model · live

Qwen3Guard-Gen-0.6B

A generative model that frames safety classification as an instruction-following task

Qwen’s own description of the model, from Qwen3Guard-Gen-0.6B model card (pinned revision). Served here as qwen/qwen3guard-gen-0.6b.

On this roster: Pick it to moderate prompt text: safety labels at a flat price per record instead of per token. Conversation (user+assistant) moderation is coming with the next gateway release.

Qwen

What Qwen built it for

in the vendor’s words

Enables detailed risk assessment by categorizing outputs into safe, controversial, and unsafe severity levels, supporting adaptation to diverse deployment scenarios.

Quoted from Qwen3Guard-Gen-0.6B model card (pinned revision), retrieved 18 Sept 2026.

Published benchmarks

Qwen’s figures, not ours

No numeric benchmark table is reproduced here from the card retrieved 18 Sept 2026; see Qwen3Guard-Gen-0.6B model card (pinned revision) for the card in full.

Vendor usage notes

what Qwen recommends

Moderating User Prompt

Quoted from Qwen3Guard-Gen-0.6B model card (pinned revision), retrieved 18 Sept 2026.

Capacity on this endpoint

dedicated capacity, not a speed claim

context8Ktokens, the served window

concurrency8in flight, before a retryable 429

No speed figure is claimed here: this surface returns a completed specialist result, not a token stream. This surface has dedicated capacity: it is admitted up to the advertised concurrency without yielding to the generation lanes, and only beyond that concurrency does the lane cap shed with a retryable 429. That posture is the price basis.

Price

per 1,000 records · no request fee · no subscription

Rates: Qwen3Guard-Gen-0.6B
per 1,000 records
$2.00

Each item bills one record per 1,000 characters of screened prompt text, rounded up per item. A batch bills the sum; no minimum or per-request fee. Full price sheet and worked examples.

Capabilities

qwen/qwen3guard-gen-0.6b

One endpoint, one base URL

POST https://api.tiyuvta.ai/v1/moderations. Point an existingOpenAI-compatible client at it and set the model id; there is no product-specific SDK.

Prompt text in, safety labels out. Conversation (user+assistant) moderation is coming with the next gateway release

text -> labels. There is no completion token and no streaming: the response is results[] with flagged and qwen3guard safety/category labels, returned once the request finishes.

No tools, no structured output, no reasoning channel

Those are chat-model concepts; this surface takes text items in and safety labels out, nothing else.

No prompt caching

Each item bills one record per 1,000 characters of screened prompt text, rounded up per item. A batch bills the sum; no minimum or per-request fee.

Gated before it serves

Every build of this model is reconciled against the vendor’s published model and passes a live readiness and authentication gate before it takes traffic; a failing gate blocks the release.

Where it fits best

use it for

Guardrail gating on prompt text before a chat completion
Prompt safety moderation: Safety Safe/Unsafe/Controversial plus category labels; conversation (user+assistant) moderation is coming with the next gateway release
Batch screening of an array of texts: each item rounds up to whole records and a batch bills the sum, no minimum or per-request fee

Also on the same key and balance: GLM-5.3-Flash, DeepSeek-V4.1-Flash, Qwen3-Embedding-8B (16K served context), Qwen3-Reranker-8B (16K served context), Skywork-Reward-V2-Qwen3-0.6B (8K served context).

First request

qwen/qwen3guard-gen-0.6b

shell · defaulthttps://api.tiyuvta.ai/v1

curl https://api.tiyuvta.ai/v1/moderations \
  -H "Authorization: Bearer $TIYUVTA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3guard-gen-0.6b","input":"Hello"}'

The request above hits /v1/moderations directly; there is no sampling parameter on this surface.

Get an API key Agent client configurations Read the docs

Vendor sources: huggingface.co/Qwen/Qwen3Guard-Gen-0.6B, Apache-2.0. Qwen trained this model; we serve it at 8K of the judge window, below its 33K native context, on dedicated specialist capacity. Benchmark scores and usage recommendations on this page come from Qwen3Guard-Gen-0.6B model card (pinned revision), retrieved 18 Sept 2026.
Machine-readable metadata: GET https://api.tiyuvta.ai/v1/models for supported parameters, and the provider feed at GET https://api.tiyuvta.ai/models?schema=openrouter.
Rate limits: This surface has dedicated capacity, admitted up to 8 concurrent requests without yielding to the generation lanes; beyond that it sheds with a retryable 429 rather than sitting behind a per-account token ceiling.