Phi 4
by Microsoft AImicrosoft/phi-4
LLMCompare cannot run Phi 4 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowPhi 4 at a glance
- Context length
- 16,384 tokens
- Maximum output
- 14,745 tokens
- Accepts
- Text
- Returns
- Text
- Features
- JSON output
- Reasoning effort levels
- Not supported
- Released
- 10 Jan 2025
- Knowledge cutoff
- 30 June 2024
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Phi 4 pricing by route
A route is the service LLMCompare calls to reach the model. Phi 4 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $0.07 | $0.14 | openrouter.ai/microsoft/phi-4 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to Phi 4 costs. The starting numbers are examples. Change them to match your task.
- Cost per call
- $0.00014
- 1 credits
- Cost of 100 calls
- $0.014
- 100 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
top_p | Number | 0 to 1in steps of 0.05 | Provider default |
max_tokens | Integer | 1 to 14,745 | Provider default |
seed | Integer | -2,147,483,648 to 4,294,967,295 | Provider default |
response_format | One of | textjson_object | Provider default |
About Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Phi 4
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Reka Edgerekaairekaai/reka-edge | 16.4k | 14.7k | $0.10 | $0.10 | JSONToolsVision | No route yet | ||
Ministral 3 3B 2512Mistralmistralai/ministral-3b-2512 | 131k | 105k | $0.10 | $0.10 | JSONToolsCacheVision | No route yet | ||
Gemma 3 12BGooglegoogle/gemma-3-12b-it | 131k | 16.4k | $0.05 | $0.15 | JSONToolsVision | No route yet | ||
Hy-MT2-1.8BTencenttencent/hy-mt2-1.8b | 8.2k | 4.1k | $0.044 | $0.177 | — | No route yet | ||
Llama 3.2 1B InstructMetameta-llama/llama-3.2-1b-instruct | 60k | 54k | $0.027 | $0.201 | — | No route yet | ||
Mercury 2.5Inceptioninception/mercury-2.5 | 260k | 65.5k | $0.04 | $0.15 | ReasoningJSONToolsCache | No route yet |
Questions about Phi 4
- How much does Phi 4 cost?
- On the OpenRouter route, Phi 4 costs $0.07 per 1 million input tokens and $0.14 per 1 million output tokens, in US dollars. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Phi 4?
- Phi 4 has a context length of 16,384 tokens and returns up to 14,745 output tokens in one call.
- What inputs does Phi 4 accept?
- Phi 4 accepts these inputs: Text. Phi 4 returns: Text.
- Can I test Phi 4 on my own data?
- Not yet. LLMCompare lists the prices and parameters of Phi 4, but no route to Phi 4 is configured on LLMCompare, so it cannot be selected for an evaluation.