OpenRouter modele

Phi 4

Microsoft: Phi 4 Comparez les tarifs API, le fournisseur, la longueur de contexte, les capacites, les cas d'usage, la latence et les alternatives. General chat via OpenRouter, API workloads. $0.013 / 1M tokens / $0.027 / 1M tokens. 16.4k tokens.

Demarrage rapideEstimer le cout
OpenRouterPlatform curatedCatalog
StreamingJSON mode
Prix entree$0.013 / 1M tokens
Prix sortie$0.027 / 1M tokens
Longueur du contexte16.4k tokens
Sortie max8.2k tokens

Qu'est-ce que Phi 4 dans NextModel ?

Microsoft: Phi 4 Comparez les tarifs API, le fournisseur, la longueur de contexte, les capacites, les cas d'usage, la latence et les alternatives. General chat via OpenRouter, API workloads. $0.013 / 1M tokens / $0.027 / 1M tokens. 16.4k tokens.

Meilleurs cas d'usage

  • General chat via OpenRouter
  • API workloads

Exemple compatible OpenAI

Conservez le style SDK OpenAI, pointez base_url vers NextModel et utilisez l'ID de catalogue microsoft--phi-4.

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.nextmodel.app/v1"
)

resp = client.chat.completions.create(
    model="microsoft/phi-4",
    messages=[{"role": "user", "content": "Hello from NextModel"}]
)

print(resp.choices[0].message.content)

Alternatives proches

OpenRouterCatalog

AllenAI: Olmo 3 32B Think

80

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

$0.029 / 1M tokensInput$0.094 / 1M tokensOutput65.5kContext
Best forGeneral chat via OpenRouter, API workloads
RoutingDegraded
StreamingJSON mode
Platform curatedNextModel gateway catalog (Go origin)
View details
OpenRouterCatalog

Magnum v4 72B

80

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

$0.564 / 1M tokensInput$0.94 / 1M tokensOutput16.4kContext
Best forGeneral chat via OpenRouter, API workloads
RoutingConfigured
StreamingJSON mode
Platform curatedNextModel gateway catalog (Go origin)
View details
OpenRouterCatalog

MythoMax 13B

80

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

$0.012 / 1M tokensInput$0.012 / 1M tokensOutput8.2kContext
Best forGeneral chat via OpenRouter, API workloads
RoutingConfigured
StreamingJSON mode
Platform curatedNextModel gateway catalog (Go origin)
View details

Comparer Microsoft: Phi 4

Microsoft: Phi 4 / AllenAI: Olmo 3 32B ThinkMicrosoft: Phi 4 / Magnum v4 72BMicrosoft: Phi 4 / MythoMax 13BMicrosoft: Phi 4 / Mancer: Weaver (alpha)Microsoft: Phi 4 / WizardLM-2 8x22B

FAQ

Microsoft: Phi 4 FAQ