{
  "fixes": {
    "slug": "prism-inference",
    "name": "Prism Inference",
    "listing": "https://www.anchorterminal.com/tools/prism-inference",
    "markdown": "# Fix list: Prism Inference\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/prism-inference, the October 2026 research run, assessed 8 October 2026. Grade C, 60.1 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Prism Inference: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No machine payment protocol (0). Per-token prices are on the pricing page and in the keyless `/v1/models` response, with no login (20). No free tier or trial credit was found. Billing is prepaid and a workspace without credit gets 402 (0). An agent can request a key from `POST /api/agent-signups`, but the key can't run inference until the owner supplies an emailed code, and a person funds the workspace in a browser, so half credit (10 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 2. Reliability, 65 out of 100, up to 7 more on the total\n\nWhy it scored 65: Hosted reading. Status page at status.prisminference.com on incident.io with a component for each of the two models (20). The incidents feed is empty and the page shows 100% for both models, but the service launched on 24 September 2026 and the domain dates from 9 September, so the record covers about two weeks of a 90-day window. We give half of the 30 for a clean record and say so as a departure from the checklist (15). The docs say per-key limits exist and publish no numbers, only a 4 MiB request cap (5). 429 carries `Retry-After` in seconds, errors carry a `retryable` flag, and the docs give backoff with jitter and rules for retrying interrupted streams (15). No published SLA. The terms say no guaranteed uptime without a separate written agreement, although the home page shows a '99.99% Uptime SLA' tile (0). The serverless API isn't labelled beta or preview, though the OpenAPI file is at version 0.1.0 (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Security \u0026 auth, 65 out of 100, up to 6.1 more on the total\n\nWhy it scored 65: Model reading. Bearer keys issued from account settings, with 401 for revoked or expired keys and a 30-day expiry on keys from agent sign-up. No scopes or per-key limits were found in the reviewed documentation (20 of 30). The privacy policy, the terms and the docs all say inputs and outputs are never used to train, fine-tune or evaluate models (20). Zero data retention is the default on every tier with no setting to turn on (15). The docs mention usage in the dashboard, which we did not see, and no audit log was found (5 of 15). security.txt is valid until 6 October 2027 with a contact address. No disclosure policy, bug bounty, SOC 2 or ISO 27001 was found (5 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 4. Agent ergonomics, 68 out of 100, up to 5.2 more on the total\n\nWhy it scored 68: Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI function tools, Anthropic tool-use blocks, `tool_choice` and `parallel_tool_calls` on Responses are documented (18 of 20). JSON mode and strict JSON Schema on Chat Completions, and `text.format` on Responses (15). A cache-read price is published for both models, $0.06 against $0.09 on DeepSeek-V4.1-Flash, but no page explains how caching is triggered, and the Claude Code guide says prompt-cache hints are accepted and ignored (5 of 15). 1M-token context and 384,000 output tokens on DeepSeek-V4.1-Flash, 32,768 on Gemma 4 31B (15). Batch appears on the pricing page as a sales-led tier with no API in the OpenAPI file (0). No SDK of its own. OpenAI and Anthropic clients are used with a base URL change (0). Every error carries `code`, `retryable`, `fix` and `docs_url`, which we confirmed on a live 401 (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Maintenance \u0026 community, 49 out of 100, up to 4.5 more on the total\n\nWhy it scored 49: Model reading. Gemma 4 31B was added to the catalogue on 6 October 2026 (30). No notice period is stated. The terms promise advance notice of a material breaking change 'when reasonably practicable', and nothing has been retired yet (3 of 12). No shutdowns in the service's two weeks of public life (8 of 8). A dated changelog with one entry, a Discord server and a support booking link, none of which we tested for replies (8 of 15). No SDK repository to sample. The Hermes provider plugin on GitHub has three commits, all on 15 September 2026 (0 of 10). No official SDKs (0 of 15) and no packages to assess (0 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 6. Transparency \u0026 trust, 61 out of 100, up to 3.4 more on the total\n\nMade of editorial 43, provenance 79.\n\nWhy it scored 61: Closed service with clear terms that name Prism Technologies Inc (15). The privacy policy, the terms and the zero-retention page agree on what is and isn't kept. Service metadata is kept 'only for as long as reasonably needed' with no period, and no DPA is published (20 of 30). No deprecation policy or dated notices, only the terms' advance notice 'when reasonably practicable' (3 of 20). The privacy policy says Prism is based in the United States and names vendors by category only, with no sub-processor list or regions (5 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: prisminference.com, registered 2026-09-09 (under a year) (0 of 15)\n- Terms of service: read, states 7 of the 7 things a reader expects, and has 1 clause that costs points (8 of 10)\n- Privacy policy: read, states 3 of the 8 things a reader expects (6.3 of 10)\n\n## 7. Schema \u0026 documentation, 82 out of 100, up to 2.9 more on the total\n\nWhy it scored 82: A public OpenAPI 3.1 file covering ten paths, including chat completions, responses, messages and models (25). llms.txt on both the site and the docs, a fuller llms-full.txt, and every docs page served as Markdown (10). Reference pages state what each endpoint is for and what isn't supported, such as stored responses and hosted tools, and the models page has a 'use when' column (15 of 20). `model` and `messages` are required, with ranges on `temperature` and `top_p` and an enum for reasoning effort, but `tool_choice` is untyped and `response_format` and the request body allow any extra properties (10 of 15). Examples in curl, TypeScript and Python, and an errors page with 13 status codes and five named codes with fixes (14 of 15). Paths are versioned under /v1 and the changelog is dated, with a single entry on 6 October 2026 (8 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-10-08. The home page shows a '99.99% Uptime SLA' tile, and the pricing page says 'No minimums, no rate limits' above the per-token table. The terms of 9 September 2026 say the services have no guaranteed uptime or service credit unless a separate written agreement says otherwise, and the docs describe per-key rate limits that return 429. No SLA document was found. A misleading claim, with the smallest deduction because the terms and docs state the real position (https://prisminference.com/, https://prisminference.com/pricing, https://prisminference.com/terms, https://docs.prisminference.com/rate-limits).\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: the API was not called with a key and no account was opened, so tool use, structured output, caching and speed are as documented, not observed\n- unchecked: the sign-up page and dashboard, which render only with JavaScript. Whether new accounts get any free credit, and what key controls and usage views the dashboard has, were not seen\n- unchecked: the agent sign-up endpoints, which we did not call because they create an account\n- unchecked: the throughput claim of 550 tokens a second, which is the vendor's own figure\n- Whether Gemma 4 31B is open to every account. The docs say request access, and llms.txt and the keyless catalogue say available\n- How prompt caching is triggered. A cache-read price is published and no caching page was found\n- The status page shows 100% from July 2026, before the domain was registered on 9 September 2026, so what the early part of that window measures is unclear\n- Judgement calls. Half marks for a clean incident record that is about two weeks long, half marks for agent sign-up that still needs an emailed code and browser funding, and a deduction of 2 for the home page SLA tile and the pricing page's 'no rate limits' line\n- The scout listed both models as available and had not read the pricing page. Prices are public, and the docs mark Gemma as request access\n\n## Weaknesses\n\n- Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt and the keyless catalogue list it as available\n- No rate-limit numbers are published. The docs say per-key limits exist, and the pricing page says 'no rate limits'\n- The home page shows a '99.99% Uptime SLA' tile, while the terms say there is no guaranteed uptime without a separate written agreement\n- No free tier found. Billing is prepaid, a person funds the workspace in a browser, and the agent sign-up key needs an emailed code\n- The service launched on 24 September 2026. The changelog has one entry, and no deprecation policy, sub-processor list or certification was found\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Call `GET https://api.prisminference.com/v1/models` at start-up, with no key, and use only ids it returns. Expect 403 on `gemma-4-31b` without organisation access\n- Use base URL `https://api.prisminference.com/v1` for OpenAI clients and `https://api.prisminference.com` with no `/v1` for Anthropic clients\n- Read `error.retryable` before retrying, and wait for `Retry-After` on 429, which covers both key limits and model capacity\n- Send `reasoning_effort: \"none\"` or `low` when latency matters. Reasoning is on by default and its tokens are billed as output\n- Keep conversation state yourself and send `store: false` on Responses. `previous_response_id`, stored responses and hosted tools aren't supported\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "C",
    "score": 60.1,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No machine payment protocol (0). Per-token prices are on the pricing page and in the keyless `/v1/models` response, with no login (20). No free tier or trial credit was found. Billing is prepaid and a workspace without credit gets 402 (0). An agent can request a key from `POST /api/agent-signups`, but the key can't run inference until the owner supplies an emailed code, and a person funds the workspace in a browser, so half credit (10 of 20).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 65,
        "maxGain": 7,
        "reason": "Hosted reading. Status page at status.prisminference.com on incident.io with a component for each of the two models (20). The incidents feed is empty and the page shows 100% for both models, but the service launched on 24 September 2026 and the domain dates from 9 September, so the record covers about two weeks of a 90-day window. We give half of the 30 for a clean record and say so as a departure from the checklist (15). The docs say per-key limits exist and publish no numbers, only a 4 MiB request cap (5). 429 carries `Retry-After` in seconds, errors carry a `retryable` flag, and the docs give backoff with jitter and rules for retrying interrupted streams (15). No published SLA. The terms say no guaranteed uptime without a separate written agreement, although the home page shows a '99.99% Uptime SLA' tile (0). The serverless API isn't labelled beta or preview, though the OpenAPI file is at version 0.1.0 (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 65,
        "maxGain": 6.1,
        "reason": "Model reading. Bearer keys issued from account settings, with 401 for revoked or expired keys and a 30-day expiry on keys from agent sign-up. No scopes or per-key limits were found in the reviewed documentation (20 of 30). The privacy policy, the terms and the docs all say inputs and outputs are never used to train, fine-tune or evaluate models (20). Zero data retention is the default on every tier with no setting to turn on (15). The docs mention usage in the dashboard, which we did not see, and no audit log was found (5 of 15). security.txt is valid until 6 October 2027 with a contact address. No disclosure policy, bug bounty, SOC 2 or ISO 27001 was found (5 of 20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 68,
        "maxGain": 5.2,
        "reason": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI function tools, Anthropic tool-use blocks, `tool_choice` and `parallel_tool_calls` on Responses are documented (18 of 20). JSON mode and strict JSON Schema on Chat Completions, and `text.format` on Responses (15). A cache-read price is published for both models, $0.06 against $0.09 on DeepSeek-V4.1-Flash, but no page explains how caching is triggered, and the Claude Code guide says prompt-cache hints are accepted and ignored (5 of 15). 1M-token context and 384,000 output tokens on DeepSeek-V4.1-Flash, 32,768 on Gemma 4 31B (15). Batch appears on the pricing page as a sales-led tier with no API in the OpenAPI file (0). No SDK of its own. OpenAI and Anthropic clients are used with a base URL change (0). Every error carries `code`, `retryable`, `fix` and `docs_url`, which we confirmed on a live 401 (15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 49,
        "maxGain": 4.5,
        "reason": "Model reading. Gemma 4 31B was added to the catalogue on 6 October 2026 (30). No notice period is stated. The terms promise advance notice of a material breaking change 'when reasonably practicable', and nothing has been retired yet (3 of 12). No shutdowns in the service's two weeks of public life (8 of 8). A dated changelog with one entry, a Discord server and a support booking link, none of which we tested for replies (8 of 15). No SDK repository to sample. The Hermes provider plugin on GitHub has three commits, all on 15 September 2026 (0 of 10). No official SDKs (0 of 15) and no packages to assess (0 of 10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 61,
        "maxGain": 3.4,
        "reason": "Closed service with clear terms that name Prism Technologies Inc (15). The privacy policy, the terms and the zero-retention page agree on what is and isn't kept. Service metadata is kept 'only for as long as reasonably needed' with no period, and no DPA is published (20 of 30). No deprecation policy or dated notices, only the terms' advance notice 'when reasonably practicable' (3 of 20). The privacy policy says Prism is based in the United States and names vendors by category only, with no sub-processor list or regions (5 of 20).",
        "blend": "editorial 43, provenance 79",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 82,
        "maxGain": 2.9,
        "reason": "A public OpenAPI 3.1 file covering ten paths, including chat completions, responses, messages and models (25). llms.txt on both the site and the docs, a fuller llms-full.txt, and every docs page served as Markdown (10). Reference pages state what each endpoint is for and what isn't supported, such as stored responses and hosted tools, and the models page has a 'use when' column (15 of 20). `model` and `messages` are required, with ranges on `temperature` and `top_p` and an enum for reasoning effort, but `tool_choice` is untyped and `response_format` and the request body allow any extra properties (10 of 15). Examples in curl, TypeScript and Python, and an errors page with 13 status codes and five named codes with fixes (14 of 15). Paths are versioned under /v1 and the changelog is dated, with a single entry on 6 October 2026 (8 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "prisminference.com, registered 2026-09-09 (under a year)",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 7 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 8,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 3 of the 8 things a reader expects",
        "points": 6.3,
        "max": 10
      }
    ],
    "deductions": [
      "2026-10-08. The home page shows a '99.99% Uptime SLA' tile, and the pricing page says 'No minimums, no rate limits' above the per-token table. The terms of 9 September 2026 say the services have no guaranteed uptime or service credit unless a separate written agreement says otherwise, and the docs describe per-key rate limits that return 429. No SLA document was found. A misleading claim, with the smallest deduction because the terms and docs state the real position (https://prisminference.com/, https://prisminference.com/pricing, https://prisminference.com/terms, https://docs.prisminference.com/rate-limits)."
    ],
    "unchecked": [
      "unchecked: the API was not called with a key and no account was opened, so tool use, structured output, caching and speed are as documented, not observed",
      "unchecked: the sign-up page and dashboard, which render only with JavaScript. Whether new accounts get any free credit, and what key controls and usage views the dashboard has, were not seen",
      "unchecked: the agent sign-up endpoints, which we did not call because they create an account",
      "unchecked: the throughput claim of 550 tokens a second, which is the vendor's own figure",
      "Whether Gemma 4 31B is open to every account. The docs say request access, and llms.txt and the keyless catalogue say available",
      "How prompt caching is triggered. A cache-read price is published and no caching page was found",
      "The status page shows 100% from July 2026, before the domain was registered on 9 September 2026, so what the early part of that window measures is unclear",
      "Judgement calls. Half marks for a clean incident record that is about two weeks long, half marks for agent sign-up that still needs an emailed code and browser funding, and a deduction of 2 for the home page SLA tile and the pricing page's 'no rate limits' line",
      "The scout listed both models as available and had not read the pricing page. Prices are public, and the docs mark Gemma as request access"
    ],
    "weaknesses": [
      "Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt and the keyless catalogue list it as available",
      "No rate-limit numbers are published. The docs say per-key limits exist, and the pricing page says 'no rate limits'",
      "The home page shows a '99.99% Uptime SLA' tile, while the terms say there is no guaranteed uptime without a separate written agreement",
      "No free tier found. Billing is prepaid, a person funds the workspace in a browser, and the agent sign-up key needs an emailed code",
      "The service launched on 24 September 2026. The changelog has one entry, and no deprecation policy, sub-processor list or certification was found"
    ],
    "agentNotes": [
      "Call `GET https://api.prisminference.com/v1/models` at start-up, with no key, and use only ids it returns. Expect 403 on `gemma-4-31b` without organisation access",
      "Use base URL `https://api.prisminference.com/v1` for OpenAI clients and `https://api.prisminference.com` with no `/v1` for Anthropic clients",
      "Read `error.retryable` before retrying, and wait for `Retry-After` on 429, which covers both key limits and model capacity",
      "Send `reasoning_effort: \"none\"` or `low` when latency matters. Reasoning is on by default and its tokens are billed as output",
      "Keep conversation state yourself and send `store: false` on Responses. `previous_response_id`, stored responses and hosted tools aren't supported"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "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"
  }
}