Qwen3 VL 235B A22B Instruct
jalapeno/Qwen3-VL-235B-A22B-Instruct · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.60
Blended $/1M (3:1)
$0.3
Input $/1M
$1.5
Output $/1M
$1.80
1M in + 1M out
—
Cache read $/1M
#2600 of 6,229
Cheapest rank
- Provider
- Jalapeno Cloud (
jalapeno) - Kind
- text (outputs text)
- Context
- 129,024 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools text image
Same model, other providers
“Qwen3 VL 235B A22B Instruct” is offered by 7 providers — cheapest-effective first. LLM Gateway is the cheapest at $0.37 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| LLM Gateway | $0.2 | $0.88 | $0.37 | 262k |
| NanoGPT | $0.3 | $1.2 | $0.52 | 128k |
| Jalapeno Cloud (this) | $0.3 | $1.5 | $0.60 | 129k |
| Helicone | $0.3 | $1.5 | $0.60 | 256k |
| NovitaAI | $0.3 | $1.5 | $0.60 | 131k |
| OpenRouter | $0.21 | $1.9 | $0.63 | 262k |
| Vercel AI Gateway | $0.4 | $1.6 | $0.70 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Jalapeno Cloud and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"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):