated 17 September 2026 (25). `llms.txt` at docs.sambanova.ai/docs/llms.txt and a Markdown copy of each page (10). 717 descriptions in the document, with feature pages for function calling, Responses, Messages and caching. When not to use a route is rarely stated (15 of 20). Typed parameters with 152 enums, 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 (13 of 15). The spec is versioned and release notes are dated, but the newest SambaCloud entry is 7 July 2026 and the models page disagrees with `/v1/models` (8 of 15).", "security": "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). No retention period is published. The product page says SambaCloud never sees or collects prompts, while the terms grant a right to store content and to use query logs (7 of 15). 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).", "transparency": "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 dated 27 May 2023 and does not name SambaCloud or API inputs, no DPA or retention period is published, and the product page's claim that prompts are never seen or collected sits beside terms that allow storing content and using query logs (10 of 30). A deprecations page with notice and removal dates back to April 2025, though it has no entry for Mistral Large 3 or MiniMax-M2.7 (14 of 20). The terms name Stripe as payment processor and the privacy policy names regions in general terms. No sub-processor list or data location for inference was found (5 of 20)." }, "sources": [ { "what": "docs index for agents", "url": "https://docs.sambanova.ai/docs/llms.txt", "seen": "2026-10-08" }, { "what": "docs robots.txt with Content-Signal", "url": "https://docs.sambanova.ai/docs/robots.txt", "seen": "2026-10-08" }, { "what": "API keys and base URL", "url": "https://docs.sambanova.ai/docs/en/get-started/api-keys-urls", "seen": "2026-10-08" }, { "what": "models and context lengths", "url": "https://docs.sambanova.ai/docs/en/models/sambacloud-models", "seen": "2026-10-08" }, { "what": "rate limits, tiers and headers", "url": "https://docs.sambanova.ai/docs/en/models/rate-limits", "seen": "2026-10-08" }, { "what": "deprecation policy and record", "url": "https://docs.sambanova.ai/docs/en/models/deprecations", "seen": "2026-10-08" }, { "what": "error codes", "url": "https://docs.sambanova.ai/docs/en/api-reference/using-the-api/api-error-codes", "seen": "2026-10-08" }, { "what": "SambaCloud release notes", "url": "https://docs.sambanova.ai/docs/en/release-notes/sambacloud", "seen": "2026-10-08" }, { "what": "function calling and structured output", "url": "https://docs.sambanova.ai/docs/en/features/function-calling", "seen": "2026-10-08" }, { "what": "prompt caching", "url": "https://docs.sambanova.ai/docs/en/features/prompt-caching", "seen": "2026-10-08" }, { "what": "Responses API limits", "url": "https://docs.sambanova.ai/docs/en/features/responses", "seen": "2026-10-08" }, { "what": "Anthropic compatibility", "url": "https://docs.sambanova.ai/docs/en/features/anthropic-compatibility", "seen": "2026-10-08" }, { "what": "live model list with prices, no key", "url": "https://api.sambanova.ai/v1/models", "seen": "2026-10-08" }, { "what": "pricing page", "url": "https://cloud.sambanova.ai/plans/pricing", "seen": "2026-10-08" }, { "what": "OpenAPI document", "url": "https://raw.githubusercontent.com/sambanova/sambanova-inference-api-spec/refs/heads/main/openapi.documented.json", "seen": "2026-10-08" }, { "what": "status incidents feed", "url": "https://status.sambanova.ai/api/v2/incidents.json", "seen": "2026-10-08" }, { "what": "status components", "url": "https://status.sambanova.ai/api/v2/components.json", "seen": "2026-10-08" }, { "what": "SambaCloud Terms of Service", "url": "https://sambanova.ai/cloud-end-user-license-agreement", "seen": "2026-10-08" }, { "what": "legal index", "url": "https://sambanova.ai/legal-agreements", "seen": "2026-10-08" }, { "what": "privacy policy", "url": "https://sambanova.ai/privacy-policy", "seen": "2026-10-08" }, { "what": "trust centre page description", "url": "https://trust.sambanova.ai/", "seen": "2026-10-08" }, { "what": "product page, data privacy claim", "url": "https://sambanova.ai/products/sambacloud", "seen": "2026-10-08" }, { "what": "security.txt (404)", "url": "https://sambanova.ai/.well-known/security.txt", "seen": "2026-10-08" }, { "what": "Python SDK repository, changelog, CI and README", "url": "https://github.com/sambanova/sambanova-python", "seen": "2026-10-08" }, { "what": "PyPI release history", "url": "https://pypi.org/pypi/sambanova/json", "seen": "2026-10-08" }, { "what": "npm release history", "url": "https://registry.npmjs.org/sambanova", "seen": "2026-10-08" }, { "what": "community forum, latest topics", "url": "https://community.sambanova.ai/latest.json", "seen": "2026-10-08" }, { "what": "domain registration", "url": "https://rdap.org/domain/sambanova.ai", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: whether calls to `MiniMax-M2.7` and `Mistral-Large-3-675B-Instruct-2512` fail. No keyed call was made. The finding rests on the pricing page and the keyless `/v1/models` response", "unchecked: the trust centre beyond its page description (it renders with JavaScript), so the SOC 2 and ISO 27001 reports, any sub-processor list and any disclosure policy were not read", "unchecked: the console after login, so key revocation, usage views and any request logs are not confirmed", "No SLA, DPA, retention period or sub-processor list was found on the legal page. Whether they exist on request is not established", "The speed claim behind `inference.fast` is the vendor's, citing Artificial Analysis. We did not measure it", "The privacy policy predates SambaCloud's September 2024 launch and does not name it. It is linked as the only privacy policy the vendor publishes", "The terms bar publishing benchmark results without written consent, which matters before our probes run" ] }, "negative": -2, "negativeNotes": [ "2026-10-08. The models and rate-limit pages list `MiniMax-M2.7` as a production model, and the July 2026 release notes say `Mistral-Large-3-675B-Instruct-2512` was promoted to production. Neither is on the pricing page or in `/v1/models`, and the deprecations page records neither. Two points, since a keyed call was not made to confirm the ids fail (https://docs.sambanova.ai/docs/en/models/sambacloud-models, https://api.sambanova.ai/v1/models)." ], "verdict": "Per-token prices and the model list are readable without a key at `/v1/models`, and a free tier needs no card. Production models get two to three weeks' notice before removal, 13 model ids left between March and June 2026, and the docs disagree with the live catalogue on MiniMax-M2.7.", "bestFor": "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.", "strengths": [ "Public OpenAPI 3.1.1 document for all 10 operations, plus `llms.txt` and a Markdown copy of every docs page", "`GET /v1/models` answers without a key and returns context length, output cap and per-token prices for each model", "Free tier with no payment method at 20 requests a minute, 20 requests a day and 200,000 tokens a day per model", "One key works with the OpenAI client, the Anthropic client (`/v1/messages`, `x-api-key`) and SambaNova's own SDKs", "Status page with a component per model and no incident posted since 25 June 2026" ], "weaknesses": [ "Production models get a notice of two to three weeks, and 13 model ids were removed between 9 March and 9 June 2026", "The docs list `MiniMax-M2.7` as a production model, while the pricing page and `/v1/models` did not list it on 8 October 2026", "`strict: true` on a JSON schema is accepted and has no effect, and the July 2026 notes record failing structured output on DeepSeek-V3.2", "Keys carry no scopes or project limits, and no key rotation guidance was found in the reviewed documentation", "The privacy policy is dated 27 May 2023, and no DPA, retention period or sub-processor list was found on the legal page" ], "agentNotes": [ "Call `GET https://api.sambanova.ai/v1/models` at start-up and use only ids it returns. The docs name models the endpoint no longer lists", "Read `x-ratelimit-remaining-requests` and `x-ratelimit-remaining-requests-day` on every response. The free tier allows 20 requests a day per model", "Treat 429 `queue_full` and 503 `maintenance` as retryable after a delay, and 410 `model_deprecated` as a signal to change model", "Validate JSON output yourself. Schema enforcement is best effort and `strict: true` changes nothing", "Check `max_completion_tokens` per model. DeepSeek-V3.1 caps output at 7,168 tokens and Llama 3.3 70B at 3,072" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.4 } ], "editorialScores": { "ergonomics": 67, "maintenance": 77, "payments": 40, "reliability": 85, "schema": 81, "security": 58, "transparency": 44 }, "provenanceScore": 81 }, "connect": { "install": "pip install sambanova # or: npm install sambanova", "http": "curl https://api.sambanova.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $SAMBANOVA_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"gpt-oss-120b\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/sambanova" }, "notable": [ "`GET https://api.sambanova.ai/v1/models` answered without a key on 8 October 2026 with six models, each with `context_length`, `max_completion_tokens` and a `pricing` object (https://api.sambanova.ai/v1/models)", "The docs list `MiniMax-M2.7` as a production model with a 192k context, and neither the pricing page nor `/v1/models` listed it on 8 October 2026. The deprecations page has no entry for it (https://docs.sambanova.ai/docs/en/models/sambacloud-models)", "The July 2026 release notes say `Mistral-Large-3-675B-Instruct-2512` was promoted to production. It is absent from the models page, the pricing page, `/v1/models` and the deprecation record (https://docs.sambanova.ai/docs/en/release-notes/sambacloud)", "The SambaCloud Terms of Service bar publishing performance results or benchmarks of the service without SambaNova's written consent, section 1.5(g) (https://sambanova.ai/cloud-end-user-license-agreement)", "The Messages API accepts the Anthropic client with `base_url` set to https://api.sambanova.ai/v1, and `/v1/messages/count_tokens` counts tokens before a call (https://docs.sambanova.ai/docs/en/features/anthropic-compatibility)", "docs.sambanova.ai/docs/robots.txt carries `Content-Signal: ai-train=yes, search=yes, ai-input=yes` (https://docs.sambanova.ai/docs/robots.txt)", "The status page lists 25 incidents since launch. The latest three are an 8-minute Playground login fault on 25 June 2026, an embedding model outage on 16 January 2026 and a 12-minute outage of the cloud on 9 January 2026 (https://status.sambanova.ai/history)" ], "area": "models", "details": [ { "label": "Endpoints", "value": "`/chat/completions`, `/completions`, `/responses`, `/messages`, `/messages/count_tokens`, `/embeddings`, `/audio/transcriptions`, `/audio/translations`, `/models` and `/models/{model_id}` under https://api.sambanova.ai/v1, per the OpenAPI document (version 1.2.0)" }, { "label": "Models on 8 October 2026", "value": "Six ids from `/v1/models` and the pricing page. gpt-oss-120b, DeepSeek-V3.1, Meta-Llama-3.3-70B-Instruct (production), and DeepSeek-V3.2, gemma-4-31B-it, MiniMax-M3 (preview). No embedding or audio model is listed" }, { "label": "Free tier", "value": "No payment method. 20 requests a minute, 20 requests a day and 200,000 tokens a day per model. MiniMax models are not in the free tier table" }, { "label": "Developer tier", "value": "Applies once a payment method is linked. 60 requests a minute and 12,000 a day on most models, 240 and 48,000 on Llama 3.3 70B, and 20M tokens a day across all models" }, { "label": "Prompt caching", "value": "Automatic on MiniMax-M3 and MiniMax-M2.7 for prefixes of 4,096 to 192,000 tokens. MiniMax-M3 cached input is $0.06 per 1M tokens against $0.60. Cache is per serving node, evicted least recently used, and not guaranteed" }, { "label": "Structured output", "value": "`response_format` takes `json_object` and `json_schema`. Schema matching is best effort, and `strict: true` is accepted with no effect" }, { "label": "Responses API", "value": "Stateless. `previous_response_id` and built-in or server-executed tools are not supported" }, { "label": "Errors", "value": "OpenAI-style `error` object with `message`, `type`, `param` and `code`, plus `request_id`. 13 documented codes, among them `context_length_exceeded`, `model_deprecated` (410), `insufficient_quota` and `queue_full` (429) and `maintenance` (503)" }, { "label": "Credentials", "value": "Bearer API key, or the same key in `x-api-key` on the Messages routes. Up to 25 keys per user, each shown once at creation" }, { "label": "Deprecation notice", "value": "Production models at least two to three weeks, preview models at short notice, by email and on the deprecations page" }, { "label": "Data use in the terms", "value": "SambaNova may access, store and process Customer Content solely to supply the service or as law requires. It may use query logs and Service Usage Data, defined as excluding Customer Content, to improve its products" }, { "label": "Certifications", "value": "SOC 2 Type 2 and ISO 27001, per the trust centre's page description. The reports and the rest of the page need JavaScript and were not read" }, { "label": "SDKs", "value": "Python `sambanova` 1.13.0 and TypeScript `sambanova` 1.10.0, both published 17 September 2026, Apache-2.0, generated by Stainless. 429 and server errors are retried twice with backoff by default" }, { "label": "Other routes", "value": "SaaS listing on AWS Marketplace with PrivateLink, and SambaStack for self-managed or hosted private deployments under separate terms" } ], "models": [ { "id": "gpt-oss-120b", "name": "GPT-OSS 120B", "inputPer1M": 0.22, "outputPer1M": 0.59, "contextTokens": 131072, "role": "default", "note": "production" }, { "id": "DeepSeek-V3.1", "name": "DeepSeek V3.1", "inputPer1M": 3, "outputPer1M": 4.5, "contextTokens": 131072, "role": "mid", "note": "production, output capped at 7,168 tokens" }, { "id": "Meta-Llama-3.3-70B-Instruct", "name": "Llama 3.3 70B", "inputPer1M": 0.6, "outputPer1M": 1.2, "contextTokens": 131072, "role": "fast", "note": "production, output capped at 3,072 tokens" } ], "deprecations": [ { "what": "`Whisper-Large-v3` and `ALLaM-7B` removed", "date": "2026-03-09", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" }, { "what": "`DeepSeek-R1-Distill-Llama-70B` removed", "date": "2026-03-20", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" }, { "what": "`DeepSeek-V3.1-Terminus`, `Qwen3-235B-A22B-Instruct-2507`, `Qwen3-32B` and `E5-Mistral-7B-Instruct` removed", "date": "2026-04-06", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" }, { "what": "`DeepSeek-V3-0324`, `DeepSeek-R1-0528` and `Meta-Llama-3.1-8B-Instruct` removed", "date": "2026-04-14", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" }, { "what": "`MiniMax-M2.5` removed from SambaCloud", "date": "2026-05-18", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" }, { "what": "`gemma-3-12b-it` and `Llama-4-Maverick-17B-128E-Instruct` removed", "date": "2026-06-09", "source": "https://docs.sambanova.ai/docs/en/models/deprecations", "kind": "shutdown" } ], "provenance": { "legalEntity": "SambaNova Systems, Inc.", "domain": "sambanova.ai", "domainRegistered": "2017-12-18", "endpointOnVendorDomain": true, "terms": "https://sambanova.ai/cloud-end-user-license-agreement", "privacy": "https://sambanova.ai/privacy-policy", "statusPage": "https://status.sambanova.ai", "changelog": "https://docs.sambanova.ai/docs/en/release-notes/sambacloud", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The SambaCloud Terms of Service name SambaNova Systems, Inc., a Delaware corporation at 2460 N. First St, Suite #100, San Jose, CA 95131, and define the Service as the SambaCloud platform. The page carries no date. The legal index says it was last updated on 5 February 2026.", "The privacy policy is the company's only one. Its last revision is dated 27 May 2023, it covers the website, communications and related services, and it does not name SambaCloud or API inputs.", "No DPA, SLA, acceptable use policy or sub-processor list is linked from https://sambanova.ai/legal-agreements.", "https://sambanova.ai/.well-known/security.txt returns 404.", "RDAP for sambanova.ai gives a registration date of 2017-12-18.", "The API answers at api.sambanova.ai and the console at cloud.sambanova.ai." ], "score": 81, "checks": [ { "check": "Legal entity named", "value": "SambaNova Systems, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "sambanova.ai, registered 2017-12-18 (8 years)", "points": 11, "max": 15, "state": "part" }, { "check": "Endpoint on the vendor's domain", "value": "api.sambanova.ai", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 4 of the 7 things a reader expects, and has 1 clause that costs points", "points": 5.4, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 8 of the 8 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "status.sambanova.ai", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ], "policies": [ { "kind": "terms", "url": "https://sambanova.ai/cloud-end-user-license-agreement", "state": "read", "readAt": "2026-10-08", "words": 4391, "points": 5.4, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": false }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "The jurisdiction and venue for litigation related to the subject matter hereof will be the state and federal courts located in Santa Clara County, California and both parties hereby submit to the personal jurisdiction of such courts.", "says": "Disputes go to the courts of Santa Clara County, California" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "(B) EACH PARTY’S AND ITS AFFILIATES’ TOTAL AGGREGATE LIABILITY FOR DAMAGES ARISING OUT OF THIS AGREEMENT SHALL NOT EXCEED THE AMOUNT ACTUALLY PAID BY CUSTOMER TO SAMBANOVA DURING THE 12 MONTH PERIOD BEFORE THE EVENT GIVING RISE TO LIABILITY AND;", "says": "Capped at the fees paid in the 12 months before the claim" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "We may suspend or restrict access if your use violates these Terms or poses a security risk." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": false }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "You must not i) Reverse-engineer, decompile, or tamper with the Services, ii) use the Services to transmit malware, spam, or unlawful content;" }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "terms.benchmark", "label": "Restricts benchmarking or competitive use", "found": true, "quote": "or (g) without our prior written consent, publish or disclose information or results relating to capabilities, performance, performance comparisons or other “benchmarking” activities relating to the Service or our infrastructure.", "costsPoints": true }, { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "If there is no Order, the Term will begin on the Effective Date and remain in effect until terminated by either party upon written notice to the other party, which it may do for any or no reason." } ], "notes": [ { "date": "2026-10-08", "text": "SambaNova may use the customer's name, logo and trademarks to identify it as a customer in marketing.", "quote": "Customer agrees that we may use Customer’s name, logo and trademarks to identify Customer as a customer of ours for marketing or promotional purposes." }, { "date": "2026-10-08", "text": "Where SambaNova terminates an Order for cause, prepaid unused tokens and compute are forfeited without refund and any unmet minimum fee commitment falls due at once.", "quote": "Conversely, any such prepaid and unused tokens, compute, units or metrics shall be forfeited without refund, and any unmet minimum Fee commitment will become immediately due, if this Agreement is terminated by us pursuant to this Section." } ] }, { "kind": "privacy", "url": "https://sambanova.ai/privacy-policy", "state": "read", "readAt": "2026-10-08", "statedDate": "2023-05-27", "words": 3729, "points": 10, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Date of Last Revision: May 27, 2023", "says": "Last updated 2023-05-27" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "We collect and have collected Personal Information about you that you affirmatively provide to us, including your:" }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "On the expiry of the applicable data retention period, we will erase or irrevocably anonymize the relevant Personal Information." }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "An IP address is a number that is automatically assigned to your computer or mobile device by your Internet service provider or mobile service provider whenever you log onto the World Wide Web or access the Internet." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "We do not sell and have not sold in the past 12 months your Personal Information.", "says": "Says it does not sell personal data" }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "Please note that you have the right to withdraw your consent at any time by sending a request using the contact details in the Section “Contact Us.”" }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "If you have reason to believe that the security of your communications or Personal Information has been compromised, please immediately notify us at: privacy@sambanova.ai", "says": "privacy@sambanova.ai" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "…an adequate level of protection, we ensure that the transfer is governed by the European Commission’s standard contractual clauses accessible here.", "says": "Relies on standard contractual clauses" } ], "toKnow": [ { "key": "old", "label": "Has not been updated for three years or more", "found": true, "quote": "Date of Last Revision: May 27, 2023" } ], "notes": [ { "date": "2026-10-08", "text": "The policy applies only to data SambaNova collects and uses in the course of its Services, a term it defines as its website, communications, notifications and related services.", "quote": "This Privacy Policy applies only to the use and collection of data by us in the course of our Services." }, { "date": "2026-10-08", "text": "The policy says automated decision-making, including profiling, may be performed on personal information.", "quote": "Please note that automated decision-making may be performed, including profiling, on the basis of your Personal Information." } ] } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/sambanova.json", "live": { "slug": "sambanova", "probe": { "target": "https://api.sambanova.ai/v1", "method": "get", "lastAt": "2026-10-09T09:27:03.720027972Z", "lastOk": true, "lastStatus": 405, "lastMs": 404, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 393, "p95ms24h": 1118, "samples24h": 20, "samples30d": 20, "days": [ { "date": "2026-10-09", "probes": 20, "ok": 20 } ] }, "vendorStatus": { "page": "https://status.sambanova.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T09:25:32.212908413Z" }, "updatedAt": "2026-10-09T09:27:03.720027972Z" } }, "verify": { "accepts": "a page on sambanova.ai or one of its subdomains, or the README of github.com/sambanova/sambanova-python", "badgeUrl": "https://www.anchorterminal.com/badges/sambanova.svg", "body": { "slug": "sambanova", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/sambanova", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/sambanova\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/sambanova.svg\" alt=\"SambaCloud on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![SambaCloud on Anchor Terminal](https://www.anchorterminal.com/badges/sambanova.svg)](https://www.anchorterminal.com/tools/sambanova)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/sambanova\"\u003eSambaCloud on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/sambanova", "json": "https://www.anchorterminal.com/tools/sambanova.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/sambanova.md", "slim": "https://www.anchorterminal.com/tools/sambanova.min.md" }, "markdown": "## Overview\n\n**Grade B · 66.4/100 · rank #269 of 842 · #7 in Model APIs \u0026 inference · not agent-ready · confidence medium**\n\n\n## Assessment\n\nPer-token prices and the model list are readable without a key at `/v1/models`, and a free tier needs no card. Production models get two to three weeks' notice before removal, 13 model ids left between March and June 2026, and the docs disagree with the live catalogue on MiniMax-M2.7.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | SambaNova Systems, Inc. (https://sambanova.ai) |\n| Kind | Model API |\n| Category | Model APIs \u0026 inference (https://www.anchorterminal.com/categories/inference) |\n| Transport | HTTP |\n| Endpoint | `https://api.sambanova.ai/v1` |\n| Auth | API key · Self-serve Bearer key from the SambaCloud console at https://cloud.sambanova.ai/apis after a browser sign-up. The Messages routes also take the same key in `x-api-key`. Up to 25 keys per user, shown once, with no scopes. |\n| Pricing | Freemium (from $0.22 / 1M in) · Free tier with no payment method, at 20 requests a minute, 20 requests a day and 200,000 tokens a day per model. Linking a card moves the account to the Developer tier, billed per token through Stripe, from $0.22 in and $0.59 out per 1M tokens on gpt-oss-120b (https://cloud.sambanova.ai/plans/pricing, checked 2026-10-08). |\n| x402 | No · No x402, MPP or L402 in the docs index, the OpenAPI document or the pricing page (checked 2026-10-08). |\n| Licence | Proprietary service under the SambaCloud Terms of Service. The SDKs and the OpenAPI document are Apache-2.0 |\n| Packages | pypi: `sambanova`; npm: `sambanova` |\n| Source | https://github.com/sambanova/sambanova-python |\n| Docs | https://docs.sambanova.ai/docs/en/get-started/overview |\n| llms.txt | https://docs.sambanova.ai/docs/llms.txt |\n| Last release | 2026-09-17 |\n| GitHub stars | 2 (as of 2026-10-08) |\n| npm downloads / week | 76 |\n| PyPI downloads / week | 6,129 |\n| Endpoints | `/chat/completions`, `/completions`, `/responses`, `/messages`, `/messages/count_tokens`, `/embeddings`, `/audio/transcriptions`, `/audio/translations`, `/models` and `/models/{model_id}` under https://api.sambanova.ai/v1, per the OpenAPI document (version 1.2.0) |\n| Models on 8 October 2026 | Six ids from `/v1/models` and the pricing page. gpt-oss-120b, DeepSeek-V3.1, Meta-Llama-3.3-70B-Instruct (production), and DeepSeek-V3.2, gemma-4-31B-it, MiniMax-M3 (preview). No embedding or audio model is listed |\n| Free tier | No payment method. 20 requests a minute, 20 requests a day and 200,000 tokens a day per model. MiniMax models are not in the free tier table |\n| Developer tier | Applies once a payment method is linked. 60 requests a minute and 12,000 a day on most models, 240 and 48,000 on Llama 3.3 70B, and 20M tokens a day across all models |\n| Prompt caching | Automatic on MiniMax-M3 and MiniMax-M2.7 for prefixes of 4,096 to 192,000 tokens. MiniMax-M3 cached input is $0.06 per 1M tokens against $0.60. Cache is per serving node, evicted least recently used, and not guaranteed |\n| Structured output | `response_format` takes `json_object` and `json_schema`. Schema matching is best effort, and `strict: true` is accepted with no effect |\n| Responses API | Stateless. `previous_response_id` and built-in or server-executed tools are not supported |\n| Errors | OpenAI-style `error` object with `message`, `type`, `param` and `code`, plus `request_id`. 13 documented codes, among them `context_length_exceeded`, `model_deprecated` (410), `insufficient_quota` and `queue_full` (429) and `maintenance` (503) |\n| Credentials | Bearer API key, or the same key in `x-api-key` on the Messages routes. Up to 25 keys per user, each shown once at creation |\n| Deprecation notice | Production models at least two to three weeks, preview models at short notice, by email and on the deprecations page |\n| Data use in the terms | SambaNova may access, store and process Customer Content solely to supply the service or as law requires. It may use query logs and Service Usage Data, defined as excluding Customer Content, to improve its products |\n| Certifications | SOC 2 Type 2 and ISO 27001, per the trust centre's page description. The reports and the rest of the page need JavaScript and were not read |\n| SDKs | Python `sambanova` 1.13.0 and TypeScript `sambanova` 1.10.0, both published 17 September 2026, Apache-2.0, generated by Stainless. 429 and server errors are retried twice with backoff by default |\n| Other routes | SaaS listing on AWS Marketplace with PrivateLink, and SambaStack for self-managed or hosted private deployments under separate terms |\n| Capabilities | inference.llm, inference.open-weights, inference.fast |\n| Tags | hosted, model, open-weights, free-tier, no-card, openapi, llms-txt, openai-compatible, anthropic-compatible, python, typescript, status-page, soc2 |\n| JSON | https://www.anchorterminal.com/api/v1/tools/sambanova.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 85 | 17.0 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 81 | 13.2 |\n| Agent ergonomics | 13% | 16.2 | 67 | 10.9 |\n| Security \u0026 auth | 14% | 17.5 | 58 | 10.2 |\n| Payments \u0026 pricing | 10% | 12.5 | 40 | 5.0 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 77 | 6.7 |\n| Transparency \u0026 trust (editorial 44, provenance 81) | 7% | 8.8 | 63 | 5.5 |\n| Negative events | up to −15 | up to −15 | 2026-10-08. The models and rate-limit pages list `MiniMax-M2.7` as a production model, and the July 2026 release notes say `Mistral-Large-3-675B-Instruct-2512` was promoted to production. Neither is on the pricing page or in `/v1/models`, and the deprecations page records neither. Two points, since a keyed call was not made to confirm the ids fail (https://docs.sambanova.ai/docs/en/models/sambacloud-models, https://api.sambanova.ai/v1/models). | -2 |\n| **Total** | | | | **66.4 → B** |\n\n### Why each score\n\n- Reliability 85: Hosted reading. Status page at status.sambanova.ai on Statuspage, with components for the API gateway, the Playground and each model (20). The incident feed lists 25 incidents since launch, the latest an 8-minute Playground login fault on 25 June 2026, so nothing is posted for the last 90 days (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 (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. No `Retry-After` header was found in the docs or the OpenAPI document (10 of 15). No SLA found on the legal page or in the terms (0). Three production models are generally available, three are previews (10).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 81: Public OpenAPI 3.1.1 document, version 1.2.0, with 10 operations and 169 schemas, last updated 17 September 2026 (25). `llms.txt` at docs.sambanova.ai/docs/llms.txt and a Markdown copy of each page (10). 717 descriptions in the document, with feature pages for function calling, Responses, Messages and caching. When not to use a route is rarely stated (15 of 20). Typed parameters with 152 enums, 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 (13 of 15). The spec is versioned and release notes are dated, but the newest SambaCloud entry is 7 July 2026 and the models page disagrees with `/v1/models` (8 of 15).\n- Agent ergonomics 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 at a tenth of the input price, 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).\n- Security \u0026 auth 58: 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). No retention period is published. The product page says SambaCloud never sees or collects prompts, while the terms grant a right to store content and to use query logs (7 of 15). 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).\n- Payments \u0026 pricing 40: No machine payment protocol (0). Per-token prices on the pricing page and in `/v1/models`, both read without a login, such as gpt-oss-120b at $0.22 in and $0.59 out per 1M tokens (20). Free tier with no payment method (20). A person signs up in the console to get a key (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 77: Model reading. The OpenAPI document and both SDKs were updated on 17 September 2026, and a MiniMax-M3 component joined the status page on 1 September (30). Production models get a notice of at least two to three weeks, and the recorded removals had 14 days or less (5 of 12). No removal is recorded in the last 90 days, but 13 model ids left between 9 March and 9 June 2026, and MiniMax-M2.7 is in the docs but not in the live catalogue (4 of 8). The SambaCloud release notes stop at 7 July 2026. The community forum has staff replies and a post dated 8 October 2026 (10 of 15). The Python SDK repository has no open issues and holds release pull requests only, so replies could not be judged (5 of 10). Python 1.13.0 and TypeScript 1.10.0, both 17 September 2026 (15). CI, release-please, a lock file and gitleaks scanning (8 of 10).\n- Transparency \u0026 trust 63: 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 dated 27 May 2023 and does not name SambaCloud or API inputs, no DPA or retention period is published, and the product page's claim that prompts are never seen or collected sits beside terms that allow storing content and using query logs (10 of 30). A deprecations page with notice and removal dates back to April 2025, though it has no entry for Mistral Large 3 or MiniMax-M2.7 (14 of 20). The terms name Stripe as payment processor and the privacy policy names regions in general terms. No sub-processor list or data location for inference was found (5 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (18 items): https://www.anchorterminal.com/fixes/sambanova.md (JSON https://www.anchorterminal.com/fixes/sambanova.json)\n\n### What we couldn't check\n\n- unchecked: whether calls to `MiniMax-M2.7` and `Mistral-Large-3-675B-Instruct-2512` fail. No keyed call was made. The finding rests on the pricing page and the keyless `/v1/models` response\n- unchecked: the trust centre beyond its page description (it renders with JavaScript), so the SOC 2 and ISO 27001 reports, any sub-processor list and any disclosure policy were not read\n- unchecked: the console after login, so key revocation, usage views and any request logs are not confirmed\n- No SLA, DPA, retention period or sub-processor list was found on the legal page. Whether they exist on request is not established\n- The speed claim behind `inference.fast` is the vendor's, citing Artificial Analysis. We did not measure it\n- The privacy policy predates SambaCloud's September 2024 launch and does not name it. It is linked as the only privacy policy the vendor publishes\n- The terms bar publishing benchmark results without written consent, which matters before our probes run\n\n### Sources\n\n- docs index for agents: \u003chttps://docs.sambanova.ai/docs/llms.txt\u003e (seen 2026-10-08)\n- docs robots.txt with Content-Signal: \u003chttps://docs.sambanova.ai/docs/robots.txt\u003e (seen 2026-10-08)\n- API keys and base URL: \u003chttps://docs.sambanova.ai/docs/en/get-started/api-keys-urls\u003e (seen 2026-10-08)\n- models and context lengths: \u003chttps://docs.sambanova.ai/docs/en/models/sambacloud-models\u003e (seen 2026-10-08)\n- rate limits, tiers and headers: \u003chttps://docs.sambanova.ai/docs/en/models/rate-limits\u003e (seen 2026-10-08)\n- deprecation policy and record: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e (seen 2026-10-08)\n- error codes: \u003chttps://docs.sambanova.ai/docs/en/api-reference/using-the-api/api-error-codes\u003e (seen 2026-10-08)\n- SambaCloud release notes: \u003chttps://docs.sambanova.ai/docs/en/release-notes/sambacloud\u003e (seen 2026-10-08)\n- function calling and structured output: \u003chttps://docs.sambanova.ai/docs/en/features/function-calling\u003e (seen 2026-10-08)\n- prompt caching: \u003chttps://docs.sambanova.ai/docs/en/features/prompt-caching\u003e (seen 2026-10-08)\n- Responses API limits: \u003chttps://docs.sambanova.ai/docs/en/features/responses\u003e (seen 2026-10-08)\n- Anthropic compatibility: \u003chttps://docs.sambanova.ai/docs/en/features/anthropic-compatibility\u003e (seen 2026-10-08)\n- live model list with prices, no key: \u003chttps://api.sambanova.ai/v1/models\u003e (seen 2026-10-08)\n- pricing page: \u003chttps://cloud.sambanova.ai/plans/pricing\u003e (seen 2026-10-08)\n- OpenAPI document: \u003chttps://raw.githubusercontent.com/sambanova/sambanova-inference-api-spec/refs/heads/main/openapi.documented.json\u003e (seen 2026-10-08)\n- status incidents feed: \u003chttps://status.sambanova.ai/api/v2/incidents.json\u003e (seen 2026-10-08)\n- status components: \u003chttps://status.sambanova.ai/api/v2/components.json\u003e (seen 2026-10-08)\n- SambaCloud Terms of Service: \u003chttps://sambanova.ai/cloud-end-user-license-agreement\u003e (seen 2026-10-08)\n- legal index: \u003chttps://sambanova.ai/legal-agreements\u003e (seen 2026-10-08)\n- privacy policy: \u003chttps://sambanova.ai/privacy-policy\u003e (seen 2026-10-08)\n- trust centre page description: \u003chttps://trust.sambanova.ai/\u003e (seen 2026-10-08)\n- product page, data privacy claim: \u003chttps://sambanova.ai/products/sambacloud\u003e (seen 2026-10-08)\n- security.txt (404): \u003chttps://sambanova.ai/.well-known/security.txt\u003e (seen 2026-10-08)\n- Python SDK repository, changelog, CI and README: \u003chttps://github.com/sambanova/sambanova-python\u003e (seen 2026-10-08)\n- PyPI release history: \u003chttps://pypi.org/pypi/sambanova/json\u003e (seen 2026-10-08)\n- npm release history: \u003chttps://registry.npmjs.org/sambanova\u003e (seen 2026-10-08)\n- community forum, latest topics: \u003chttps://community.sambanova.ai/latest.json\u003e (seen 2026-10-08)\n- domain registration: \u003chttps://rdap.org/domain/sambanova.ai\u003e (seen 2026-10-08)\n\n## Who's behind it (provenance 81/100, checked 2026-10-08)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | SambaNova Systems, Inc. | 20/20 |\n| Domain age | sambanova.ai, registered 2017-12-18 (8 years) | 11/15 |\n| Endpoint on the vendor's domain | api.sambanova.ai | 15/15 |\n| Terms of service | read, states 4 of the 7 things a reader expects, and has 1 clause that costs points | 5.4/10 |\n| Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 |\n| Status page | status.sambanova.ai | 10/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe SambaCloud Terms of Service name SambaNova Systems, Inc., a Delaware corporation at 2460 N. First St, Suite #100, San Jose, CA 95131, and define the Service as the SambaCloud platform. The page carries no date. The legal index says it was last updated on 5 February 2026.\n\nThe privacy policy is the company's only one. Its last revision is dated 27 May 2023, it covers the website, communications and related services, and it does not name SambaCloud or API inputs.\n\nNo DPA, SLA, acceptable use policy or sub-processor list is linked from https://sambanova.ai/legal-agreements.\n\nhttps://sambanova.ai/.well-known/security.txt returns 404.\n\nRDAP for sambanova.ai gives a registration date of 2017-12-18.\n\nThe API answers at api.sambanova.ai and the console at cloud.sambanova.ai.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://sambanova.ai/cloud-end-user-license-agreement), read 2026-10-08, gives no date, states 4 of the 7 things a reader expects.\n\n- To know. Restricts benchmarking or competitive use (costs points). \"or (g) without our prior written consent, publish or disclose information or results relating to capabilities, performance, performance comparisons or other “benchmarking” activities relating to the Service or our infrastructure.\"\n- To know. Says access can be ended without notice or for any reason. \"If there is no Order, the Term will begin on the Effective Date and remain in effect until terminated by either party upon written notice to the other party, which it may do for any or no reason.\"\n- Not found in the text. Gives the date it was last updated.\n- Names the governing law or courts. Disputes go to the courts of Santa Clara County, California.\n- States a limit on its liability. Capped at the fees paid in the 12 months before the claim.\n- Not found in the text. Says how changes to the terms are announced.\n- Not found in the text. Refers to a service level or uptime commitment.\n- Also in the text (2026-10-08). SambaNova may use the customer's name, logo and trademarks to identify it as a customer in marketing. \"Customer agrees that we may use Customer’s name, logo and trademarks to identify Customer as a customer of ours for marketing or promotional purposes.\"\n- Also in the text (2026-10-08). Where SambaNova terminates an Order for cause, prepaid unused tokens and compute are forfeited without refund and any unmet minimum fee commitment falls due at once. \"Conversely, any such prepaid and unused tokens, compute, units or metrics shall be forfeited without refund, and any unmet minimum Fee commitment will become immediately due, if this Agreement is terminated by us pursuant to this Section.\"\n\n**Privacy policy** (https://sambanova.ai/privacy-policy), read 2026-10-08, dated 2023-05-27, states 8 of the 8 things a reader expects.\n\n- To know. Has not been updated for three years or more. \"Date of Last Revision: May 27, 2023\"\n- Gives the date it was last updated. Last updated 2023-05-27.\n- Says whether personal data is sold or shared for advertising. Says it does not sell personal data.\n- Gives a privacy contact. privacy@sambanova.ai.\n- Says where data is transferred or stored. Relies on standard contractual clauses.\n- Also in the text (2026-10-08). The policy applies only to data SambaNova collects and uses in the course of its Services, a term it defines as its website, communications, notifications and related services. \"This Privacy Policy applies only to the use and collection of data by us in the course of our Services.\"\n- Also in the text (2026-10-08). The policy says automated decision-making, including profiling, may be performed on personal information. \"Please note that automated decision-making may be performed, including profiling, on the basis of your Personal Information.\"\n\n## Live (updated 2026-10-09 09:27 UTC)\n\n- Right now: up, HTTP 405, 404 ms, checked 2026-10-09 09:27 UTC (get on `https://api.sambanova.ai/v1`)\n- Uptime 24h 100.0% (20 probes) · 30 days 100.0% (20 probes) · p50 393 ms · p95 1.1 s\n- Vendor status page: none, All Systems Operational\n- Always current: https://www.anchorterminal.com/api/v1/live/sambanova.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Models and prices (per 1M tokens)\n\n| Model | Input | Output | Context | Role | Supports |\n| --- | --- | --- | --- | --- | --- |\n| `gpt-oss-120b` GPT-OSS 120B | $0.22 | $0.59 | 131k | default (production) | not checked |\n| `DeepSeek-V3.1` DeepSeek V3.1 | $3 | $4.50 | 131k | mid (production, output capped at 7,168 tokens) | not checked |\n| `Meta-Llama-3.3-70B-Instruct` Llama 3.3 70B | $0.60 | $1.20 | 131k | fast (production, output capped at 3,072 tokens) | not checked |\n Rate limits depend on your account tier: https://docs.sambanova.ai/docs/en/models/rate-limits\n\n## Dated changes\n\n- 2026-03-09 · Shutdown · `Whisper-Large-v3` and `ALLaM-7B` removed (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n- 2026-03-20 · Shutdown · `DeepSeek-R1-Distill-Llama-70B` removed (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n- 2026-04-06 · Shutdown · `DeepSeek-V3.1-Terminus`, `Qwen3-235B-A22B-Instruct-2507`, `Qwen3-32B` and `E5-Mistral-7B-Instruct` removed (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n- 2026-04-14 · Shutdown · `DeepSeek-V3-0324`, `DeepSeek-R1-0528` and `Meta-Llama-3.1-8B-Instruct` removed (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n- 2026-05-18 · Shutdown · `MiniMax-M2.5` removed from SambaCloud (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n- 2026-06-09 · Shutdown · `gemma-3-12b-it` and `Llama-4-Maverick-17B-128E-Instruct` removed (source: \u003chttps://docs.sambanova.ai/docs/en/models/deprecations\u003e)\n\nAll listings, as a calendar: https://www.anchorterminal.com/sunsets.ics\n\n## Strengths\n\n- Public OpenAPI 3.1.1 document for all 10 operations, plus `llms.txt` and a Markdown copy of every docs page\n- `GET /v1/models` answers without a key and returns context length, output cap and per-token prices for each model\n- Free tier with no payment method at 20 requests a minute, 20 requests a day and 200,000 tokens a day per model\n- One key works with the OpenAI client, the Anthropic client (`/v1/messages`, `x-api-key`) and SambaNova's own SDKs\n- Status page with a component per model and no incident posted since 25 June 2026\n\n## Weaknesses\n\n- Production models get a notice of two to three weeks, and 13 model ids were removed between 9 March and 9 June 2026\n- The docs list `MiniMax-M2.7` as a production model, while the pricing page and `/v1/models` did not list it on 8 October 2026\n- `strict: true` on a JSON schema is accepted and has no effect, and the July 2026 notes record failing structured output on DeepSeek-V3.2\n- Keys carry no scopes or project limits, and no key rotation guidance was found in the reviewed documentation\n- The privacy policy is dated 27 May 2023, and no DPA, retention period or sub-processor list was found on the legal page\n\n## Before you call it (notes for agents)\n\n1. Call `GET https://api.sambanova.ai/v1/models` at start-up and use only ids it returns. The docs name models the endpoint no longer lists\n2. Read `x-ratelimit-remaining-requests` and `x-ratelimit-remaining-requests-day` on every response. The free tier allows 20 requests a day per model\n3. Treat 429 `queue_full` and 503 `maintenance` as retryable after a delay, and 410 `model_deprecated` as a signal to change model\n4. Validate JSON output yourself. Schema enforcement is best effort and `strict: true` changes nothing\n5. Check `max_completion_tokens` per model. DeepSeek-V3.1 caps output at 7,168 tokens and Llama 3.3 70B at 3,072\n\n## Connect\n\nInstall:\n\n```bash\npip install sambanova # or: npm install sambanova\n```\n\nFirst request:\n\n```bash\ncurl https://api.sambanova.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $SAMBANOVA_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"gpt-oss-120b\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}]}'\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| GroqCloud | BB | 75.6 | 43 | inference.llm, inference.fast, inference.open-weights | no | https://www.anchorterminal.com/tools/groq.md |\n| Prism Inference | C | 60.1 | 479 | inference.fast, inference.open-weights, inference.llm | no | https://www.anchorterminal.com/tools/prism-inference.md |\n| Mistral AI API | BB | 71.2 | 130 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/mistral-api.md |\n| DeepInfra | B | 63 | 371 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/deepinfra.md |\n| Docker Model Runner | C | 57.1 | 559 | inference.open-weights, inference.llm | no | https://www.anchorterminal.com/tools/docker-model-runner.md |\n| Ollama | C | 56.3 | 570 | inference.open-weights, inference.llm | no | https://www.anchorterminal.com/tools/ollama.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- `GET https://api.sambanova.ai/v1/models` answered without a key on 8 October 2026 with six models, each with `context_length`, `max_completion_tokens` and a `pricing` object (source: \u003chttps://api.sambanova.ai/v1/models\u003e)\n- The docs list `MiniMax-M2.7` as a production model with a 192k context, and neither the pricing page nor `/v1/models` listed it on 8 October 2026. The deprecations page has no entry for it (source: \u003chttps://docs.sambanova.ai/docs/en/models/sambacloud-models\u003e)\n- The July 2026 release notes say `Mistral-Large-3-675B-Instruct-2512` was promoted to production. It is absent from the models page, the pricing page, `/v1/models` and the deprecation record (source: \u003chttps://docs.sambanova.ai/docs/en/release-notes/sambacloud\u003e)\n- The SambaCloud Terms of Service bar publishing performance results or benchmarks of the service without SambaNova's written consent, section 1.5(g) (source: \u003chttps://sambanova.ai/cloud-end-user-license-agreement\u003e)\n- The Messages API accepts the Anthropic client with `base_url` set to https://api.sambanova.ai/v1, and `/v1/messages/count_tokens` counts tokens before a call (source: \u003chttps://docs.sambanova.ai/docs/en/features/anthropic-compatibility\u003e)\n- docs.sambanova.ai/docs/robots.txt carries `Content-Signal: ai-train=yes, search=yes, ai-input=yes` (source: \u003chttps://docs.sambanova.ai/docs/robots.txt\u003e)\n- The status page lists 25 incidents since launch. The latest three are an 8-minute Playground login fault on 25 June 2026, an embedding model outage on 16 January 2026 and a 12-minute outage of the cloud on 9 January 2026 (source: \u003chttps://status.sambanova.ai/history\u003e)\n\n## Compare\n\n- [Claude API vs SambaCloud](https://www.anchorterminal.com/compare/anthropic-api-vs-sambanova.md): BB 77.3 vs B 66.4\n- [Antseed vs SambaCloud](https://www.anchorterminal.com/compare/antseed-vs-sambanova.md): C 55.1 vs B 66.4\n- [BlockRun.AI vs SambaCloud](https://www.anchorterminal.com/compare/blockrun-ai-vs-sambanova.md): BB 72.4 vs B 66.4\n- [DeepInfra vs SambaCloud](https://www.anchorterminal.com/compare/deepinfra-vs-sambanova.md): B 63 vs B 66.4\n- [DeepSeek API vs SambaCloud](https://www.anchorterminal.com/compare/deepseek-api-vs-sambanova.md): D 46.8 vs B 66.4\n- [Gemini Developer API vs SambaCloud](https://www.anchorterminal.com/compare/gemini-api-vs-sambanova.md): B 65.5 vs B 66.4\n- [GroqCloud vs SambaCloud](https://www.anchorterminal.com/compare/groq-vs-sambanova.md): BB 75.6 vs B 66.4\n- [Mistral AI API vs SambaCloud](https://www.anchorterminal.com/compare/mistral-api-vs-sambanova.md): BB 71.2 vs B 66.4\n- [OpenAI API vs SambaCloud](https://www.anchorterminal.com/compare/openai-api-vs-sambanova.md): A 83.3 vs B 66.4\n- [OpenRouter vs SambaCloud](https://www.anchorterminal.com/compare/openrouter-vs-sambanova.md): B 68.5 vs B 66.4\n- [Prism Inference vs SambaCloud](https://www.anchorterminal.com/compare/prism-inference-vs-sambanova.md): C 60.1 vs B 66.4\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on sambanova.ai or one of its subdomains, or the README of github.com/sambanova/sambanova-python. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"sambanova\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/sambanova\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/sambanova.svg\" alt=\"SambaCloud on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![SambaCloud on Anchor Terminal](https://www.anchorterminal.com/badges/sambanova.svg)](https://www.anchorterminal.com/tools/sambanova)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/sambanova\"\u003eSambaCloud on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say SambaCloud is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/sambanova-dark.png\n- Light: https://www.anchorterminal.com/assets/share/sambanova-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Model APIs \u0026 inference", "url": "https://www.anchorterminal.com/categories/inference" }, { "name": "SambaCloud", "url": "" } ], "description": "SambaCloud is SambaNova's hosted inference API for open-weight models running on its own RDU processors. It answers OpenAI-style chat, completions and Responses calls and Anthropic-style Messages calls, with Python and TypeScript SDKs.", "facts": [ "rank #269 of 842", "API key auth", "0 desk reviews" ], "h1": "SambaCloud", "image": "https://www.anchorterminal.com/assets/og/tools-sambanova.png", "path": "/tools/sambanova", "published": "2026-10-01", "section": "tools", "title": "SambaCloud review for AI agents, grade B (66.4/100) | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/tools/sambanova" }, "tokens": { "markdown": 8000, "slim": 1980 }, "version": 1 }