Markdown version for AI agents

A token-efficient Markdown version of this page is available at: https://www.getmaxim.ai/bifrost/model-library/provider/wandb.md

AI agents and LLMs should fetch the Markdown version instead of parsing this HTML — it contains the same content with far fewer tokens.

Wandb Models

Browse all 37 AI models from Wandb

Total Models

37

Modes

1

Avg Input (1M Tokens)

$0.42

Avg Output (1M Tokens)

$1.38

All Wandb Models

Click on any model to view details

All Modes

Showing 37 of 37 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
DeepSeek-R1-0528 wandb/deepseek-ai/DeepSeek-R1-0528	Wandb	Chat	Input $1.35 / 1M tokensOutput $5.40 / 1M tokens	161k	161k	Reasoning
DeepSeek-V3-0324 wandb/deepseek-ai/DeepSeek-V3-0324	Wandb	Chat	Input $1.14 / 1M tokensOutput $2.75 / 1M tokens	161k	161k
DeepSeek-V3.1 wandb/deepseek-ai/DeepSeek-V3.1	Wandb	Chat	Input $0.550000 / 1M tokensOutput $1.65 / 1M tokens	161k	128k	Reasoning
DeepSeek-V4-Flash wandb/deepseek-ai/DeepSeek-V4-Flash	Wandb	Chat	Input $0.140000 / 1M tokensOutput $0.280000 / 1M tokens	1048k	,	Reasoning
DeepSeek-V4-Flash-0731 wandb/deepseek-ai/DeepSeek-V4-Flash-0731	Wandb	Chat	Input $0.130000 / 1M tokensOutput $0.280000 / 1M tokens	262k	,	Reasoning
DeepSeek-V4-Pro wandb/deepseek-ai/DeepSeek-V4-Pro	Wandb	Chat	Input $1.15 / 1M tokensOutput $2.55 / 1M tokens	1048k	,	Reasoning
DeepSeek-V4-Pro-0813 wandb/deepseek-ai/DeepSeek-V4-Pro-0813	Wandb	Chat	Input $1.31 / 1M tokensOutput $3.96 / 1M tokens	,	,	Reasoning
gemma-4-31B-it wandb/google/gemma-4-31B-it	Wandb	Chat	Input $0.100000 / 1M tokensOutput $0.340000 / 1M tokens	262k	,	VisionReasoning
GLM-4.5 wandb/zai-org/GLM-4.5	Wandb	Chat	Input $0.055000 / 1M tokensOutput $0.200000 / 1M tokens	131k	131k	Reasoning
GLM-5.2 wandb/zai-org/GLM-5.2	Wandb	Chat	Input $0.760000 / 1M tokensOutput $2.42 / 1M tokens	262k	,	Reasoning
gpt-oss-120b wandb/openai/gpt-oss-120b	Wandb	Chat	Input $0.030000 / 1M tokensOutput $0.170000 / 1M tokens	131k	131k	Reasoning
gpt-oss-20b wandb/openai/gpt-oss-20b	Wandb	Chat	Input $0.030000 / 1M tokensOutput $0.130000 / 1M tokens	131k	131k	Reasoning
granite-4.1-8b wandb/ibm-granite/granite-4.1-8b	Wandb	Chat	Input $0.050000 / 1M tokensOutput $0.100000 / 1M tokens	131k	,
granite-4.2-8b wandb/ibm-granite/granite-4.2-8b	Wandb	Chat	Input $0.100000 / 1M tokensOutput $0.150000 / 1M tokens	,	,	Reasoning
Kimi-K2-Instruct wandb/moonshotai/Kimi-K2-Instruct	Wandb	Chat	Input $0.600000 / 1M tokensOutput $2.50 / 1M tokens	128k	128k
Kimi-K2.5 wandb/moonshotai/Kimi-K2.5	Wandb	Chat	Input $0.600000 / 1M tokensOutput $3.00 / 1M tokens	262k	262k	FunctionsVisionReasoning
Kimi-K2.6 wandb/moonshotai/Kimi-K2.6	Wandb	Chat	Input $0.650000 / 1M tokensOutput $3.41 / 1M tokens	262k	,	VisionReasoning
Kimi-K2.7-Code wandb/moonshotai/Kimi-K2.7-Code	Wandb	Chat	Input $0.710000 / 1M tokensOutput $3.50 / 1M tokens	262k	,	VisionReasoning
Llama-3.1-70B-Instruct wandb/meta-llama/Llama-3.1-70B-Instruct	Wandb	Chat	Input $0.800000 / 1M tokensOutput $0.800000 / 1M tokens	128k	,
Llama-3.1-8B-Instruct wandb/meta-llama/Llama-3.1-8B-Instruct	Wandb	Chat	Input $0.220000 / 1M tokensOutput $0.220000 / 1M tokens	128k	128k
Llama-3.3-70B-Instruct wandb/meta-llama/Llama-3.3-70B-Instruct	Wandb	Chat	Input $0.710000 / 1M tokensOutput $0.710000 / 1M tokens	128k	128k
Llama-4-Scout-17B-16E-Instruct wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct	Wandb	Chat	Input $0.170000 / 1M tokensOutput $0.660000 / 1M tokens	64,000	64,000
Mellum2-12B-A2.5B-Instruct wandb/JetBrains/Mellum2-12B-A2.5B-Instruct	Wandb	Chat	Input $0.050000 / 1M tokensOutput $0.100000 / 1M tokens	131k	,
MiniMax-M2.5 wandb/MiniMaxAI/MiniMax-M2.5	Wandb	Chat	Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens	197k	197k	FunctionsReasoning
MiniMax-M3 wandb/MiniMaxAI/MiniMax-M3	Wandb	Chat	Input $0.230000 / 1M tokensOutput $0.960000 / 1M tokens	262k	,	VisionReasoning
NVIDIA-Nemotron-3-Ultra-550B-A55B wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	Wandb	Chat	Input $0.500000 / 1M tokensOutput $2.15 / 1M tokens	262k	,	Reasoning
NVIDIA-Nemotron-3.5-Lightning-30B-A3B wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B	Wandb	Chat	Input $0.070000 / 1M tokensOutput $0.200000 / 1M tokens	262k	,	Reasoning
Phi-4-mini-instruct wandb/microsoft/Phi-4-mini-instruct	Wandb	Chat	Input $0.008000 / 1M tokensOutput $0.035000 / 1M tokens	128k	128k
Qwen3-14B-Instruct wandb/OpenPipe/Qwen3-14B-Instruct	Wandb	Chat	Input $0.050000 / 1M tokensOutput $0.220000 / 1M tokens	32,768	,
Qwen3-235B-A22B-Instruct-2507 wandb/Qwen/Qwen3-235B-A22B-Instruct-2507	Wandb	Chat	Input $0.100000 / 1M tokensOutput $0.100000 / 1M tokens	262k	262k
Qwen3-235B-A22B-Thinking-2507 wandb/Qwen/Qwen3-235B-A22B-Thinking-2507	Wandb	Chat	Input $0.100000 / 1M tokensOutput $0.100000 / 1M tokens	262k	262k	Reasoning
Qwen3-30B-A3B-Instruct-2507 wandb/Qwen/Qwen3-30B-A3B-Instruct-2507	Wandb	Chat	Input $0.100000 / 1M tokensOutput $0.300000 / 1M tokens	262k	,
Qwen3-Coder-480B-A35B-Instruct wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct	Wandb	Chat	Input $1.00 / 1M tokensOutput $1.50 / 1M tokens	262k	262k
Qwen3.5-35B-A3B wandb/Qwen/Qwen3.5-35B-A3B	Wandb	Chat	Input $0.250000 / 1M tokensOutput $1.25 / 1M tokens	262k	,	VisionReasoning
Qwen3.6-27B wandb/Qwen/Qwen3.6-27B	Wandb	Chat	Input $0.600000 / 1M tokensOutput $3.60 / 1M tokens	262k	,	VisionReasoning
Qwen3.6-35B-A3B wandb/Qwen/Qwen3.6-35B-A3B	Wandb	Chat	Input $0.250000 / 1M tokensOutput $1.25 / 1M tokens	262k	,	VisionReasoning
Qwen3.8-27B wandb/Qwen/Qwen3.8-27B	Wandb	Chat	Input $0.400000 / 1M tokensOutput $3.00 / 1M tokens	262k	,	VisionReasoning

Related Resources

Calculate Wandb costs →