Models/Collections/Best LLMs

Best LLMs

Large language models for general-purpose text generation, reasoning, summarization, and conversation. Capable of understanding complex instructions and producing high-quality, coherent text responses.

Models

Gemini 4 Argon

compatible API

Google's frontier Gemini model for long-horizon coding, enterprise knowledge work, and cyber defense

$2.00/ 1M tokensInput · Through Nov 30, 2026
View

Claude Opus 5.5

compatible API

Top-capability Claude model for long-horizon agents, complex coding, and deep reasoning

$4.00/ 1M tokensInput tokens
View

Claude Fable 5.1

compatible API

Frontier multimodal model for long-running coding, research, and professional work

$10.00/ 1M tokensInput tokens
View

Claude Opus 5

compatible API

High-capability Claude model for deep reasoning, long-horizon agents, and complex coding and enterprise work

$5.00/ 1M tokensInput tokens
View

Gemini 3.8 Flash

compatible API

Google's most capable Flash model for long-horizon coding, autonomous agents, and complex multimodal work

$0.75/ 1M tokensInput tokens
View

Kimi K3

compatible API

Flagship multimodal reasoning LLM for long-horizon coding, knowledge work, and tool-rich agent workflows

$3.00/ 1M tokensInput tokens
View

Claude Sonnet 5.5

compatible API

Fast, cost-efficient Claude model for everyday coding, agents, and knowledge work

$2.00/ 1M tokensInput tokens
View

GLM-5.3

compatible API

Flagship coding and agentic LLM with stronger long-horizon execution and security-oriented reasoning

$1.20/ 1M tokensInput tokens
View

Multimodal 1M-context MoE checkpoint for coding, reasoning, and tool-using agents

$0.15/ 1M tokensInput tokens
View

GPT-6.1 Sol

compatible API

Upgraded reasoning model for coding, computer use, and professional work

$2.00/ 1M tokensInput · Up to 272K context
View

GPT-6 Astra

compatible API

Frontier reasoning and tool-use model for demanding end-to-end professional workflows

$10.00/ 1M tokensInput · Up to 272K context
View

Frontier reasoning LLM for complex coding, long-context work, and tool-using professional tasks

$5.00/ 1M tokensInput tokens
Run

DeepSeek-V4-Pro-0813

compatible API

High-capability frontier LLM with 1M context, stronger agent performance, and dual thinking modes

$0.961/ 1M tokensInput tokens
View

GPT-6 Luna

compatible API

Efficient reasoning model for focused, high-volume text and vision workloads

$0.10/ 1M tokensInput · Up to 272K context
View

Claude Haiku 5.5

compatible API

Fastest, lowest-cost Claude model for high-volume agents, extraction, and low-latency applications

$0.10/ 1M tokensInput · Up to 100K context
View

Open-weight alternatives

Z.ai

GLM-5.3-Flash

by Z.ai

Efficient multimodal GLM for coding, agents, and long-context visual understanding

$0.15 / 1M tokens · Input tokens
Google

Gemma 4 31B

by Google

Open 31B multimodal reasoning model for coding, long context, and agentic workflows

$0.102 / 1M tokens · Input tokens
DeepSeek

DeepSeek-V4.1-Flash

by DeepSeek

Multimodal 1M-context MoE for efficient coding, reasoning, and long-horizon agent workflows

$0.15 / 1M tokens · Input tokens
M

Shieldstral 1.0 3B

by mistral ai

Compact multimodal moderation model that judges text and images against your own policy

$0.09 / 1M tokens · Input tokens