Weights & Biases

wandb

Updated 51 minutes ago

Weights & Biases (W&B) is an AI/ML platform that provides model training tracking, experiment management, and inference services. Their W&B Inference API offers an OpenAI-compatible interface to access curated open-source language models including DeepSeek, Qwen, Meta Llama, Google Gemma, MiniMax, Moonshot AI (Kimi), NVIDIA Nemotron, Microsoft Phi, and others. The platform is known for its MLOps tooling and has expanded into hosted inference with competitive pricing.

Visit Website LLMs.txt

Browse 56 LLM models available from Weights & Biases. Compare prices and features.

Models (56)

Organization	Model Name	Original Model	Input	Output
Moonshot AI	Kimi K3	`moonshotai/Kimi-K3`	$3.00	$15.00	View
qwen	Qwen3.8-27B	`Qwen/Qwen3.8-27B`	$0.40	$3.00	View
qwen	Qwen3.8-27B	`Qwen3.8-27B`	-	-	View
Z.ai	GLM-5.2	`GLM-5.2`	-	-	View
Z.ai	GLM-5.2	`zai-org/GLM-5.2`	$0.76	$2.42	View
Moonshot AI	Kimi K2.7 Code	`Kimi-K2.7-Code`	-	-	View
Moonshot AI	Kimi K2.7 Code	`moonshotai/Kimi-K2.7-Code`	$0.71	$3.50	View
Minimax	MiniMax M3	`MiniMaxAI/MiniMax-M3`	$0.23	$0.96	View
Minimax	MiniMax M3	`MiniMax-M3`	-	-	View
Nvidia	Nemotron 3 Ultra 550B A55B	`NVIDIA-Nemotron-3-Ultra-550B-A55B`	-	-	View
Nvidia	Nemotron 3 Ultra 550B A55B	`nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B`	$0.75	$2.75	View
DeepSeek	DeepSeek V4 Pro	`DeepSeek-V4-Pro`	-	-	View
DeepSeek	DeepSeek V4 Pro	`deepseek-ai/DeepSeek-V4-Pro`	$1.15	$2.55	View
DeepSeek	DeepSeek V4 Flash	`DeepSeek-V4-Flash`	-	-	View
DeepSeek	DeepSeek V4 Flash	`deepseek-ai/DeepSeek-V4-Flash`	$0.14	$0.28	View
DeepSeek	DeepSeek V4 Flash	`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.13	$0.28	View
DeepSeek	DeepSeek V4 Flash	`DeepSeek-V4-Flash-0731`	-	-	View
Moonshot AI	Kimi K2.6	`Kimi-K2.6`	-	-	View
Moonshot AI	Kimi K2.6	`moonshotai/Kimi-K2.6`	$0.65	$3.41	View
Alibaba	Qwen3.6 27B	`Qwen3.6-27B`	-	-	View
Alibaba	Qwen3.6 27B	`Qwen/Qwen3.6-27B`	$0.60	$3.60	View
Z.ai	GLM-5.1	`GLM-5.1`	-	-	View
qwen	Qwen3.6 35B A3B	`Qwen3.6-35B-A3B`	-	-	View
qwen	Qwen3.6 35B A3B	`Qwen/Qwen3.6-35B-A3B`	$0.25	$1.25	View
Minimax	MiniMax M2.5	`MiniMax-M2.5`	-	-	View
google	Gemma 4 31B	`gemma-4-31B-it`	-	-	View
google	Gemma 4 31B	`google/gemma-4-31B-it`	$0.10	$0.34	View
qwen	Qwen3.5-35B-A3B	`Qwen3.5-35B-A3B`	-	-	View
qwen	Qwen3.5-35B-A3B	`Qwen/Qwen3.5-35B-A3B`	$0.25	$1.25	View
OpenAI	GPT OSS 120B	`openai/gpt-oss-120b`	$0.03	$0.17	View
OpenAI	GPT OSS 120B	`gpt-oss-120b`	-	-	View
qwen	Qwen3-Coder 480B A35B Instruct	`Qwen3-Coder-480B-A35B-Instruct`	-	-	View
OpenAI	GPT OSS 20B	`openai/gpt-oss-20b`	$0.03	$0.13	View
OpenAI	GPT OSS 20B	`gpt-oss-20b`	-	-	View
qwen	Qwen3-235B-A22B-Instruct-2507	`Qwen3-235B-A22B-Instruct-2507`	-	-	View
DeepSeek	DeepSeek-V3.1	`deepseek-ai/DeepSeek-V3.1`	$0.55	$1.65	View
DeepSeek	DeepSeek-V3.1	`DeepSeek-V3.1`	-	-	View
Meta	Llama 3.1 70B Instruct	`meta-llama/Llama-3.1-70B-Instruct`	$0.80	$0.80	View
Meta	Llama 3.1 70B Instruct	`Llama-3.1-70B-Instruct`	-	-	View
Meta	Llama 3.1 8B Instruct	`meta-llama/Llama-3.1-8B-Instruct`	$0.22	$0.22	View
Meta	Llama 3.1 8B Instruct	`Llama-3.1-8B-Instruct`	-	-	View
Meta	Llama 3.3 70B Instruct	`meta-llama/Llama-3.3-70B-Instruct`	$0.71	$0.71	View
Meta	Llama 3.3 70B Instruct	`Llama-3.3-70B-Instruct`	-	-	View
WandB	Granite 4.2 8B	`ibm-granite/granite-4.2-8b`	$0.10	$0.15	View
WandB	Granite 4.2 8B	`granite-4.2-8b`	-	-	View
WandB	Nemotron 3.5 Lightning	`nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B`	$0.10	$0.25	View
WandB	Nemotron 3.5 Lightning	`NVIDIA-Nemotron-3.5-Lightning-30B-A3B`	-	-	View
WandB	Mellum2 12B A2.5B	`JetBrains/Mellum2-12B-A2.5B-Instruct`	$0.05	$0.10	View
WandB	Mellum2 12B A2.5B	`Mellum2-12B-A2.5B-Instruct`	-	-	View
IBM	Granite 4.1 8B	`granite-4.1-8b`	-	-	View
IBM	Granite 4.1 8B	`ibm-granite/granite-4.1-8b`	$0.05	$0.10	View
WandB	NVIDIA Nemotron 3 Super 120B	`NVIDIA-Nemotron-3-Super-120B-A12B-FP8`	-	-	View
Alibaba	qwen3-30b-a3b-instruct-2507	`Qwen/Qwen3-30B-A3B-Instruct-2507`	$0.10	$0.30	View
Alibaba	qwen3-30b-a3b-instruct-2507	`Qwen3-30B-A3B-Instruct-2507`	-	-	View
WandB	OpenPipe Qwen3 14B Instruct	`OpenPipe/Qwen3-14B-Instruct`	$0.05	$0.22	View
WandB	OpenPipe Qwen3 14B Instruct	`Qwen3-14B-Instruct`	-	-	View

Back to Providers Visit Website