RADAR DEI MODELLI AI

Confronta i modelli AI con gli stessi criteri

Tutti i modelli attualmente elencati da OpenRouter, con dati coerenti su modalità, contesto, prezzi, configurazione e provider.

AMPIEZZA CATALOGO
TUTTI PUBBLICI
modelli
740
provider
101
ultimo aggiornamento
20 nov 2026
740 modelli
openai logoopenai

OpenAI: o3

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

Contesto
200K
Input
image · text · file
Output
text
Input: $2Output: $8per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: o3 (batch)

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

Contesto
200K
Input
image · text · file
Output
text
Input: $1Output: $4per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: o4 Mini (batch)

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Contesto
200K
Input
image · text · file
Output
text
Input: $0.55Output: $2.2per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $2Output: $8per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1 (batch)

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $1Output: $4per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1 Mini

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $0.4Output: $1.6per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1 Mini (batch)

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $0.2Output: $0.8per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1 Nano

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $0.1Output: $0.4per milione di token
Vedi i dettagli del modello →
openai logoopenai

OpenAI: GPT-4.1 Nano (batch)

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Contesto
1.0M
Input
image · text · file
Output
text
Input: $0.05Output: $0.2per milione di token
Vedi i dettagli del modello →
meta-llama logometa-llama

Meta: Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Contesto
524K
Input
text · image
Output
text
Input: $0.35Output: $1per milione di token
Vedi i dettagli del modello →
meta-llama logometa-llama

Meta: Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Contesto
1.3M
Input
text · image
Output
text
Input: $0.1Output: $0.3per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V3 0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...

Contesto
164K
Input
text
Output
text
Input: $0.29Output: $1.14per milione di token
Vedi i dettagli del modello →
mistralai logomistralai

Mistral: Mistral Small 3.1 24B

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

Contesto
128K
Input
text · image
Output
text
Input: $0.351Output: $0.555per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Gemma 3 4B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Contesto
131K
Input
text · image
Output
text
Input: $0.05Output: $0.1per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Gemma 3 12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Contesto
131K
Input
text · image
Output
text
Input: $0.05Output: $0.15per milione di token
Vedi i dettagli del modello →
cohere logocohere

Cohere: Command A

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

Contesto
256K
Input
text
Output
text
Input: $2.5Output: $10per milione di token
Vedi i dettagli del modello →
rekaai logorekaai

Reka Flash 3

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

Contesto
66K
Input
text
Output
text
Input: $0.1Output: $0.2per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Contesto
131K
Input
text · image
Output
text
Input: $0.08Output: $0.16per milione di token
Vedi i dettagli del modello →
thedrummer logothedrummer

TheDrummer: Skyfall 36B V2

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

Contesto
33K
Input
text
Output
text
Input: $0.55Output: $0.8per milione di token
Vedi i dettagli del modello →
perplexity logoperplexity

Perplexity: Sonar Reasoning Pro

Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

Contesto
128K
Input
text · image
Output
text
Input: $2Output: $8per milione di token
Vedi i dettagli del modello →
perplexity logoperplexity

Perplexity: Sonar Pro

Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

Contesto
200K
Input
text · image
Output
text
Input: $3Output: $15per milione di token
Vedi i dettagli del modello →
perplexity logoperplexity

Perplexity: Sonar Deep Research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Contesto
128K
Input
text
Output
text
Input: $2Output: $8per milione di token
Vedi i dettagli del modello →
mistralai logomistralai

Mistral: Saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

Contesto
33K
Input
text · file
Output
text
Input: $0.2Output: $0.6per milione di token
Vedi i dettagli del modello →
aion-labs logoaion-labs

AionLabs: Aion-RP 1.0 (8B)

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

Contesto
33K
Input
text
Output
text
Input: $0.8Output: $1.6per milione di token
Vedi i dettagli del modello →