LLM Pricing
← All models

Phi-3-small-128k-instruct

azure_ai · Chat model

Phi-3-small-128k-instruct is listed here as a chat model from azure_ai. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.

Provider and model identifiers are kept in their original form for accuracy.

azure_ai-azure_ai-phi-3-small-128k-instruct

Input
$0.1500 / 1M tokens
Output
$0.6000 / 1M tokens
Cached input
$0.0150 / 1M tokens
Context window
4.1K

Catalog generated: Jul 13, 2026

Compare this model Open a side-by-side table using this route and a close match from the current catalog. Estimate cost Use token counts, request volume, and cache assumptions to check a realistic monthly bill.

Quick read

Best for

Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.

Things to verify

Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.

Pricing

Item Price
Input
$0.1500 / 1M tokens
Output
$0.6000 / 1M tokens
Cached input
$0.0150 / 1M tokens
Cache write
$0.1500 / 1M tokens
Embedding
$0.1500 / 1M tokens

Limits

Context window
4.1K
Max input tokens
128.0K
Max output tokens
4.1K
Max tokens
4.1K
Explore benchmark family Review source-backed benchmark rows for the attached base model family. Check data sources See how pricing data is generated and what still needs provider verification. API vs subscription Learn when API pricing matters compared with ChatGPT, Claude Code, Cursor, or Copilot subscriptions. Cache and batch pricing Understand cached input, cache write, batch, priority, and flex pricing rows shown on this page.

Capabilities

Capability Supported
Vision -
Function calling -
Parallel function calling -
Tool choice Supported
Prompt caching -
Reasoning -
Response schema -
System messages -
Audio input -
Audio output -
Web search -
PDF input -
Video input -

Benchmarks

Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer

Benchmark Score Metric Scope Checked Source
MMLU 75.5 5-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
ARC-Challenge 90.8 10-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
GSM8K (CoT) 87.3 8-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
HumanEval 59.1 0-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
AGI Eval 39.5 5-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
MMLU 69.7 5-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
BigBench Hard 72.1 3-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
ANLI 52.3 7-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
HellaSwag 70.5 5-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
ARC-Challenge 85.5 10-shot Base model: Phi-3 (Phi-3-Mini-128K-Instruct) 2026-05-31 Link
ARC Easy 97.3 10-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
BoolQ 83.7 2-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
CommonsenseQA 80.8 10-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
MedQA 46.3 2-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
OpenBookQA 87.8 10-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
PIQA 88.1 5-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
Social IQA 78.7 5-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
TruthfulQA (MC2) 69.6 10-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
WinoGrande 80.1 5-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
TriviaQA 66.0 5-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
GSM8K (CoT) 87.3 8-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
HumanEval 59.1 0-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link
MBPP 70.3 3-shot Base model: Phi-3 (Phi-3-Small-128K-Instruct) 2026-05-31 Link

Sources

Source links
Pricing dataLiteLLM model cost map
Synced at2026-05-28
Catalog generated2026-07-13T14:21:55.110Z