jishie

Qwen-Omni Turbo

alibaba/qwen-omni-turbo · family qwen · in: text, image, audio, video → out: text, audio · price provider-declared (via models.dev). Capabilities: tools text image audio video.

$0.12
Blended $/1M (3:1)
$0.07
Input $/1M
$0.27
Output $/1M
$0.34
1M in + 1M out
—
Cache read $/1M
#1055 of 7,708
Cheapest rank
Provider
Alibaba (alibaba)
Kind
text (outputs text, audio)
Context
32,768 tokens
Max output
2,048 tokens
Capabilities
tools text image audio video

Same model, other providers

“Qwen-Omni Turbo” is offered by 3 providers — cheapest-effective first. Alibaba (China) is the cheapest at $0.10 blended.

ProviderInputOutputBlendedContext
Alibaba (China)$0.058$0.23$0.1033k
Alibaba (this)$0.07$0.27$0.1233k
DevPass (LLM Gateway)$0.2$0.8$0.3533k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Alibaba and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen-omni-turbo","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Alibaba models · model index · JSON