← Back to all models

Llama 3.3 70b Instruct

llama-3.3-70b-instruct

Provider: Nvidia, Context: 128000, Output Limit: 4096

Available at 17 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
nvidia models-dev Input: $0.00 Output: $0.00 Provider: Nvidia, Context: 128000, Output Limit: 4096
githubmodels models-dev Input: $0.00 Output: $0.00 Provider: GitHub Models, Context: 128000, Output Limit: 32768
azure models-dev Input: $0.71 Output: $0.71 Provider: Azure, Context: 128000, Output Limit: 32768
helicone models-dev Input: $0.13 Output: $0.39 Provider: Helicone, Context: 128000, Output Limit: 16400
wandb models-dev Input: $0.71 Output: $0.71 Provider: Weights & Biases, Context: 128000, Output Limit: 32768
synthetic models-dev Input: $0.90 Output: $0.90 Provider: Synthetic, Context: 128000, Output Limit: 32768
nanogpt models-dev Input: $1.00 Output: $2.00 Provider: NanoGPT, Context: 128000, Output Limit: 8192
ionet models-dev Input: $0.13 Output: $0.38 Provider: IO.NET, Context: 128000, Output Limit: 4096
azurecognitiveservices models-dev Input: $0.71 Output: $0.71 Provider: Azure Cognitive Services, Context: 128000, Output Limit: 32768
llama models-dev Input: $0.00 Output: $0.00 Provider: Llama, Context: 128000, Output Limit: 4096
scaleway models-dev Input: $0.90 Output: $0.90 Provider: Scaleway, Context: 100000, Output Limit: 4096
azureai litellm Input: $0.71 Output: $0.71 Source: azure_ai, Context: 128000
deepinfra litellm Input: $0.23 Output: $0.40 Source: deepinfra, Context: 131072
hyperbolic litellm Input: $0.12 Output: $0.30 Source: hyperbolic, Context: 131072
metallama litellm Input: $0.00 Output: $0.00 Source: meta_llama, Context: 128000
nscale litellm Input: $0.20 Output: $0.20 Source: nscale, Context: N/A
openrouter openrouter Input: $0.10 Output: $0.32 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 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md) Context: 131072