Using WizardCoder Python 34B on Replicate API
Implementation guide · WizardCoder · WizardLM Team
Replicate API exposes WizardCoder Python 34B through model ID lucataco/wizardcoder-python-34b-v1.0. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-29. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
lucataco/wizardcoder-python-34b-v1.0— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENlucataco/wizardcoder-python-34b-v1.0Replicate 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
# lucataco/wizardcoder-python-34b-v1.0 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"lucataco/wizardcoder-python-34b-v1.0",
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 | $0.20 |
| Output tokens | $1.00 |
Capabilities
About WizardCoder Python 34B
WizardCoder Python 34B is a large language model (LLM) tailored for code generation and comprehension, primarily focusing on Python. Harnessing a Transformer-based structure with 34 billion parameters, it was refined using the Evol-Instruct method to enhance its instruction-following skills. This model excels in generating accurate and context-aware code, offering functionalities like code generation, completion, summarization, and translation across languages. It has achieved notable performance in benchmarks such as HumanEval, even outperforming certain versions of GPT-4 in specific tests.