Qwen3 VL 30B A3B Instruct
prime/qwen/qwen3-vl-30b-a3b-instruct · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.33
Blended $/1M (3:1)
$0.2
Input $/1M
$0.7
Output $/1M
$0.90
1M in + 1M out
—
Cache read $/1M
#2467 of 8,066
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools text image
Same model, other providers
“Qwen3 VL 30B A3B Instruct” is offered by 7 providers — cheapest-effective first. Deep Infra is the cheapest at $0.26 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.15 | $0.6 | $0.26 | 262k |
| Kilo Gateway | $0.15 | $0.6 | $0.26 | 262k |
| OpenRouter | $0.15 | $0.6 | $0.26 | 262k |
| DevPass (LLM Gateway) | $0.15 | $0.6 | $0.26 | 262k |
| Prime Inference (this) | $0.2 | $0.7 | $0.33 | 262k |
| Novita AI | $0.2 | $0.7 | $0.33 | 131k |
| Hugging Face | $0.2 | $0.7 | $0.33 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3-vl-30b-a3b-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):