Skip to content

Perplexity · chat

codellama-70b-instruct

perplexity/codellama-70b-instruct

Input price
$0.700 / 1M tokens
Output price
$2.80 / 1M tokens
Context window
16K tokens
Lifecycle
stable

codellama-70b-instruct for OpenAI-compatible gateway routing

codellama-70b-instruct is a Perplexity chat model in the Ferro Labs live catalog with a 16K tokens context window, 16K tokens maximum output, and capabilities including Streaming.

Token pricing is listed as $0.700 / 1M tokens for input tokens and $2.80 / 1M tokens for output tokens. Route calls through the Ferro Labs AI Gateway by sending model as perplexity/codellama-70b-instruct to the OpenAI-compatible chat completions endpoint. The catalog lists this model as stable for normal gateway routing.

OpenAI-compatible usage example

curl https://api.ferrolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "perplexity/codellama-70b-instruct", "messages": [{"role": "user", "content": "Hello!"}]}'

Capabilities

  • Streaming

Modalities

Input

  • Text

Output

  • Text

More from Perplexity

Catalog prices may change. Verify current provider terms before purchasing.