Phi-3 Mini 128K
Phi-3 Mini 128K is worth evaluating for coding, long context, and classification when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, long context, and classification
- Workloads that can use a 128k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
Advancing the state-of-the-art in AI and computing.
Cheapest of 5 routes · Fireworks AI
About
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. The model is available on platforms like Azure AI Studio and Hugging Face and benefits from training on high-quality synthetic and publicly available data, with fine-tuning to improve instruction adherence and safety.
Phi-3 Mini 128K is an open-source model in the Phi-3 family. The structured metadata tracks a 128k-token context window. This page tracks provider routes through NVIDIA NIM, Baseten API, Microsoft Foundry, and 2 more, with the cheapest tracked route listed at $0.05 input and $0.25 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 50.8, HellaSwag 90.2, and HumanEval 75.9.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ A1 relevant benchmark in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Classification
Q/$ B3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 5Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.100 | $0.100 | Provisioned |
| Replicate API | $0.050 | $0.250 | Serverless |
| Microsoft Foundry | $0.300 | $0.900 | ServerlessProvisioned |
| Baseten API | - | - | ServerlessPartial |
Available via routers & gateways(7)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
Benchmark scores(7)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 50.8 | diamond | https://arxiv.org/abs/2404.14219 |
| HellaSwag | 90.2 | 10-shot | https://arxiv.org/abs/2404.14219 |
| HumanEval | 75.9 | pass@1 | https://arxiv.org/abs/2404.14219 |
| Massive Multitask Language Understanding | 76.5 | 5-shot | https://arxiv.org/abs/2404.14219 |
| MMLU PRO | 43.9 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| Grade School Math 8K | 84.9 | — | https://arxiv.org/abs/2404.14219 |
| AI2 Reasoning Challenge | 78.6 | — | https://arxiv.org/abs/2404.14219 |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Phi-3 Mini 128K?
Phi-3 Mini 128K has a context window of 128k tokens.
How much does Phi-3 Mini 128K cost?
Phi-3 Mini 128K pricing ranges from $0.05/1M to $0.3/1M input tokens depending on the provider.
When was Phi-3 Mini 128K released?
Phi-3 Mini 128K was released on 2024-04-23.
Which providers offer Phi-3 Mini 128K?
Phi-3 Mini 128K is available from 5 providers: NVIDIA NIM, Baseten API, Microsoft Foundry, Fireworks AI, Replicate API.
What benchmarks has Phi-3 Mini 128K been tested on?
Phi-3 Mini 128K has been evaluated on 7 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding, MMLU PRO.
Advancing the state-of-the-art in AI and computing.
Cheapest of 5 routes · Fireworks AI