Skip to content

Llama 3.3 70B Instruct

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.155

at DeepInfra

Input / output
$0.10 / $0.32
Providers
6
Spread
3.6×
7 days
0%
30 days
0%
Context
128K
Prices per 1M tokens, blended: DeepInfra (turbo) $0.155, AkashML $0.28, Parasail $0.29, Groq $0.64, CoreWeave $0.71, Cloudflare $0.783.

Providers

  • DeepInfraCheapest
    turbo
    $0.155
    $0.10 in · $0.32 out
    −29% vs ref
    128K ctx99.4% uptimefp8
  • $0.28
    $0.20 in · $0.52 out
    +29% vs ref
    128K ctx99.1% uptimefp8
  • $0.29
    $0.22 in · $0.50 out
    +33% vs ref
    128K ctx99.9% uptimefp8
  • $0.64
    $0.59 in · $0.79 out
    +194% vs ref
    128K ctx100% uptime
  • $0.71
    $0.71 in · $0.71 out
    +226% vs ref
    125K ctx100% uptimefp16
  • $0.783
    $0.293 in · $2.253 out
    +260% vs ref
    24K ctx99.4% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.218 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Other pricing

Offered byCache read
AkashML$0.10
Parasail$0.11
Groq$0.295
CoreWeave$0.71

Changes

  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • Discount price,
    25%→——
  • Output price,
    $0.90→$1.20+33.3%
  • Input price,
    $0.45→$0.60+33.3%
  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • Now served,
    Listed

About

The cheapest provider for Llama 3.3 70B Instruct is DeepInfra at $0.155 per 1M tokens (blended), charging $0.10 per 1M input and $0.32 per 1M output tokens. 6 providers serve it; the most expensive charges 3.6× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Released
Dec 6, 2024
First tracked
Oct 3, 2026
Canonical slug
meta-llama/llama-3.3-70b-instruct
Weights
meta-llama/Llama-3.3-70B-Instruct