Gemini 4 Hydrogen vs Prism Inference

Gemini 4 Hydrogen 85

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 12 November 2026, recorded in Google Cloud's release notes; the Gemini API changelog, last updated 30 October, has no entry for it yet (30). Google Cloud states a minimum of 45 days' notice before Hydrogen is retired, short and stated for Cloud only; the Gemini API's deprecations give earliest dates with no stated minimum (6 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelog (15). SDK replies not sampled (5 of 10). Current SDKs; the developer guide names the minimum google-genai, @google/genai, Go and Java versions (15). Runtimes stated (10). 30 + 6 + 4 + 15 + 5 + 15 + 10 = 85.

Prism Inference 49

Model reading. Gemma 4 31B was added to the catalogue on 6 October 2026, 29 days before this check, and nothing newer is dated in the changelog or on the blog, whose newest post is of 9 September (30). No notice period is stated. The terms promise advance notice of a material breaking change 'when reasonably practicable', and no model has been retired (3 of 12). No model shutdowns since launch (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 still 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). 30+3+8+8+0 = 49.

Gemini 4 Hydrogen 90

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling, with forced calls by FunctionCallingConfig on the API (20). Structured output to a response_schema, listed as supported on the Cloud model page (13 of 15). Implicit caching on prefixes of 4,096 tokens or more with durable caching on by default and explicit caches not supported, per the Cloud model page; the announcement names no cached-input price (12 of 15). 1,048,576 tokens shared between input and output, with background long decode up to 1M (15). Batch at half price on the platform (10). Python and JavaScript SDKs, and an OpenAI-compatible Chat Completions surface (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 12 + 15 + 10 + 10 + 10 = 90.

Prism Inference 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, $0.03 against $0.09 input on DeepSeek-V4.1-Flash on 4 November, 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). The errors page (8 October) and the rate-limits page (4 November) document code, retryable, fix and docs_url on every error (15). 18+15+5+15+0+0+15 = 68.

Gemini 4 Hydrogen 45

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published, per-model limits in AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). Google Cloud's release notes and model page call Hydrogen generally available, a short-term release, under the same model ID; the Gemini API pages read don't name a stage, so full marks rest on Cloud's statement (10, a judgement call; Carbon, with no stage stated anywhere, got 5). 10 + 5 + 5 + 15 + 0 + 10 = 45.

Prism Inference 65

Hosted reading. Status page at status.prisminference.com on incident.io with a component for each of the two models, per the 8 October check (20). The 8 October incident reading came only from the page's /api/v2 incidents feed, a data endpoint this run doesn't use, so it is struck. On 4 November the status host's robots.txt answered a plain 404 (no rules), and the status page itself shows both models at 100 per cent uptime from 5 August to 3 November with "No incidents", data available only from 6 October 2026. The page has never posted an incident, and its record covers 29 days of the 90, so the short-record value applies, as for excaliclaw and serpkite (15). The rate-limits page says per-key limits exist and publishes no numbers, and a 4 MiB request cap was documented on 8 October (5). 429 carries Retry-After in seconds, errors carry a retryable flag, and the docs give bounded exponential backoff with jitter and rules for retrying interrupted streams (15). No published SLA. The terms of 9 September 2026 say the services have no guaranteed uptime or service credit without a separate written agreement, although the home page still 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). 20+15+5+15+0+10 = 65.

Gemini 4 Hydrogen 50

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). Hydrogen is on the free tier, where Google's terms say content is used to improve products and may be read by humans; paid-tier content isn't (10 of 20, the platform's reading; Carbon, paid tier only, got 15). Abuse retention has no number and new paid projects store requests by default since 26 October; Google's prompt-injection figure (2.3 times more resilient on Gray Swan's benchmark) is its own, and the model card says jailbreak resistance is still being improved (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 10 + 5 + 15 + 5 = 50.

Prism Inference 68

Model reading. Bearer keys, also accepted in x-api-key, issued by the workspace owner from the dashboard, with 401 for revoked or expired keys. No scopes or per-key limits were found in the reviewed documentation (20 of 30). The privacy policy, the terms, the docs and the security policy 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, and a security policy dated 13 October 2026 asks for vulnerability reports by email to the founders' address. No bug bounty, SOC 2 or ISO 27001 was found. robotomail, with a valid security.txt and reports by email and nothing more, holds 7 (8 of 20). 20+20+15+5+8 = 68.

Gemini 4 Hydrogen 40

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). Prices published in Google's announcement without a login, $1.50 input and $7.50 output per million tokens, flat across the window; the Gemini API pricing page, now at aistudio.google.com, is still to be read for Hydrogen's row (20). A free tier with no card: Google's announcement puts Hydrogen on all tiers of the Gemini API, and the free tier needs no billing account per the gemini-api listing; its limits for Hydrogen are on that pricing page (20). A Google account and AI Studio for a key (0). 0 + 20 + 20 + 0 = 40.

Prism Inference 30

No machine payment protocol (0). Per-token prices are on the pricing page with no login (20). No free tier or trial credit was found. Billing is prepaid and a person funds the workspace in a browser (0). Agent self-signup is closed. The docs say the legacy agent-signup endpoints return 403 signup_disabled, prisminference.com/signup redirects to the login page, and the authentication page sends new users to a sales call for access (0). 0+20+0+0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Gemini 4 Hydrogen 72

Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Free-tier content is used to improve products, paid-tier content isn't, abuse retention has no number, and request storage is on by default for new paid projects; the statements agree with each other (20 of 30). Deprecations table, and a stated 45-day minimum on Cloud (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). A DeepMind model card gives a March 2026 knowledge cutoff, automated safety results and Frontier Safety Framework outcomes, with the full safety report marked coming soon. Every benchmark figure is Google's own. 15 + 20 + 15 + 5 = 55.

Prism Inference 63

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). 15+20+3+5 = 43.