Qwen3-VL 235B
stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$1.83
Blended $/1M (3:1)
$1.76
Input $/1M
$2.05
Output $/1M
$3.81
1M in + 1M out
—
Cache read $/1M
#5041 of 7,708
Cheapest rank
- Provider
- STACKIT (
stackit) - Kind
- text (outputs text)
- Context
- 218,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools text image
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at STACKIT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):