Qwen: Qwen3.8 Omni Flash

Qwen

qwen/qwen3.8-omni-flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

Context

1M

Input /1M

$0.15

Output /1M

$0.47

Latency (TTFT)

1,538ms

Pricing

Per 1M tokens, in USD

Input$0.15

Output$0.47

Cache read$0.016

Specs

text inimage inaudio invideo intext out

TokenizerQwen

Max output tokens131,072

Supported parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 165 routable models

Input$0.15

Cheaper than 87% of routable models

Output$0.47

Cheaper than 90% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-omni-flash",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Qwen: Qwen3.8 Omni Flash

Qwen

qwen/qwen3.8-omni-flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

Context

1M

Input /1M

$0.15

Output /1M

$0.47

Latency (TTFT)

1,538ms

Pricing

Per 1M tokens, in USD

Input$0.15

Output$0.47

Cache read$0.016

Specs

text inimage inaudio invideo intext out

TokenizerQwen

Max output tokens131,072

Supported parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 165 routable models

Input$0.15

Cheaper than 87% of routable models

Output$0.47

Cheaper than 90% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-omni-flash",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'