🧠 AI Models

22 models across 13 providers

Llama 3.3 70B

NVIDIA NIM

128K ctxTextGeneral Purpose

Meta's latest 70B model. Great all-rounder for agents and chat.

✅ Free tierView deals

Llama 3.3 70B

Groq

128K ctxTextGeneral Purpose

Meta's Llama 3.3 on Groq LPU — ultra fast inference.

✅ Free tierView deals

Mixtral 8x22B

OpenRouter

66K ctxTextGeneral Purpose

Mistral's MoE model. Top-tier reasoning at reasonable cost.

Mixtral 8x7B

Groq

33K ctxTextGeneral Purpose

Fast MoE model on Groq. Great for quick completions.

✅ Free tierView deals

Llama 3 70B

Together AI

8K ctxTextGeneral Purpose

Llama 3 70B at competitive prices on Together AI.

DeepSeek R1

Together AI

66K ctxTextReasoning

DeepSeek's reasoning model. Great for complex math/code.

DeepSeek V3

DeepSeek

66K ctxTextGeneral Purpose

Extremely cost-effective 671B MoE model.

✅ Free tierView deals

Gemini 2.5 Pro

Google Gemini

1M ctxMultimodalGeneral Purpose

Google's most capable model. 1M context, multimodal.

✅ Free tierView deals

Gemini 2.0 Flash

Google Gemini

1M ctxMultimodalGeneral Purpose

Fast and cheap. Great for high-throughput use cases.

✅ Free tierView deals

Claude Sonnet 4

Anthropic

200K ctxTextGeneral Purpose

Best balance of speed and capability. Excellent for coding.

Claude Haiku 4

Anthropic

200K ctxTextGeneral Purpose

Fastest Claude. Great for high-throughput tasks.

GPT-4o

OpenAI

128K ctxMultimodalGeneral Purpose

OpenAI's flagship multimodal model.

GPT-4.1

OpenAI

1M ctxTextGeneral Purpose

Latest GPT with 1M context. Excellent for coding agents.

DeepSeek V4 Pro

OpenCode Zen

262K ctxTextCoding

High-quality coding AI via OpenCode Zen.

Nemotron

NVIDIA NIM

128K ctxTextEnterprise

NVIDIA's in-house model. Great for enterprise use.

✅ Free tierView deals

Command R+

Cohere

128K ctxTextEnterprise

Enterprise-grade with strong RAG capabilities.

✅ Free tierView deals

Mistral Large

Mistral

128K ctxTextGeneral Purpose

Mistral's flagship. Top-tier reasoning in multiple languages.

Codestral

Mistral

33K ctxTextCoding

Mistral's code-specialized model. Great fill-in-the-middle.

Qwen 2.5 72B

Together AI

131K ctxTextGeneral Purpose

Alibaba's Qwen 2.5. Strong multilingual performance.

Grok-3

xAI

131K ctxTextGeneral Purpose

xAI's latest Grok. Real-time knowledge integration.

Sonar Pro

Perplexity

200K ctxTextSearch

Search-grounded AI. Cites sources in responses.

Llama 3.1 Nemotron 70B

NVIDIA NIM

128K ctxTextEnterprise

NVIDIA's fine-tuned Llama. Enterprise-optimized.

✅ Free tierView deals