LiteLLM vs Tencent Cloud TokenHub

LiteLLM 60

Read with the self-hosted rule, since an agent uses the free gateway and Enterprise is a sales-led licence for the same software. No x402, MPP or L402 (0). MIT with no account and no card, so 20, 20 and 20 on the last three lines. Model calls cost what the operator's provider keys cost.

Tencent Cloud TokenHub 35

No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by thcli auth login, but only from that account (0).

LiteLLM 70

Read with the local-software lines, since the gateway runs on the operator's hardware and BerriAI hosts nothing an agent calls. litellm on PyPI states Python 3.10 to 3.14, and the gateway ships as a Docker image, a Helm chart and Terraform modules, with GHCR images signed by cosign (20). 51 GitHub Actions workflows plus a CircleCI config cover unit, proxy-database, end-to-end, chaos, mutation and UI tests. The GitHub API was rate-limited for our reader on 6 November and Actions pages refused it on 6 October, so we couldn't confirm main is passing (15 of 25). The issue tracker showed 1,674 open issues on 6 November, with eight bug reports among the 15 newest, seven of them with a reply, against a project that tags several releases a day (10 of 25, down from an unchecked 12). Release notes carry breaking-change bullets, but breaking changes land in weekly minor releases on the 1.x line, so version numbers don't signal them (10 of 15). 1.108.1, past 1.0 (15).

Tencent Cloud TokenHub 46

Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry Retry-After and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10).

LiteLLM 91

Every gateway serves Swagger at /, ReDoc at /redoc and the raw schema at /openapi.json, and the docs host a public Swagger explorer (25). llms.txt, llms-full.txt and a Markdown twin of every page via .md (10). Pages say what a feature is for and where its limits are, and the key-auth page explains how permissions are inherited and where they aren't, but the reference is very large for a model to navigate (16 of 20). OpenAI-shaped request schemas from Pydantic models, with metadata, litellm_params and config blocks left as free-form objects (10 of 15). A full error reference with the envelope, every status, response headers and how to tell gateway limits from provider limits, plus examples on every page (15). Release notes per version with dates, newest v1.108.0 and v1.106.7 on 4 November 2026 (15).

Tencent Cloud TokenHub 73

Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use deepseek-v3, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry /v1, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).

LiteLLM 82

v1.108.1 tagged on 5 November 2026, v1.108.0 and v1.106.7 on 3 and 4 November (30). 125 tags between 8 August and 6 November, stable, patch, release-candidate and dev builds, with patch releases for four minor lines at once (20). Reply times not measured. On the issues page 7 of the 15 newest had a reply on the day, workflows auto-close duplicates and label issues, and Discord is the listed community channel (12 of 25). The package is the official SDK, current, with OpenAI and Anthropic SDKs working against the gateway (12 of 15). Dependency and image scanning (OSV, zizmor, Scorecard, grype) run in CI, with pass state unchecked (8 of 10).

Tencent Cloud TokenHub 73

Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q&A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and tencent-tokenhub-cli 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).

LiteLLM 63

MIT for everything outside enterprise/, which has its own licence (25 of 30). The data security page (updated 6 November 2026) and security.md agree that a self-hosted gateway sends no data or telemetry to BerriAI, and the gateway stores prompts and spend in the operator's own Postgres. We found no terms of service or privacy policy on litellm.ai for its site, trial or Enterprise licence (20 of 30). A version support policy since 29 June 2026 (four stable minor lines), deprecated pages labelled in the docs, and release notes with breaking-change bullets (15 of 20). Usage telemetry, new in v1.107.0, is off by default, lists every field it can send and goes only to a table or endpoint the operator sets. A main-branch commit of 23 October 2026 made the Admin UI chat post a hashed user id to chat-telemetry.litellm.ai, and it was removed on 24 October before any tagged release contained it, so it isn't deducted. The start-up fetch of the price map from GitHub is documented with an opt-out (17 of 20).

Tencent Cloud TokenHub 54

Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a pre-offline status in /v1/models and a DiscontinuedAt field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20).