Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Meta
meta-llama/llama-3.3-70b-instructCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Meta meta-llama/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). The Llama 3.3 instruction tuned text only model...
Llama 3.3 70B Instruct earns a request when it needs tool calls, running on your own hardware; a short, general request would go to MiniMax M3.1 Flash (free) instead - free per million input tokens against $0.10 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Llama 3.3 70B Instruct
targets:
- id: llama-3-3-70b-instruct
kind: llm
name: Llama 3.3 70B Instruct
metadata:
model: meta-llama/llama-3.3-70b-instruct # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 131072
cost:
usd_per_1k_tokens: 0.000210Input list price per million tokens; Llama 3.3 70B Instruct is the 4th cheapest of 8 listed.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
