Qwen 3.8 Omni Flash API

Alibaba's Qwen 3.8 Omni Flash, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send qwen3.8-omni-flash as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: qwen3.8-omni-flash
Maker: Alibaba
Context window: 1M tokens
Input price: $0.300 per million tokens
Output price: $0.940 per million tokens
Providers: 1 independent provider
Regions: global

Providers

EmpirioLabs AI: global, $0.300 input and $0.940 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context

Scores

HLE: 7.6, #173 of 273
GPQA: 74.2, #137 of 250
AA-LCR: 52.0, #157 of 237
Terminal-Bench Hard: 8.3, #121 of 166
τ²-Bench: 84.5, #54 of 169
IFBench: 38.0, #132 of 178
SimpleQA Verified: 20.3, #93 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-omni-flash",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3.8 Omni Flash?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Qwen 3.8 Omni Flash cost?: Offers now ask $0.300 per million input tokens and $0.940 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Qwen 3.8 Omni Flash?: The largest offer takes 1,006,592 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3.8 Omni Flash do?: Its providers list Audio input, Vision, Video input, Reasoning budget, Reasoning effort, JSON object, JSON schema, Log probabilities, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Qwen 3.8 Omni Flash support?: Text · Audio · Images · Video → Text.
Which providers serve Qwen 3.8 Omni Flash?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Qwen 3.8 Omni Flash?: Send "qwen3.8-omni-flash" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3.8 Omni Flash listed?: The exchange first listed it on 10/8/2026. This is not its release date.