CodeGemma 7B Instruct

Name: CodeGemma 7B Instruct
Author: Google DeepMind

Released

2024-04-09

Last refreshed

2026-10-07

Status

Researched 160d ago

DeprecatedOpen weightsCommercial use: restricted

CodeGemma 7B Instruct is a legacy integration reference; keep it only while you identify a current replacement.

Google DeepMind releases · 53 in the last 12 monthsChangelog →

Specifications

Family: CodeGemma
Released: 2024-04-09
Context: 8K
Parameters: 7B
Architecture: Decoder Only
Specialization: general
Openness: Open weights
License: GemmaRestricted
Weights: Unknown
Code: Unknown
Training: Fine-tuned

Created by

Google DeepMind

Pioneering artificial intelligence research.

London, United Kingdom

Founded 2014

Website

Pricing

Output / 1M

$0.200

Input / 1M

$0.200

Cheapest of 2 routes · Fireworks AI

Providers(2)

NVIDIA NIM Fireworks AI

View 2 provider routes

About

CodeGemma 7B Instruct is Google DeepMind's CodeGemma model. It is deprecated (originally released 2024-04-09); use it only for reproducing earlier results or evaluating drift over time.

Providers(2)

Compare all 2

Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
Fireworks AI	$0.200	$0.200	Provisioned
NVIDIA NIM	-	-	ProvisionedPartial

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM