jishie

Qwen3 VL 235B A22B Instruct

vercel/alibaba/qwen3-vl-235b-a22b-instruct · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.

$0.70
Blended $/1M (3:1)
$0.4
Input $/1M
$1.6
Output $/1M
$2.00
1M in + 1M out
—
Cache read $/1M
#3485 of 7,708
Cheapest rank
Provider
Vercel AI Gateway (vercel)
Kind
text (outputs text)
Context
131,072 tokens
Max output
129,024 tokens
Capabilities
text image

Same model, other providers

“Qwen3 VL 235B A22B Instruct” is offered by 13 providers — cheapest-effective first. Deep Infra is the cheapest at $0.37 blended.

ProviderInputOutputBlendedContext
Deep Infra$0.2$0.88$0.37262k
DevPass (LLM Gateway)$0.2$0.88$0.37262k
Kilo Gateway$0.26$1.04$0.46131k
NovitaAI$0.3$1.5$0.60131k
Hugging Face$0.3$1.5$0.60131k
Jalapeno Cloud$0.3$1.5$0.60129k
Helicone$0.3$1.5$0.60256k
OpenRouter$0.21$1.9$0.63262k
NanoGPT$0.3$1.9$0.70131k
Vercel AI Gateway (this)$0.4$1.6$0.70131k
OrcaRouter$0.4$1.6$0.70131k
Eden AI$0.4$1.6$0.70131k
Amazon Bedrock$0.53$2.66$1.06262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"alibaba/qwen3-vl-235b-a22b-instruct","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Vercel AI Gateway models · model index · JSON