Qwen3 VL 235B A22B Thinking

alibaba· 2025-09-23· 262K ctx· apache-2.0

API onlytool callreasoningstructured quant: unknown

spread (output)

2.1×

$2.87 – $6.00 · 13 providers

13 providers priced

Provider	Input	Output	Cache rd	Blended
Merge Gateway unknown	$0.287	$2.87	$0.057	$0.376
SiliconFlow (China) relay router	$0.450	$3.50	—	$0.728^*
SiliconFlow relay router	$0.450	$3.50	—	$0.728^*
Jalapeno Cloud relay router	$0.980	$3.95	—	$1.25^*
DevPass (LLM Gateway) relay router	$0.980	$3.95	—	$1.25^*
LLM Gateway relay router	$0.980	$3.95	—	$1.25^*
Hugging Face relay router	$0.980	$3.95	—	$1.25^*
NovitaAI relay router	$0.980	$3.95	—	$1.25^*
Kilo Gateway relay router	$0.400	$4.00	—	$0.728^*
OpenRouter unknown	$0.400	$4.00	—	$0.728^*
OrcaRouter relay router	$0.400	$4.00	—	$0.728^*
Eden AI relay router	$0.400	$4.00	—	$0.728^*
NanoGPToutlier relay router	$0.500	$6.00	$0.250	$0.841

Cheapest (output)

Merge Gateway

$2.87 /M

opencode.json

{
  "provider": {
    "merge-gateway": {
      "npm": "merge-gateway-ai-sdk-provider",
      "options": {
        "baseURL": "https://api-gateway.merge.dev/v1/ai-sdk"
      },
      "models": {
        "qwen/qwen3-vl-235b-a22b-thinking": {}
      }
    }
  }
}

Set MERGE_GATEWAY_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.