jishie

Qwen-Omni Turbo Realtime

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

$0.47
Blended $/1M (3:1)
$0.27
Input $/1M
$1.07
Output $/1M
$1.34
1M in + 1M out
—
Cache read $/1M
#2749 of 7,712
Cheapest rank
Provider
Alibaba (alibaba)
Kind
text (outputs text, audio)
Context
32,768 tokens
Max output
2,048 tokens
Capabilities
tools text image audio

Same model, other providers

“Qwen-Omni Turbo Realtime” is offered by 2 providers — cheapest-effective first. Alibaba (China) is the cheapest at $0.40 blended.

ProviderInputOutputBlendedContext
Alibaba (China)$0.23$0.918$0.4033k
Alibaba (this)$0.27$1.07$0.4733k

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-realtime","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