Qwen3 235B-A22B

alibaba· 2025-04· 41K ctx· apache-2.0

open weights quant: unknown

spread (output)

5.7×

$0.500 – $2.86 · 12 providers

12 providers priced

Provider	Input	Output	Cache rd	Blended
iFlow relay router	free/—	free/—	—	free/—
NanoGPT relay router	$0.300	$0.500	$0.150	$0.223
LLM Gatewayfp8 relay router	$0.200	$0.800	—	$0.255^*
Hugging Face relay router	$0.200	$0.800	—	$0.255^*
NovitaAIfp8 relay router	$0.200	$0.800	—	$0.255^*
DevPass (LLM Gateway)fp8 relay router	$0.200	$0.800	—	$0.255^*
Jiekou.AIfp8 relay router	$0.200	$0.800	—	$0.255^*
Alibaba (China) relay router	$0.287	$1.15	—	$0.365^*
Merge Gateway unknown	$0.287	$1.15	$0.057	$0.219
OpenRouter unknown	$0.455	$1.82	—	$0.579^*
Kilo Gateway relay router	$0.455	$1.82	—	$0.579^*
Alibaba first party lab	$0.700	$2.80	—	$0.891^*
302.AI relay router	$0.290	$2.86	—	$0.524^*

Cheapest (output)

NanoGPT

$0.500 /M

opencode.json

{
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "qwen/qwen3-235b-a22b": {}
      }
    }
  }
}

Set NANO_GPT_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.