GeniusRelay
Sign upConsole

Qwen: Qwen3 VL 235B A22B Thinking

qwen3-vl-235b-a22b-thinking

CompareAPIGet an API keyGet an API key

Qwen3 VL 235B A22B Thinking costs $0.650 per million input tokens and $7.80 per million output tokens, supports — context, and is available through the OpenAI-compatible API.

Qwen3 Vision‑Language model built on a 235B MoE backbone (≈22B active per token). Strong at OCR, charts/tables, multi‑image reasoning, and complex document understanding. The Thinking variant enables long‑form, chain‑of‑thought style reasoning.

Modalities

Text + Image → Text

Input / output price

$0.650 / $7.80 per 1M

Context

— · max output 33K

Capabilities

ReasoningVisionOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.650
Output$7.80
Cached input$0.325

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00819
Per day
$4.09
Per month (30 days)
$122.85

Qwen3 VL 235B A22B Thinking: input $0.65/M · output $7.8/M · cached input $0.325/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3-vl-235b-a22b-thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to qwen3-vl-235b-a22b-thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-vl-235b-a22b-thinking",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Qwen3 VL 235B A22B Thinking billed?
Input is $0.650 and output is $7.80 per million tokens; cached input is $0.325. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
— tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Qwen3 VL 235B A22B Thinking API pricing · GeniusRelay