qwen/qwen3-vl-30b-a3b-thinking
novita-ai/qwen/qwen3-vl-30b-a3b-thinking · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools text image video.
$0.40
Blended $/1M (3:1)
$0.2
Input $/1M
$1
Output $/1M
$1.20
1M in + 1M out
—
Cache read $/1M
#2469 of 7,712
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools text image video
Same model, other providers
“qwen/qwen3-vl-30b-a3b-thinking” is offered by 3 providers — cheapest-effective first. This one (NovitaAI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NovitaAI (this) | $0.2 | $1 | $0.40 | 131k |
| SiliconFlow | $0.29 | $1 | $0.47 | 262k |
| SiliconFlow (China) | $0.29 | $1 | $0.47 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NovitaAI 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-thinking","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):