AI MODEL RADAR

The AI model catalog made comparable

Search every model currently listed by OpenRouter. Compare modalities, context windows, pricing, configuration, and provider facts from one consistent snapshot.

CATALOG SCOPE
ALL PUBLIC
models
740
providers
101
last synced
Nov 20, 2026
740 models
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....

Context
200K
Input
image · text · file
Output
text
Input: $2Output: $8per 1M tokens
View model details →
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....

Context
200K
Input
image · text · file
Output
text
Input: $1Output: $4per 1M tokens
View model details →
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...

Context
200K
Input
image · text · file
Output
text
Input: $0.55Output: $2.2per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $2Output: $8per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $1Output: $4per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $0.4Output: $1.6per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $0.2Output: $0.8per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $0.1Output: $0.4per 1M tokens
View model details →
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...

Context
1.0M
Input
image · text · file
Output
text
Input: $0.05Output: $0.2per 1M tokens
View model details →
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...

Context
524K
Input
text · image
Output
text
Input: $0.35Output: $1per 1M tokens
View model details →
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...

Context
1.3M
Input
text · image
Output
text
Input: $0.1Output: $0.3per 1M tokens
View model details →
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...

Context
164K
Input
text
Output
text
Input: $0.29Output: $1.14per 1M tokens
View model details →
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...

Context
128K
Input
text · image
Output
text
Input: $0.351Output: $0.555per 1M tokens
View model details →
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,...

Context
131K
Input
text · image
Output
text
Input: $0.05Output: $0.1per 1M tokens
View model details →
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,...

Context
131K
Input
text · image
Output
text
Input: $0.05Output: $0.15per 1M tokens
View model details →
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...

Context
256K
Input
text
Output
text
Input: $2.5Output: $10per 1M tokens
View model details →
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...

Context
66K
Input
text
Output
text
Input: $0.1Output: $0.2per 1M tokens
View model details →
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,...

Context
131K
Input
text · image
Output
text
Input: $0.08Output: $0.16per 1M tokens
View model details →
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.

Context
33K
Input
text
Output
text
Input: $0.55Output: $0.8per 1M tokens
View model details →
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...

Context
128K
Input
text · image
Output
text
Input: $2Output: $8per 1M tokens
View model details →
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...

Context
200K
Input
text · image
Output
text
Input: $3Output: $15per 1M tokens
View model details →
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...

Context
128K
Input
text
Output
text
Input: $2Output: $8per 1M tokens
View model details →
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...

Context
33K
Input
text · file
Output
text
Input: $0.2Output: $0.6per 1M tokens
View model details →
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...

Context
33K
Input
text
Output
text
Input: $0.8Output: $1.6per 1M tokens
View model details →