Skip to content
Metered.
Meta model

Llama 3.3 70B Instruct

API pricing per million tokens

llama-3-3-70b-instruct Open weightsChecked 8h ago
Cost calculator Compare
Input
$0.1
per 1M, DeepInfra (turbo)
Output
$0.32
per 1M tokens
Cached input
n/a
no batch tier listed
Context
131K
16K max output

Where to buy it (14)

  • DeepInfraturbo, fp8$0.1 / $0.32$0.155 blended
  • Novita AIbf16, bf16$0.135 / $0.4$0.201 blended
  • AkashMLfp8, fp8$0.2 / $0.52cached $0.1
  • Parasailfp8, fp8$0.22 / $0.5cached $0.11
  • SambaNovadefault region$0.45 / $0.9$0.563 blended
  • Groqdefault region$0.59 / $0.79cached $0.295
  • CoreWeavefp16, fp16$0.71 / $0.71cached $0.71
  • Google Vertex AIdefault region$0.72 / $0.72$0.72 blended
  • Google Vertex AIus-central1$0.72 / $0.72$0.72 blended
  • Databricks Mosaic AI Gateway + Foundation Model APIsdefault region, 7.143 DBU per 1M input tokens, 21.429 DBU per 1M output tokens$0.5 / $1.5$0.75 blended
  • IBM watsonx.aidefault region, USD 0.7526 per 1M tokens (single price listed)$0.753 / $0.753$0.753 blended
  • Cloudflare Workers AIfp8, fp8$0.293 / $2.25$0.783 blended
  • Snowflake Cortex AI (AI_COMPLETE)default region, 0.432 AI Credits per 1M input tokens, 0.432 per 1M output tokens$0.864 / $0.864$0.864 blended
  • Together AIdefault region$1.04 / $1.04$1.04 blended

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $16.40 direct.

Related models

About Llama 3.3 70B Instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.155 per 1M tokens at 3 input to 1 output.

OpenRouter listing Meta pricing page
Across fru.devCompany profile3 acquisitionsNext earnings 2026-11-04Paid biweekly4 conferences

Questions

How much does Llama 3.3 70B Instruct cost?

$0.1 per million input tokens and $0.32 per million output tokens.

What is the context window of Llama 3.3 70B Instruct?

131K tokens, with up to 16K tokens of output.

Where is Llama 3.3 70B Instruct cheapest?

Of 14 routes tracked, DeepInfra is cheapest at $0.1 input and $0.32 output per million tokens.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.