Live coverage

Directory

Models vs apps & tools · live OpenRouter pricing · no fake benchmarks

PaidModel

Claude API

Anthropic

Claude is best used for generating human-like text responses in conversational applications.

Pricing is tiered based on usage; co
PaidModelLive

DeepSeek V4 Flash Latest

~deepseek

Redirecting users to the latest DeepSeek V4 Flash model.

$0.04 / 1M input tokens1311k
PaidModelLive

DeepSeek: DeepSeek V4 Flash 0731

DeepSeek

This model is best used for coding and reasoning tasks.

$0.05 / 1M input tokens1311k
PaidModel

GPT API

OpenAI

GPT-4o is best used for generating high-quality text across various applications.

Pricing is based on usage and may va
PaidModel

Gemini API

Google

Gemini is best used for advanced natural language processing tasks.

Pricing is tiered based on usage and
PaidModelLive

Google: Gemma 3 4B

Google

Best for multimodal tasks involving vision and language; weak at highly specialized technical queries.

$0.05 / 1M input tokens131k
PaidModelLive

IBM: Granite 4.0 Micro

IBM

Best for long-form content generation; weak at real-time interactive applications.

$0.02 / 1M input tokens131k
PaidModelLive

Meta: Llama 3.1 8B Instruct

Meta

Best for quick, efficient instruction-following tasks; weak at handling complex reasoning or deep contextual understanding.

$0.05 / 1M input tokens131k
PaidModelLive

Mistral: Mistral Nemo

Mistral

Best for multilingual text generation; weak at highly specialized technical topics.

$0.02 / 1M input tokens131k
PaidModelLive

Mistral: Mistral Small 3

Mistral

Best for low-latency AI tasks; weak at handling complex reasoning or nuanced conversations.

$0.05 / 1M input tokens33k
PaidModelLive

MythoMax 13B

Gryphe

Best for creative storytelling and roleplay; weak at technical or factual accuracy.

$0.06 / 1M input tokens8k
PaidModelLive

Nex AGI: Nex-N2-Mini

Nex AGI

Best for coding and tool use; weak at handling large-scale image processing tasks.

$0.02 / 1M input tokens262k
PaidModelLive

Qwen: Qwen3.7 Flash

Qwen

Best for multimodal tasks like visual coding; weak at handling purely text-based queries.

$0.03 / 1M input tokens1000k
PaidModelLive

Sao10K: Llama 3 8B Lunaris

Sao10K

Best for creative storytelling and roleplaying; weak at highly technical or specialized knowledge tasks.

$0.04 / 1M input tokens8k
PaidModelLive

Upstage: Solar Pro 4

Upstage

Best for long-horizon tasks and document management; weak at real-time conversational interactions.

$0.03 / 1M input tokens524k
PaidModelLive

inclusionAI: Ling 3.0 Flash

inclusionAI

Best for high-efficiency token processing; weak at handling complex multi-turn dialogues.

$0.02 / 1M input tokens262k