All models
Model card

Qwen3 VL 235B

sdn-qwen3-vl-235bGeneral purposeLive in the catalog

The economical way to give an agent vision: a 235B mixture-of-experts that reads screenshots, diagrams, and documents alongside text, priced far below the premium vision tiers. Use it for the high-volume looking — UI checks, document intake, image-heavy pipelines — and save the frontier for the judgment calls.

Context window262K tokens
Input · per Mtok$0.4
Output · per Mtok$1.6
Served bySideren engine
Where it earns its keep[01/03]
  • 01Vision at a fraction of premium prices
  • 02262K context for image-heavy work
  • 03Direct answers — no reasoning overhead
Capabilities
Tool callingYes

Strict, schema-faithful tool calls, enforced by the engine on every request — safe to build an agent loop on.

ReasoningNo

No hidden chain-of-thought: output length stays predictable, latency stays tight.

VisionYes

Reads images — screenshots, diagrams, and UI states — inline in the conversation.

Behind the endpoint[02/03]

One endpoint. Served by our engine.

Qwen3 VL 235B is served through the Sideren engine — zero-downtime serving is the design target, not a status-page apology. You request it by name; everything else is our problem.

Call it by name
curl https://api.sideren.io/v1/messages \
  -H "x-api-key: sdn_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "sdn-qwen3-vl-235b",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

OpenAI-style clients work too — send the same model name to /v1/chat/completions with a Bearer key. See the docs for both dialects.

Put your agent on real infrastructure

Your agent doesn't change.
Everything underneath does.

$export ANTHROPIC_BASE_URL=https://api.sideren.io

Start free · no card · Starter from $5/mo