Gemini 4 Hydrogen vs MiniMax API

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.

MiniMax API 45

Model reading. MiniMax-M3.1-Flash shipped on 19 October 2026, dated on the model release page, which has no newer entry on 4 November (16 days, 30). No stated notice policy. The M2.5 and M2.7 families closed to new users on 19 October and retire on 18 November, 30 days later, and from 19 October M Plan and Token Plan requests to them are served by M3.1 Flash under the old names. We couldn't find when that notice was first posted, and the page carries the same notice on 4 November (3 of 12). Churn is high. M2.5 (February 2026) and M2.7 (March 2026) retire within nine months of release, M2.1 and M2 are already retired, and the model list still calls M2.5 and M2.7 retired on 4 November while the notice on the same page gives 18 November (2 of 8). A dated release page, support email addresses on the contact and model pages, a Discord server and GitHub issues on the model repositories. We didn't test whether they answer (10 of 15). No official SDK (0 of 15, 0 of 10). Total 45.

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.

MiniMax API 59

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use on all three formats, with tool_choice on the Anthropic format only (17 of 20). No JSON Schema output mode documented on any format (0 of 15). Caching is automatic, with cache reads at a tenth of the input price on M3.1 Flash and a token-count endpoint for sizing a request (15). 1,000,000-token context and up to 524,288 output tokens (15). No batch API found (0). No official SDK. The docs point to the Anthropic and OpenAI SDKs and the AI SDK (0). Typed error bodies with a request id on the Anthropic format and a code table, though stop_sequences is ignored without an error (12 of 15). M3.1 Flash can't turn thinking off and defaults to the deepest effort, which costs output tokens unless the caller lowers it. Total 59.

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.

MiniMax API 75

Atlassian Statuspage at status.minimax.io with Large Language Models, Text-to-Speech and Video Generation components (20). Its history pages, re-read on 4 November, now cover the whole 90 days from 6 August. They list 212 incidents on the LLM component, every one titled 'Elevated errors on Large Language Models (LLM)' and labelled major, and none states a full outage. The longest ran 65 minutes (01:15 to 02:20 UTC on 20 October, 'We are currently investigating this issue' and then resolved), and the rest closed within the hour. This run reads elevated errors with no fuller scope as partial, so minor only, frequent as they are (20). The rate-limits page publishes 200 requests and 10,000,000 tokens a minute for M3.1 Flash and M3 (15). The Anthropic-format OpenAPI file documents 429 for rate limits and 529 as an overload that can be retried, and the error-code page says to retry later on 1002, 2064 and other codes, with no Retry-After header or backoff schedule found (10). No SLA found (0). M3.1 Flash and M3 are generally available (10). Total 75.

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.

MiniMax API 30

Model reading (credential, training, retention, operator visibility, programme). One bearer key per account on the pay-as-you-go side and a separate Subscription Key for M Plan, with no scopes found. MiniMax says it may disable keys that leak publicly (20 of 30). The terms, effective 30 March 2026 and unchanged on 4 November, say MiniMax may use input and generated content to provide, maintain, develop and improve its services, and no opt-out was found. The privacy policy says only that personal data isn't used for training to profile or target consumers (0 of 20). Data is kept as long as necessary for its purpose, with no period stated and no zero-retention route (5 of 15). A usage page and balance alerts, no audit log found (5 of 15). No security.txt on platform.minimax.io (404 again on 4 November) or api.minimax.io (per the 19 October check), and no bug bounty or certification found (0 of 20). Total 30.

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.

MiniMax API 30

No x402, MPP or L402 (0). Per-token prices for M3.1 Flash and M3 are published without a login, unchanged on 4 November (20). No free tier found for the text models (0). A person signs up in a browser and tops up a balance or buys an M Plan before the first call (0). Total 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.

MiniMax API 65

Closed service with clear terms under Singapore law and SIAC arbitration. MiniMax-M3's weights, and since 23 October 2026 MiniMax-M3.1-Flash's, are on Hugging Face under the MiniMax community licence, which isn't an OSI licence and doesn't change the hosted service (15). The terms and privacy policy, both still dated 30 March 2026 on 4 November, agree on the contracting entity, that inputs and outputs are processed and may be used to improve services, and that data sits in a United States data centre, but give no retention period and no DPA was read (10 of 30). A dated retirement notice for M2.5 and M2.7 and a retired-models table, undercut by the table contradicting the notice and API release notes a year stale (12 of 20). Data location stated as the United States and an EU representative named, with third parties named only by category (10 of 20). MiniMax publishes an EU AI Act training-data summary for M3. Total 47.