Granite 34B Code

Released
2024-05-06
Last refreshed
2026-10-13
Status
Researched 151d ago
DeprecatedOpen sourceCommercial use: permitted

Granite 34B Code is a legacy integration reference; keep it only while you identify a current replacement.

IBM Research releases · 23 in the last 12 monthsChangelog →
Specifications
Released
2024-05-06
Context
8K
Parameters
34B
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by
IBM Research

Creating reliable and adaptable AI solutions

Armonk, New York, United States
Founded 1945
Website
Pricing
Output / 1M
$0.600
Input / 1M
$0.600

Cheapest of 3 routes · IBM watsonx

Providers(3)
NVIDIA NIMRHEL AIIBM watsonx
View 3 provider routes

About

Granite 34B Code is IBM Research's Granite Code model. It is deprecated (originally released 2024-05-06); use it only for reproducing earlier results or evaluating drift over time.

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
IBM watsonx$0.600$0.600
Serverless
NVIDIA NIM--
ProvisionedPartial
RHEL AI--
ServerlessPartial

Available via routers & gateways(1)

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

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.