LLM Reference

StarCoder2 15B

Released
2024-07-04
Last refreshed
2026-06-15
Status
Researched 136d ago
DeprecatedOpen sourceCommercial use: permittedCodingClassificationJSON / Tool use

StarCoder2 15B is a legacy integration reference; keep it only while you identify a current replacement.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 8k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • New production launches
  • Vision or document-understanding workloads
Specifications
Released
2024-07-04
Context
8k
Parameters
15B
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Empowering responsible AI for efficient workflows

Santa Clara, California, United States
Founded 2003
Website
Pricing
Output / 1M
$0.200
Input / 1M
$0.200

Cheapest of 3 routes · Fireworks AI

About

StarCoder2-15B is a sophisticated large language model, expertly crafted for code generation and understanding. Developed by the BigCode project, it features 15 billion parameters and is trained on The Stack v2, a vast dataset of over 4 trillion tokens from more than 600 programming languages. Its advanced transformer decoder architecture, equipped with a grouped-query and sliding window attention mechanism and a Fill-in-the-Middle training objective, allows a context window of 16,384 tokens. In addition to generating and completing code, the model excels in tasks like code summarization and retrieving relevant snippets through natural language queries.

Top use-case fit: coding, agents, and build tasks

Coding

1 relevant benchmark in the decision map.

Classification

2 relevant benchmarks in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
HellaSwag91.710-shotObserved 2026-03-06research
HumanEval82.4pass@1Observed 2026-03-06Source
Massive Multitask Language Understanding79.85-shotObserved 2026-03-06research

Migration checks

No linked migration route is available for this model yet.