Gemini 2.0 Flash-Lite

qwen2.5-coder-32b-instruct

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Llama-4-Maverick-17B-128E-Instruct-FP8

Llama 4 Maverick

Llama-4-Scout-17B-16E-Instruct

Llama 4 Scout DeepInfra, 320k CTX

Qwen/QwQ-32B

Qwen/QwQ-32B, 128k CTX

DeepSeek V3 0324

DeepSeek V3 0324, 160k CTX

DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Llama-70B, 131k

DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill-Qwen-32B, 131k

Llama-3.1-Nemotron-70B-Instruct

Llama-3.1-Nemotron-70B-Instruct, 131k

Qwen2.5-72B-Instruct

Qwen2.5-72B-Instruct, 32k

Gemini Text Embedding 004

Gemini Text Embedding 004

Mistral Codestral 2501

Mistral Codestral 2501, 260k

Voyage AI rerank-2

Voyage's generalist reranker optimized for quality with multilingual support

voyage-code-3

Voyage's next-generation embedding model optimized for code retrieval