StableCode 3B
Code Nano
Code-tuned StableCode at 3B. Cheap on-device code completion model from Stability AI.
StableCode 3B is a efficient AI model from Stability AI. It costs $0.100 per million input tokens and $0.100 per million output tokens (blended $0.100/M), with a 16,000-token context window.
INPUT
$0.100/M
per million input tokens
OUTPUT
$0.100/M
per million output tokens
CONTEXT
16,000
tokens
What it is good at
- Code-tuned
- Edge / consumer-GPU
- Open weights
Typical use cases
- On-device code completion
- Cheap IDE backends
Benchmarks
No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.
More from Stability AI
See all 3 →Frequently asked questions
How much does StableCode 3B cost?
StableCode 3B costs $0.100 per million input tokens and $0.100 per million output tokens, for a blended reference rate of $0.100 per million tokens.
What is StableCode 3B's context window?
StableCode 3B supports up to 16,000 tokens of context in a single request.
What is StableCode 3B best for?
StableCode 3B is well suited to Code-tuned, Edge / consumer-GPU and Open weights.
Who makes StableCode 3B?
StableCode 3B is developed and served by Stability AI. It was released in Mar 2024.