FactQuire

fireworks

Llama 3.3 70B Instruct

llama-v3p3-70b-instruct

Fields

provider"fireworks"
model_id"llama-v3p3-70b-instruct"
display_name"Llama 3.3 70B Instruct"
status"ga"
release_datenull
deprecation_datenull
retirement_datenull
pricing{"input_per_mtok": 0.9, "output_per_mtok": 0.9, "cached_input_per_mtok": null, "batch_discount_pct": null}
context_window_tokens131072
max_output_tokensnull
modalities{"input": ["text"], "output": ["text"]}
knowledge_cutoffnull
verified_at"2026-07-04T08:44:47Z"
notes"Provider is Fireworks serving platform; upstream model family is Meta Llama. Generic >16B serverless token tier recorded."
permalink"/models/fireworks/llama-v3p3-70b-instruct.html"

Sources

  1. https://docs.fireworks.ai/serverless/pricing

    Accessed: 2026-07-04T08:44:47Z

    Fields: pricing.input_per_mtok, pricing.output_per_mtok

    Prices below are per 1 million tokens in US dollars ... Other base models -- by size and architecture ... More than 16B parameters $0.90
  2. https://fireworks.ai/models/fireworks/llama-v3p3-70b-instruct

    Accessed: 2026-07-04T08:44:47Z

    Fields: model_id, context_window_tokens, modalities

    model path:accounts/fireworks/models/llama-v3p3-70b-instruct ... Fireworks supports a context length of 131,072 tokens ... The model is available via serverless at $0.90 per million tokens ... Support image input Not supported

Verified At

2026-07-04T08:44:47Z

Changelog History