modelgrep

Cheapest Sao10K Models

Quick answer · Updated June 2026

The cheapest Sao10K model is Llama 3 8B Lunaris at $0.040 per million input tokens. Llama 3.3 Euryale 70B ($0.650) and Llama 3.1 Euryale 70B v2.2 ($0.850) round out the top three.

$0.040Input /M
74 t/sSpeed
8KContext

AI models ranked by input token price. The most affordable large language model APIs, from budget open-weight models to discounted frontier models.

  1. 1S
    l3-lunaris-8b
    JSON74 t/s · 133ms ttft · 8K ctx
    $0.040
    Input /M
  2. 2S
    l3.3-euryale-70b
    JSON9 t/s · 977ms ttft · 131K ctx
    $0.650
    Input /M
  3. 3S
    l3.1-euryale-70b
    ToolsJSON37 t/s · 281ms ttft · 131K ctx
    $0.850
    Input /M
  4. 4S
    l3.1-70b-hanami-x1
    5 t/s · 861ms ttft · 16K ctx
    $3.00
    Input /M

Frequently asked

What is the cheapest Sao10K model?

The cheapest Sao10K model is Llama 3 8B Lunaris at $0.040 per million input tokens. Llama 3.3 Euryale 70B ($0.650) and Llama 3.1 Euryale 70B v2.2 ($0.850) round out the top three.

What's a good alternative to Llama 3 8B Lunaris?

Llama 3.3 Euryale 70B ($0.650) is the closest alternative on this metric, followed by Llama 3.1 Euryale 70B v2.2 ($0.850). See the full ranking above for the tradeoffs.

How many Sao10K models are there?

modelgrep tracks 4 Sao10K models with live benchmarks, speed, latency and per-provider pricing. 4 of them qualify for this ranking.

More Sao10K rankings

All rankings