影

Weights & Biases

[PROVIDER]
kaged models / provider / Weights & Biases
id: wandb
npm: @ai-sdk/openai-compatible
env: WANDB_API_KEY
api: https://api.inference.wandb.ai/v1
doc: https://docs.wandb.ai/guides/integrations/inference/

Models

DeepSeek V3.1

deepseek-ai/DeepSeek-V3.1
in $0.55/M
out $1.65/M
ctx: 161,000 max out: 161,000 in: text out: text
reasoning tools vision structured temp open weights

GLM 5

zai-org/GLM-5-FP8
in $1.00/M
out $3.20/M
ctx: 200,000 max out: 200,000 in: text out: text
reasoning tools vision structured temp open weights

GLM-5.1

zai-org/GLM-5.1
in $1.40/M
out $4.40/M
cache read $0.26/M
cache write $0.00/M
ctx: 200,000 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

gpt-oss-120b

openai/gpt-oss-120b
in $0.15/M
out $0.60/M
ctx: 131,072 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

gpt-oss-20b

openai/gpt-oss-20b
in $0.05/M
out $0.20/M
ctx: 131,072 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

Kimi K2.5

moonshotai/Kimi-K2.5
in $0.50/M
out $2.85/M
ctx: 262,144 max out: 262,144 in: text, image out: text
reasoning tools vision structured temp open weights

Llama 3.1 70B

meta-llama/Llama-3.1-70B-Instruct
in $0.80/M
out $0.80/M
ctx: 128,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

Llama 4 Scout 17B 16E Instruct

meta-llama/Llama-4-Scout-17B-16E-Instruct
in $0.17/M
out $0.66/M
ctx: 64,000 max out: 64,000 in: text, image out: text
reasoning tools vision structured temp open weights

Llama-3.3-70B-Instruct

meta-llama/Llama-3.3-70B-Instruct
in $0.71/M
out $0.71/M
ctx: 128,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

Meta-Llama-3.1-8B-Instruct

meta-llama/Llama-3.1-8B-Instruct
in $0.22/M
out $0.22/M
ctx: 128,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

MiniMax M2.5

MiniMaxAI/MiniMax-M2.5
in $0.30/M
out $1.20/M
ctx: 196,608 max out: 196,608 in: text out: text
reasoning tools vision structured temp open weights

NVIDIA Nemotron 3 Super 120B

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
in $0.20/M
out $0.80/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

OpenPipe Qwen3 14B Instruct

OpenPipe/Qwen3-14B-Instruct
in $0.05/M
out $0.22/M
ctx: 32,768 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Phi-4-mini-instruct

microsoft/Phi-4-mini-instruct
in $0.08/M
out $0.35/M
ctx: 128,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 235B A22B Instruct 2507

Qwen/Qwen3-235B-A22B-Instruct-2507
in $0.10/M
out $0.10/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 30B A3B Instruct 2507

Qwen/Qwen3-30B-A3B-Instruct-2507
in $0.10/M
out $0.30/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

Qwen3-235B-A22B-Thinking-2507

Qwen/Qwen3-235B-A22B-Thinking-2507
in $0.10/M
out $0.10/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

Qwen3-Coder-480B-A35B-Instruct

Qwen/Qwen3-Coder-480B-A35B-Instruct
in $1.00/M
out $1.50/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights