Using Stable LM 7B on Replicate API
Implementation guide · StableLM · Stability AI
Replicate API exposes Stable LM 7B through model ID stable-lm-7b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-22. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
stable-lm-7b— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENstable-lm-7bReplicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
import replicate
# reads REPLICATE_API_TOKEN from env
# stable-lm-7b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"stable-lm-7b",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.05 |
| Output tokens | $0.25 |
Capabilities
No model capability flags are currently sourced.
About Stable LM 7B
StableLM 7B, a large language model by Stability AI, features a 7-billion parameter, decoder-only architecture designed to predict subsequent words based on context. Built on the robust NeoX transformer framework, it excels in managing long text sequences with its 4096-token context window. Pre-trained on a substantial dataset of about 1.5 trillion tokens, this model demonstrates strong capabilities in generating human-like text, performing tasks such as summarization and translation. However, it shares common limitations with other LLMs, including the potential for bias and generating inappropriate content.