Microsoft › Phi 3 Medium 4K Instruct › Pricing
Phi 3 Medium 4K Instruct pricing
Cheapest host: DeepInfra · checked Oct 26, 2026
$0.14 / $0.14per 1M tokens in / out
Price sheetper 1M tokens
| Input | $0.14 | DeepInfra |
| Output | $0.14 | |
| Context | 4K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.14 | $0.14 | — |
In Microsoft's line-upper 1M in / out
| Microsoft Decision 1 | $0.042 / — | −100% |
| Phi 4 | $0.056 / $0.11 | −50% |
| Phi-4 Mini | $0.075 / $0.30 | −6% |
| Phi 4 Reasoning Plus | $0.07 / $0.35 | 0% |
| Phi 3 Medium 4K Instruct | $0.14 / $0.14 | this model |
| WizardLM 2 8x22B | $0.48 / $0.48 | 3.4× |
| Phi 3 Mini 4K Instruct | $0.40 / $0.80 | 3.6× |
Cheaper for the same workvs Phi 3 Medium 4K Instruct
| Qwen 3.5 Flash unstated | -19% | score wins 79% | $0.065 / $0.26 |
| Nemotron 3 Nano 30B A3B unstatedOpen | -25% | score wins 77% | $0.06 / $0.24 |
| Gemma 3 27B unstatedOpen | -29% | score wins 77% | $0.08 / $0.16 |
| GPT OSS 120B unstatedOpen | -57% | score wins 77% | $0.03 / $0.15 |
| Gemma 3 12B unstatedOpen | -55% | score wins 74% | $0.05 / $0.10 |
Pricing questions
How much does Phi 3 Medium 4K Instruct cost?›
$0.14 per 1M input tokens and $0.14 per 1M output tokens.
Is Phi 3 Medium 4K Instruct free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
What is a cheaper alternative to Phi 3 Medium 4K Instruct?›
Qwen 3.5 Flash at unstated effort costs -19% per task with a score wins 79% on Arena Text · English.