Models.dev

An open-source database of AI models

Llama-3.3-70B-Instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

meta/llama-3.3-70b-instruct
Lab
Meta
Family
llama
Providers
29
Context
128,000
Output limit
4,096
Knowledge
2023-12
Release
2024-12-06
Updated
2024-12-06
Weights
Open
Input
Output types
Capabilities
tools, temperature

Providers

29
Provider Lab Model ID Context Output Price Reasoning Tool Call Structured Temperature
AbacusMetameta-llama/Meta-Llama-3.3-70B-Instruct131,0728,192$0.59 / $0.79NoYes-Yes
Amazon BedrockMetameta.llama3-3-70b-instruct-v1:0128,0004,096$0.72 / $0.72NoYes-Yes
Amazon BedrockMetaus.meta.llama3-3-70b-instruct-v1:0128,0004,096$0.72 / $0.72NoYes-Yes
Charm HyperMetallama-3.3-70b-instruct128,00012,800$0.61 / $1.04NoYes-Yes
Cloudflare Workers AIMeta@cf/meta/llama-3.3-70b-instruct-fp8-fast24,00024,000$0.29 / $2.25NoYesNoYes
CortecsMetallama-3.3-70b-instruct131,000131,000$0.13 / $0.40NoYesYesYes
CrusoeMetameta-llama/Llama-3.3-70B-Instruct128,0004,096$0.25 / $0.75NoYes-Yes
DevPass (LLM Gateway)Metallama-3.3-70b-instruct131,0724,096$0.14 / $0.40NoYes-Yes
Eden AIMetadeepinfra/meta-llama/Llama-3.3-70B-Instruct131,0724,096$0.10 / $0.32NoYesYesYes
Eden AIMetaionos/meta-llama/Llama-3.3-70B-Instruct128,0004,096$0.75 / $0.75NoNoNoYes
Eden AIMetanebius/meta-llama/Llama-3.3-70B-Instruct131,0724,096$0.13 / $0.40NoYesYesYes
Eden AIMetascaleway/llama-3.3-70b-instruct128,0004,096$1.04 / $1.04NoYesNoYes
evrocMetanvidia/Llama-3.3-70B-Instruct-FP8128,0004,096$1.15 / $1.15NoYes-Yes
GreenPTMetallama-3.3-70b-instruct100,00016,384$1.25 / $1.25NoYes-Yes
Hugging FaceMetameta-llama/Llama-3.3-70B-Instruct131,0724,096$0.59 / $0.79NoYesYesYes
Kilo GatewayMetameta-llama/llama-3.3-70b-instruct131,07216,384$0.10 / $0.32NoYesYesYes
LLM GatewayMetacerebras/llama-3.3-70b-instruct128,0004,096$0.85 / $1.20NoYesNoYes
LLM GatewayMetanovita/llama-3.3-70b-instruct131,072120,000$0.14 / $0.40NoYesNoYes
Merge GatewayMetameta/llama-3.3-70b-instruct131,07232,768$0.22 / $0.50NoYesNoYes
NanoGPTMetameta-llama/llama-3.3-70b-instruct131,07216,384$0.05 / $0.23NoYesYesYes
NeonMetameta-llama-3-3-70b-instruct128,0008,192$0.50 / $1.50NoYesYesYes
NvidiaMetameta/llama-3.3-70b-instruct128,0004,096$0.00 / $0.00NoYesYesYes
OpenRouterMetameta-llama/llama-3.3-70b-instruct131,07216,384$0.10 / $0.32NoYesYesYes
PendraMetallama3.3:70b128,0004,096$0.00 / $0.00NoYes-Yes
PioneerMetameta-llama/Llama-3.3-70B-Instruct16,38416,384$0.90 / $0.90NoYes-Yes
Snowflake CortexMetasnowflake-llama3.3-70b128,0004,096-NoYes-Yes
TinfoilMetallama3-3-70b131,0724,096$1.75 / $2.75NoYes-Yes
watsonx.aiMetameta-llama/llama-3-3-70b-instruct131,0724,096$0.75 / $0.75NoYes-Yes
Weights & BiasesMetameta-llama/Llama-3.3-70B-Instruct128,000128,000$0.71 / $0.71NoYesYesYes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

The homepage starts with provider-agnostic model metadata. Model pages list the providers serving that model; provider pages list every model available from that provider; lab pages group canonical models by author.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

SDK

Use the SDK to query the API from your app. It's type-safe and exports the latest snapshot for offline use.

Contribute

The data is stored in GitHub as TOML files organized by provider and canonical model.