Skip to content
Wandb

Microsoft/Phi 4 Mini Instruct

Microsoft/Phi 4 Mini Instruct is available via Wandb with a 128K context window and up to 128,000 output tokens. Pricing: $8000.00/1M input tokens, $35000.00/1M output tokens.

Microsoft/Phi 4 Mini Instruct Pricing & Specifications

Input Price$8000.00 per 1M tokens
Output Price$35000.00 per 1M tokens
Context Window128,000 tokens (128K)
Max Output128,000 tokens
ProviderWandb

What is Microsoft/Phi 4 Mini Instruct?

Microsoft/Phi 4 Mini Instruct is a large language model by Wandb with a 128K context window and up to 128,000 output tokens. It costs $8000.00 per 1M input tokens and $35000.00 per 1M output tokens. Microsoft/Phi 4 Mini Instruct is available via Wandb with a 128K context window and up to 128,000 output tokens. Pricing: $8000.00/1M input tokens, $35000.00/1M output tokens.

Capabilities

text

Microsoft/Phi 4 Mini Instruct Cost Examples

Short prompt (500 tokens)

$4.000000

Medium prompt (2K tokens)

$16.00000

Long output (4K tokens)

$140.00000

Count tokens for Microsoft/Phi 4 Mini Instruct

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Microsoft/Phi 4 Mini Instruct

Wandb

Qwen/Qwen3 235B A22B Instruct 2507

$10000.00/1M in 262K ctx

Wandb

Qwen/Qwen3 235B A22B Thinking 2507

$10000.00/1M in 262K ctx

Wandb

Openai/Gpt Oss 20b

$5000.00/1M in 131K ctx

Wandb

Openai/Gpt Oss 120b

$15000.00/1M in 131K ctx

Frequently Asked Questions

How much does Microsoft/Phi 4 Mini Instruct cost per token? +
Microsoft/Phi 4 Mini Instruct costs $8000.00 per 1M input tokens and $35000.00 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $25.500000.
What is the context window for Microsoft/Phi 4 Mini Instruct? +
Microsoft/Phi 4 Mini Instruct supports a context window of 128,000 tokens (128K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Microsoft/Phi 4 Mini Instruct? +
Microsoft/Phi 4 Mini Instruct can generate up to 128,000 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Microsoft/Phi 4 Mini Instruct good for coding tasks? +
Microsoft/Phi 4 Mini Instruct can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All Wandb Models