L3.1 70B Euryale V2.2 API

Meta's L3.1 70B Euryale V2.2, 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 l3.1-70b-euryale-v2.2 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: l3.1-70b-euryale-v2.2
Maker: Meta
Context window: 20.5K tokens
Input price: $0.306 per million tokens
Output price: $0.357 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.306 input and $0.357 output per million tokens, $0.306 cache read per million tokens, 20.5K tokens of context

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "l3.1-70b-euryale-v2.2",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is L3.1 70B Euryale V2.2?: L3.1 70B Euryale V2.2 is a model from Meta.
How much does L3.1 70B Euryale V2.2 cost?: Offers now ask $0.306 per million input tokens and $0.357 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 L3.1 70B Euryale V2.2?: The largest offer takes 20,480 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can L3.1 70B Euryale V2.2 do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does L3.1 70B Euryale V2.2 support?: Text → Text.
Which providers serve L3.1 70B Euryale V2.2?: 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 L3.1 70B Euryale V2.2?: Send "l3.1-70b-euryale-v2.2" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was L3.1 70B Euryale V2.2 listed?: The exchange first listed it on 10/10/2026. This is not its release date.

L3.1 70B Euryale V2.2 API

Facts

Providers

Request

Questions

Related pages