Qwen3 VL 235B A22B Instruct

alibaba· 2025-09-23· 131K ctx· apache-2.0

open weights quant: unknown

spread (output)

3.0×

$0.880 – $2.66 · 20 providers

20 providers priced

Provider	Input	Output	Cache rd	Blended
DevPass (LLM Gateway) relay router	$0.200	$0.880	$0.110	$0.205
LLM Gateway relay router	$0.200	$0.880	$0.110	$0.205
Deep Infra open weights host	$0.200	$0.880	$0.110	$0.205
Kilo Gateway relay router	$0.260	$1.04	—	$0.331^*
Merge Gateway unknown	$0.287	$1.15	$0.158	$0.283
NanoGPT relay router	$0.300	$1.20	$0.150	$0.286
SiliconFlow (China) relay router	$0.300	$1.50	—	$0.409^*
NovitaAI relay router	$0.300	$1.50	—	$0.409^*
SiliconFlow relay router	$0.300	$1.50	—	$0.409^*
Helicone relay router	$0.300	$1.50	—	$0.409^*
Hugging Face relay router	$0.300	$1.50	—	$0.409^*
Jalapeno Cloud relay router	$0.300	$1.50	—	$0.409^*
LLM Gateway relay router	$0.300	$1.50	—	$0.409^*
Vercel AI Gateway unknown	$0.400	$1.60	—	$0.509^*
Eden AI relay router	$0.400	$1.60	—	$0.509^*
OrcaRouter relay router	$0.400	$1.60	—	$0.509^*
OpenRouter unknown	$0.210	$1.90	$0.100	$0.294
TensorX relay router	$0.210	$1.90	$0.052	$0.285
STACKITfp8 relay router	$1.76	$2.05	—	$1.79^*
Amazon Bedrockoutlier hyperscaler	$0.530	$2.66	—	$0.724^*

Cheapest (output)

DevPass (LLM Gateway)

$0.880 /M

opencode.json

{
  "provider": {
    "llmgateway": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.llmgateway.io/v1"
      },
      "models": {
        "qwen3-vl-235b-a22b-instruct": {}
      }
    }
  }
}

Set LLMGATEWAY_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.