Head to head · LLM inference · October 2026 research run

Antseed vs Tencent Hy4

Tencent Hy4 scores 64 (B) on agent readiness against Antseed's 57 (C), and leads in 3 of 7 scored categories. Antseed leads on reliability, payments & pricing, maintenance & community and transparency & trust. Both do llm inference.

Best model APIs and inference for AI agents · All 1044 models comparisons

Which one, for what

Antseed C

Best for Agents and coding tools that want pay-per-request inference with no account, and owners comfortable holding USDC on Base.

Ahead on

  • Reliability, 52 against 46
  • Payments & pricing, 93 against 45
  • Maintenance & community, 79 against 73
  • Transparency & trust, 59 against 52

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

The buyer proxy copied client credential headers to sellers until v0.2.58 (12 October 2026), with no published advisory

Tencent Hy4 B

Best for Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there.

Ahead on

  • Schema & documentation, 73 against 55
  • Agent ergonomics, 86 against 56
  • Security & auth, 71 against 45

Also in its favour

  • No incidents deducted, where Antseed loses 3 points for them

Watch for

Weights, licence and system card are promised but not published; tencent/Hy4 didn't answer on Hugging Face on 11 November

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Antseed +48

Antseed 93

x402 v2 exists only on POST /v1/key/topup of a gateway the owner runs, and is off until enabled per key. Inference is paid through Antseed's own HTTP 402 flow with EIP-712 signatures and USDC channels on Base, which isn't one of the three protocols the rubric names (10 of 40, a judgement call). PRICING.md in the repository says seller prices per 1M tokens are published without authentication at a cached endpoint and live through antseed network browse --json (20); the 8 October snapshot figures came from that JSON endpoint and are struck. Free models answer with no card and no account, per the docs on 8 October (20). An agent can install the CLI, get a key generated locally and fund it by a USDC transfer, with no sign-up flow (20). The self-hosted rule gives the same three lines for the free software. Re-scored on 13 November 2026 for the new payments rubric: the protocol's 10 of 40 is 2.5 of 10, and the other lines' 60 is 90 at 30 each, so 70 is 93.

Tencent Hy4 45

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The price page, updated 9 November, lists ¥6 input, ¥0.3 cached and ¥18 output per million tokens, with Hy4 billed at 50% until 31 December 2026 (20). TokenHub's campaign of 1M free tokens per language model, read on 1 November, isn't confirmed for hy4 on the price page, so half (10 of 20, a judgement call). A person signs up with real-name verification (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Agent ergonomics Tencent Hy4 +30

Antseed 56

Model reading, as for other routers. Tool use and structured output depend on the seller, and the model list reports both per seller with conservative model-level values (12 of 20 and 8 of 15). Cached-input pricing is advertised per seller where supported (8 of 15). Context length is reported per model as the lowest value across sellers (10 of 15). No batch route found (0 of 10). No SDK of its own for buyers. OpenAI and Anthropic SDKs work against the proxy, and wrappers launch Claude Code, Codex and OpenCode (5 of 10). Documented error codes with fixes, and cost and seller headers on non-streaming responses (13 of 15). Docs per the 8 October check, not re-read on 4 November, because the terms of 9 October 2026 bar scripts that scrape or mine data from the Offerings, which include the documentation.

Tencent Hy4 86

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling is marked for hy4 in the model list (18 of 20). Structured output marked (13 of 15). Cache-hit price published, ¥0.3 against ¥6 input (14 of 15). 1M-token context with 960K input and 64K output (15). Batch at half price covered Hy3 and Hy4 preview on 1 November; whether it covers hy4 wasn't re-read (3 of 10). OpenAI and Anthropic SDKs with a changed base URL, plus Tencent Cloud's SDK and CLI for the control plane (8 of 10). Errors with code, messages, upstream status and request ID (15 of 15). 18 + 13 + 14 + 15 + 3 + 8 + 15 = 86.

Security & auth Tencent Hy4 +26

Antseed 45

Model reading. The local proxy has no key and binds to 127.0.0.1. One secp256k1 key is identity and wallet, stored in plain text by the CLI unless supplied by environment variable, and encrypted by the OS keychain in the desktop app. Spending is bounded by a deposit contract, a capped ReserveAuth per seller and an optional separate withdrawal wallet, and gateway keys are hashed, revocable and spend-limited (18 of 30). Sellers are independent, and the FAQ says a standard seller can read prompts and sets its own practices (5 of 20). No central log, and an optional TEE-verified route with attestation checked on the buyer's machine (8 of 15). Seller, token and cost headers per response, antseed buyer metering and a Prometheus exporter (12 of 15). The buyer proxy stopped forwarding client credentials to sellers in v0.2.58 (12 October 2026). No SECURITY.md in the 4 November clone; no security.txt, published advisory, bug bounty, certification or contract audit report found. The repository holds one automated review of the buyer proxy dated 8 March 2026 (2 of 20). Docs per the 8 October check, not re-read on 4 November, because the terms of 9 October 2026 bar scripts that scrape or mine data from the Offerings, which include the documentation.

Tencent Hy4 71

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Bearer keys limited by model, service, IP range and token quota, long-lived with no rotation (26 of 30). The terms say inputs aren't used to train Tencent Cloud's own models, and Hy4 is first party, so no third party's terms apply (14 of 20). Retention only as long as the service needs, no periods (7 of 15). Per-call audit logs and optional full logs to the customer's CLS (14 of 15). No security.txt; Tencent's TSRC bounty covers Tencent Cloud; no certification checked (10 of 20). 26 + 14 + 7 + 14 + 10 = 71.

Schema & documentation Tencent Hy4 +18

Antseed 55

No OpenAPI document found in the repository or docs. The proxy copies the OpenAI and Anthropic wire formats (0 of 25). llms.txt at antseed.com/llms.txt and a setup skill at /skill.md (10). The API guide states what each route is for, how routing picks a seller and when to pin one (14 of 20). Request bodies follow the upstream formats, and /v1/models reports context length, modalities, tool use and supported parameters per seller (8 of 15). Curl examples for each format and an error table with status, code, meaning and fix (13 of 15). A public changelog and tagged releases, with recent entries under an undated Unreleased heading (10 of 15). Docs per the 8 October check, not re-read on 4 November, because the terms of 9 October 2026 bar scripts that scrape or mine data from the Offerings, which include the documentation.

Tencent Hy4 73

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No OpenAPI file for inference; field pages for the OpenAI and Anthropic formats as TokenHub implements them (12 of 25). llms.txt with Markdown copies (10). The model list, updated 9 November, gives hy4's context, input and output limits and marks thinking, structured output, function calling, caching and image understanding; computer use, which Tencent's release names, isn't marked (13 of 20). Typed field pages (10 of 15). Examples in five languages and an error page of 30 codes (14 of 15). Dated release notes, with hy4 added on 4 November (14 of 15). 12 + 10 + 13 + 10 + 14 + 14 = 73.

Transparency & trust Antseed +7

Antseed 59

GPL-3.0 source for the protocol, CLI, desktop app and contracts (30). The terms (last updated 9 October 2026), FAQ and privacy page agree that there is no central request log and that sellers may log prompts. There is no privacy policy document, and docs/telemetry.md says the PostHog region and retention period are still to be documented (12 of 30). No deprecation policy found. The changelog gives version cut-offs for protocol changes and a dated cutover of 10 September 2026 for staking contracts (8 of 20). Desktop telemetry is documented event by event with a toggle and an environment switch, and is keyed to the buyer's public wallet address. No telemetry code found in the CLI (16 of 20). docs/telemetry.md is unchanged since 15 September 2026 in the 4 November clone.

Tencent Hy4 52

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service under the TokenHub terms, but Tencent's release headline calls Hy4 open source while the weights and system card are only promised 'in the coming days', with no licence stated, and tencent/Hy4 didn't answer on Hugging Face on 11 November (14 of 30). Terms and FAQ agree inputs aren't used for training; the privacy policy renders only with JavaScript and wasn't read (15 of 30). Dated retirement notices and shutdown fields (13 of 20). Processing generally in mainland China for the China site, Singapore for the international one (13 of 20). Every benchmark in the release is Tencent's own or a partner's. 14 + 15 + 13 + 13 = 55.

Reliability Antseed +6

Antseed 52

Read with the local-software lines, since the buyer runs the proxy. Official npm package @antseed/cli with Node.js 20 or later stated, plus desktop installers (20). Public CI on main runs the unit tests, an end-to-end suite and a payment flow (ci.yml in the clone), but the run results on GitHub couldn't be read on 4 November, so 15 of 25. Open issues and pull requests per the 8 October count (74 and 32), with bug reports from late September open then and reply times not sampled (12 of 25). CHANGELOG.md calls out breaking CLI changes, but versions are 0.x patch bumps and recent entries sit under one Unreleased heading (5 of 15). Release tag v0.2.72 and CLI 0.1.220 at that tag, with no statement of stability (0). Whether a request is answered also depends on which sellers are online, which this checklist doesn't score.

Tencent Hy4 46

Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No public status page (0) and so no incident record to read (5 of 30). Per-model rate limits only in the console and DescribeModelQuota (8 of 15). Six 429 codes, Retry-After and backoff advice (13 of 15). The TokenHub SLA promises 99.5% a month, and Hy4 is Tencent's own model, so the third-party exclusion doesn't apply (10). Released as hy4 on 4 November, a separate id from hy4-preview, with no preview label (10). 0 + 5 + 8 + 13 + 10 + 10 = 46.

Score by category

CategoryWeight this runAntseedTencent Hy4Edge
Reliability16%205246Antseed +6
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25573Tencent Hy4 +18
Agent ergonomics13%16.25686Tencent Hy4 +30
Security & auth14%17.54571Tencent Hy4 +26
Payments & pricing10%12.59345Antseed +48
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87973Antseed +6
Transparency & trust7%8.85952Antseed +7
Negative events≤15-30
TotalC 57/100B 64/100

Facts side by side

FactAntseedTencent Hy4
KindModel routerModel API
VendorAntseed FoundationTencent (Hy team)
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneAPI key
PricingPay per usePay per use
x402nono
LicenceGPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence fieldHosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-312026-11-04
Terms last updated2026-05-15couldn't be read
Privacy policy last updatedno document linkedcouldn't be read
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessnot found in the textcouldn't be read
Terms restrict benchmarkingnot found in the textcouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularity106 stars, 1.8k npm/wknone

How the scores have moved

Verdicts

Antseed

A buyer needs no account. The CLI creates a wallet key, free models answer at once and paid ones draw on deposited USDC, with seller, tokens and cost in response headers. Sellers are unvetted and can read prompts unless TEE-verified, the proxy forwarded client credentials to them until 12 October 2026 with no advisory, and every package is pre-1.0.

Tencent Hy4

Tencent's flagship model is on TokenHub as hy4, with a 1M-token context, image understanding, function calling and caching, at ¥6 input and ¥18 output per million tokens, half price until the end of 2026. The weights it is called open source for aren't published yet, and every benchmark is Tencent's own.

Before you call either

Antseed

  1. Send a placeholder key such as antseed-p2p, and run v0.2.58 or later, which stops credential headers reaching sellers.
  2. Call GET /v1/models first and request a concrete id. The antseed alias works only when the desktop app has a model selected
  3. Handle 402 insufficient_deposits by reading suggestedAmount, then fund the address from antseed buyer deposit with USDC on Base
  4. Pass --verifiers antseed-verifier --require-verifier to antseed buyer start when prompts are private, so only TEE-verified sellers are routed
  5. Read x-antseed-peer-id and x-antseed-estimated-cost-usd on each response, and pin a seller with <peerId>@<model> when the same one must answer

Tencent Hy4

  1. Use model id hy4 on TokenHub's OpenAI- or Anthropic-compatible endpoints; hy4-preview is a separate, older model
  2. Keep input under 960K tokens and expect at most 64K output
  3. Reuse prompt prefixes: cached input is ¥0.3 against ¥6
  4. Check the price page for the end of the 50% discount on 31 December 2026 before budgeting
  5. Read rate limits from the console or DescribeModelQuota; the public docs don't give them for chat models

Questions

Which is better for AI agents, Antseed or Tencent Hy4?

Tencent Hy4 scores 64 (B) on agent readiness against Antseed's 57 (C), and leads in 3 of 7 scored categories. Antseed leads on reliability, payments & pricing, maintenance & community and transparency & trust.

Do Antseed and Tencent Hy4 need an API key?

Antseed needs no key. Tencent Hy4 needs an API key.

Can an agent call Antseed and Tencent Hy4 without installing anything?

No hosted endpoint is listed for Antseed. No hosted endpoint is listed for Tencent Hy4.

Are Antseed and Tencent Hy4 open source?

Antseed is open source (GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field). No open-source release is listed for Tencent Hy4.

Other comparisons with Antseed or Tencent Hy4

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.