OctoML CodeLlama-70b-Instruct on OctoML (Deprecated)

Code Llama · AI at Meta

ServerlessOpen Weights

Last refreshed 2026-07-09. Next refresh: weekly.

Why use OctoML CodeLlama-70b-Instruct on OctoML (Deprecated)?

OctoML (Deprecated) offers OctoML CodeLlama-70b-Instruct with pay-as-you-go pricing at $0.40/1M input tokens. OctoML is an optimized inference platform for foundation models, offering serverless and dedicated deployment with performance tuning for production AI workloads.

Input / 1M
$0.40
Output / 1M
$0.60
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: octoml-codellama-70b-instruct
Model ID
octoml-codellama-70b-instruct

Request example

Curated snippets for this provider are not sourced yet. Use OctoML (Deprecated) documentation with model ID octoml-codellama-70b-instruct.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Pricing

TypePrice (per 1M)
Input tokens$0.40
Output tokens$0.60

Capabilities

No model capability flags are currently sourced.

About OctoML CodeLlama-70b-Instruct

OctoML CodeLlama-70b-Instruct is Meta's Code Llama model. It offers a 100K-token context window with weights openly available for self-hosting.

Get Started

DocsPortalPricing

Model Specs

Released2023-07-18
Parameters70B
Context100k
ArchitectureDecoder Only
Knowledge cutoff2022-09

Provider

OctoML (Deprecated)

OctoML

All models on OctoML (Deprecated) →Provider setup guide →