Skip to content
Replicate

Meta/Llama 2 70b

Meta/Llama 2 70b is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.

Meta/Llama 2 70b Pricing & Specifications

Input Price$0.65 per 1M tokens
Output Price$2.75 per 1M tokens
Context Window4,096 tokens (4K)
Max Output4,096 tokens
ProviderReplicate

What is Meta/Llama 2 70b?

Meta/Llama 2 70b is a large language model by Replicate with a 4K context window and up to 4,096 output tokens. It costs $0.65 per 1M input tokens and $2.75 per 1M output tokens. Meta/Llama 2 70b is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.

Capabilities

text

Meta/Llama 2 70b Cost Examples

Short prompt (500 tokens)

$0.000325

Medium prompt (2K tokens)

$0.00130

Long output (4K tokens)

$0.01100

Count tokens for Meta/Llama 2 70b

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

Open Token Counter

Similar Models to Meta/Llama 2 70b

Replicate

Meta/Llama 2 70b Chat

$0.65/1M in 4K ctx

Replicate

Meta/Llama 3 70b

$0.65/1M in 8K ctx

Replicate

Meta/Llama 3 70b Instruct

$0.65/1M in 8K ctx

Replicate

Deepseek Ai/Deepseek V3.1

$0.67/1M in 164K ctx

Frequently Asked Questions

How much does Meta/Llama 2 70b cost per token? +
Meta/Llama 2 70b costs $0.65 per 1M input tokens and $2.75 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.002025.
What is the context window for Meta/Llama 2 70b? +
Meta/Llama 2 70b supports a context window of 4,096 tokens (4K). 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 2 70b? +
Meta/Llama 2 70b can generate up to 4,096 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Meta/Llama 2 70b good for coding tasks? +
Meta/Llama 2 70b can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All Replicate Models