AI Model DirectorySearch
Search models, providers, and docs
AI Model DirectorySearch models, providers, and docs
Weights & Biases offers 23 models tracked in the AI Model Directory, covering chat, coding, reasoning, and embedding workloads. Compare per-million-token pricing, context window sizes, output limits, and supported features and modalities side by side - including DeepSeek: DeepSeek V3.1, DeepSeek: DeepSeek V4.1 Flash, DeepSeek: DeepSeek V4 Flash 0731, DeepSeek: DeepSeek V4 Pro 0813.
23 of 23 modelsShowing 23 of 23 models from 1 provider
deepseek-ai/DeepSeek-V3.1 | $0.55 | $1.65 | - | $0.55 | - | - | - | 161K | - | 161K | ToolsStructured outputTemperature | Text | Text | Aug 21, 2025 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
deepseek-ai/DeepSeek-V4-Flash-0731 | $0.13 | $0.28 | - | $0.07 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputTemperature | Text | Text | Jul 31, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
deepseek-ai/DeepSeek-V4-Pro-0813 | $1.31 | $3.96 | - | $0.044 | - | - | - | 1M | - | 1M | ToolsStructured outputTemperature | Text | Text | Aug 13, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
deepseek-ai/DeepSeek-V4.1-Flash | $0.13 | $0.65 | - | $0.002 | - | - | - | 1M | - | 1M | ToolsStructured outputFilesTemperature | ImageText | Text | Sep 10, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
google/gemma-4-26B-A4B-it | $0.1 | $0.3 | - | $0.05 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Apr 2, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
google/gemma-4-31B-it | $0.1 | $0.34 | - | $0.1 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Apr 2, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
ibm-granite/granite-4.2-8b | $0.06 | $0.15 | - | $0.015 | - | - | - | 131.1K | - | 131.1K | ToolsStructured outputTemperature | Text | Text | Aug 25, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
meta-llama/Llama-3.1-8B-Instruct | $0.22 | $0.22 | - | $0.22 | - | - | - | 131.1K | - | 131.1K | ToolsStructured outputTemperature | Text | Text | Jul 1, 2024 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
meta-llama/Llama-3.3-70B-Instruct | $0.71 | $0.71 | - | $0.71 | - | - | - | 128K | - | 128K | ToolsStructured outputTemperature | Text | Text | Dec 1, 2024 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
MiniMaxAI/MiniMax-M3 | $0.23 | $0.96 | - | $0.05 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Jun 12, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
moonshotai/Kimi-K2.6 | $0.65 | $3.41 | - | $0.15 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Apr 20, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
moonshotai/Kimi-K2.7-Code | $0.6 | $3 | - | $0.12 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Jun 12, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.15 | - | $0.1 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputTemperature | Text | Text | Jun 4, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B | $0.07 | $0.2 | - | $0.04 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputTemperature | Text | Text | Aug 11, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | $0.15 | $0.5 | - | $0.02 | - | - | - | 1M | - | 1M | ToolsStructured outputFilesTemperature | ImageText | Text | Oct 15, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
openai/gpt-oss-20b | $0.03 | $0.13 | - | $0.03 | - | - | - | 131.1K | - | 131.1K | ToolsStructured outputTemperature | Text | Text | Aug 5, 2025 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
openai/gpt-oss-120b | $0.03 | $0.17 | - | $0.03 | - | - | - | 131.1K | - | 131.1K | ToolsStructured outputTemperature | Text | Text | Aug 5, 2025 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
Qwen/Qwen3.6-35B-A3B | $0.1 | $0.95 | - | $0.05 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Apr 15, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
Qwen/Qwen3.8-27B | $0.4 | $3 | - | $0.15 | - | - | - | 262.1K | - | 262.1K | ToolsStructured outputFilesTemperature | ImageText | Text | Aug 14, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
reflection/Beam-1.0-501B-A23B | $0.3 | $1 | - | $0.04 | - | - | - | 1M | - | 1M | ToolsStructured outputTemperature | Text | Text | Oct 16, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
zai-org/GLM-5.2 | $0.62 | $2.42 | - | $0.14 | - | - | - | 1M | - | 1M | ToolsStructured outputTemperature | Text | Text | Jun 16, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
zai-org/GLM-5.3 | $0.75 | $3 | - | $0.19 | - | - | - | 1M | - | 1M | ToolsStructured outputTemperature | Text | Text | Aug 14, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 | |
zai-org/GLM-5.3-Flash | $0.12 | $0.38 | - | $0.02 | - | - | - | 1M | - | 1M | ToolsStructured outputFilesTemperature | ImageText | Text | Aug 26, 2026 | - | - | - | @ai-sdk/openai-compatible | WANDB_API_KEY | https://api.inference.wandb.ai/v1 |