Inteligência em modelos de IA

Phi-3-medium-instruct (4k)

microsoft/phi-3-medium-4k-instruct

Por Microsoft · família: phi · lançado 2024-04-23 · data de conhecimento: 2023-10

$0.170
Entrada / 1M tokens
$0.680
Saída / 1M tokens
4K
Janela de contexto
1K
Saída máxima

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Capacidades

✗ Tool calling✗ Raciocínio? Saída estruturada✗ Anexos✓ Pesos abertos✓ Controle de temperatura
Modalidades: entrada text · saída text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding3
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability3/10
Agents3
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit0/15
  • Provider availability3/10
JSON / structured output28
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control10/10
  • Price-friendly for high-volume18/20
Cost efficiency64
  • Headline price (log-scaled)64/95
  • Has prompt-cache pricing0/5
Long context0
  • Context ≥ 100K0/100
Production-readiness60
  • Number of independent providers15/40
  • Has published per-token price20/20
  • Context window ≥ 8K0/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$1.19
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$2.38
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$0.68
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$2.04
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$2.45
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Detalhes de preço

Preço recomendado de azure · phi-3-medium-4k-instruct

$0.170
Entrada
$0.680
Saída

Provedor mais barato: github-models · Unknown entrada + Unknown saída

Disponível em 3 provedores

ProvedorID do modelo do provedorEntrada / 1MSaída / 1MContextoLançado
Azure
azure
phi-3-medium-4k-instruct$0.170$0.6804K2024-04-23
Azure Cognitive Services
azure-cognitive-services
phi-3-medium-4k-instruct$0.170$0.6804K2024-04-23
GitHub Models
github-models
microsoft/phi-3-medium-4k-instructUnknownUnknown4K2024-04-23

Frequently asked questions

How much does Phi-3-medium-instruct (4k) cost?

Phi-3-medium-instruct (4k) costs $0.170 per 1M input tokens and $0.680 per 1M output tokens, sourced from azure. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of Phi-3-medium-instruct (4k)?

Phi-3-medium-instruct (4k) has a context window of 4K tokens, with a max output of 1K tokens per reply. This is the total combined size of prompt + completion.

Does Phi-3-medium-instruct (4k) support tool calling?

No. Phi-3-medium-instruct (4k) does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does Phi-3-medium-instruct (4k) support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for Phi-3-medium-instruct (4k) in our data source. Verify with Microsoft's official documentation before relying on it in production.

Can Phi-3-medium-instruct (4k) accept image input?

No. Phi-3-medium-instruct (4k) only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is Phi-3-medium-instruct (4k) open-weight?

Yes. Phi-3-medium-instruct (4k)'s weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to Phi-3-medium-instruct (4k)?

If Phi-3-medium-instruct (4k) doesn't fit, consider Phi-4-mini-instruct, Phi-4, WizardLM-2 8x22B. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More Microsoft models

Capability lists this model is in

See also

Última atualização:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.