Llama 3.3 70B Instruct API

Meta's Llama 3.3 70B Instruct, 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 llama-3.3-70b-instruct 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: llama-3.3-70b-instruct
Maker: Meta
Context window: 131.1K tokens
Input price: $0.200 per million tokens
Output price: $0.520 per million tokens
Providers: 1 independent provider
Regions: us-west

Providers

akash: us-west, $0.200 input and $0.520 output per million tokens, $0.100 cache read per million tokens, 131.1K tokens of context

Scores

HLE: 3.6, #255 of 273
GPQA: 49.8, #211 of 250
AA-LCR: 15.7, #220 of 237
Terminal-Bench Hard: 3.0, #150 of 166
LiveCodeBench: 28.8, #92 of 130
AIME 2025: 7.7, #94 of 100
MMLU-Pro: 71.3, #87 of 133
τ²-Bench: 26.6, #141 of 169
IFBench: 47.1, #99 of 178

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

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-instruct",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Llama 3.3 70B Instruct?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Llama 3.3 70B Instruct cost?: Offers now ask $0.200 per million input tokens and $0.520 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 Llama 3.3 70B Instruct?: The largest offer takes 131,072 input tokens. One job can generate up to 128,000 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Llama 3.3 70B Instruct do?: Its providers list JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does Llama 3.3 70B Instruct support?: Text → Text.
Which providers serve Llama 3.3 70B Instruct?: 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 Llama 3.3 70B Instruct?: Send "llama-3.3-70b-instruct" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Llama 3.3 70B Instruct listed?: The exchange first listed it on 10/8/2026. This is not its release date.