Skip to content
SambaNova

Meta Llama 3.3 70B Instruct

Meta Llama 3.3 70B Instruct is available via SambaNova with a 131K context window and up to 131,072 output tokens. Pricing: $0.6000/1M input tokens, $1.20/1M output tokens.

Meta Llama 3.3 70B Instruct Pricing & Specifications

Input Price$0.60 per 1M tokens
Output Price$1.20 per 1M tokens
Context Window131,072 tokens (131K)
Max Output131,072 tokens
ProviderSambaNova

What is Meta Llama 3.3 70B Instruct?

Meta Llama 3.3 70B Instruct is a large language model by SambaNova with a 131K context window and up to 131,072 output tokens. It costs $0.60 per 1M input tokens and $1.20 per 1M output tokens. Meta Llama 3.3 70B Instruct is available via SambaNova with a 131K context window and up to 131,072 output tokens. Pricing: $0.6000/1M input tokens, $1.20/1M output tokens.

Capabilities

text function calling json mode

Meta Llama 3.3 70B Instruct Cost Examples

Short prompt (500 tokens)

$0.000300

Medium prompt (2K tokens)

$0.00120

Long output (4K tokens)

$0.00480

Count tokens for Meta Llama 3.3 70B Instruct

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Meta Llama 3.3 70B Instruct

SambaNova

Llama 4 Maverick 17B 128E Instruct

$0.63/1M in 131K ctx

SambaNova

QwQ 32B

$0.50/1M in 16K ctx

SambaNova

Qwen2 Audio 7B Instruct

$0.50/1M in 4K ctx

SambaNova

DeepSeek R1 Distill Llama 70B

$0.70/1M in 131K ctx

Frequently Asked Questions

How much does Meta Llama 3.3 70B Instruct cost per token? +
Meta Llama 3.3 70B Instruct costs $0.60 per 1M input tokens and $1.20 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.001200.
What is the context window for Meta Llama 3.3 70B Instruct? +
Meta Llama 3.3 70B Instruct supports a context window of 131,072 tokens (131K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Meta Llama 3.3 70B Instruct? +
Meta Llama 3.3 70B Instruct can generate up to 131,072 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Meta Llama 3.3 70B Instruct good for coding tasks? +
Yes, Meta Llama 3.3 70B Instruct supports capabilities well-suited for coding tasks including code generation, debugging, and refactoring.
Token Counter | Pricing Calculator | Model Comparison | All SambaNova Models