jishie

Qwen3-ASR Flash

alibaba/qwen3-asr-flash · family qwen · in: audio → out: text · price provider-declared (via models.dev). Capabilities: audio.

$0.04
Blended $/1M (3:1)
$0.035
Input $/1M
$0.035
Output $/1M
$0.07
1M in + 1M out
—
Cache read $/1M
#655 of 7,710
Cheapest rank
Provider
Alibaba (alibaba)
Kind
text (outputs text)
Context
53,248 tokens
Max output
4,096 tokens
Capabilities
audio

Same model, other providers

“Qwen3-ASR Flash” is offered by 2 providers — cheapest-effective first. Alibaba (China) is the cheapest at $0.03 blended.

ProviderInputOutputBlendedContext
Alibaba (China)$0.032$0.032$0.0353k
Alibaba (this)$0.035$0.035$0.0453k

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":"qwen3-asr-flash","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