Qwen 3.8 Flash Next API

Alibaba's Qwen 3.8 Flash Next, 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-flash-next 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-flash-next
Maker: Alibaba
Context window: 262.1K tokens
Input price: $0.200 per million tokens
Output price: $0.500 per million tokens
Providers: 1 independent provider
Regions: eu

Providers

TensorX: eu, $0.200 input and $0.500 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context

Scores

HLE: 38.0, #59 of 273
GPQA: 92.3, #22 of 250
AA-LCR: 79.7, #47 of 237
SciCode: 50.6, #52 of 123
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-flash-next",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3.8 Flash Next?: Qwen3.8-Flash-Next on NVIDIA B300 in the EU (Finland). Zero data retention.
How much does Qwen 3.8 Flash Next cost?: Offers now ask $0.200 per million input tokens and $0.500 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 Flash Next?: The largest offer takes 262,144 input tokens. One job can generate up to 64,000 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3.8 Flash Next do?: Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Qwen 3.8 Flash Next support?: Text · Images → Text.
Which providers serve Qwen 3.8 Flash Next?: 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 Flash Next?: Send "qwen3.8-flash-next" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3.8 Flash Next listed?: The exchange first listed it on 10/26/2026. This is not its release date.