Last refreshed 2026-09-21. Next refresh: weekly.
Why use Phi-3 Mini 128K on Replicate API?
Replicate API offers Phi-3 Mini 128K with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Phi-3 Mini 128K across 5 providers to find the best fit for your use caseSetup recipe
Python + curlpip install replicateexport REPLICATE_API_TOKEN=...import replicate
output = replicate.run(
"microsoft/phi-3-mini-128k-instruct",
input={"prompt": "Hello"}microsoft/phi-3-mini-128k-instructRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# microsoft/phi-3-mini-128k-instruct format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"microsoft/phi-3-mini-128k-instruct",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "microsoft/phi-3-mini-128k-instruct", not the LLMReference slug "phi-3-mini-128k".
- Replicate 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.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare Phi-3 Mini 128K Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Baseten API | — | — |
| Microsoft Foundry | $0.30 | $0.90 |
| Fireworks AI | $0.10 | $0.10 |
| Replicate API | $0.05 | $0.25 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.05 |
| Output tokens | $0.25 |
Capabilities
No model capability flags are currently sourced.
About Phi-3 Mini 128K
Phi-3 Mini-128K-Instruct, developed by Microsoft, is a 3.8 billion-parameter large language model renowned for its lightweight, open-source architecture. Despite its modest size, it excels in reasoning tasks, particularly in math and logic, and showcases strong code generation capabilities. A standout feature is its remarkable ability to handle up to 128,000 tokens, allowing it to process extensive text documents and codebases efficiently. While it has limitations in factual knowledge and focuses primarily on English, it strikes a balance between performance and efficiency, making it ideal for resource-constrained environments.