Contact
LOG IN
Sign up
Physics to intelligence: Accelerating the design of next-generation products
On-demand webinar
From physics to intelligence: Accelerating the design of next‑generation products
physicalAI
Demo video
Getting started with Weights & Biases for robotics

Available models

W&B Inference powered by CoreWeave provides API and playground access to leading open-source LLMs, including OpenAI GPT OSS, Qwen3, Kimi K2, Llama 4, DeepSeek, and Phi, allowing Weights & Biases users to develop AI applications and agents without needing to sign up for a hosting provider or host models themselves

Z.AI GLM 5.2

Text

New

Jun 2026
$1.39 input

 / 

$0.26 cached

 / 

$4.40 output
262K
GLM-5.2 is an MoE language model featuring 40 billion activated parameters and a total of 744 billion parameters

Moonshot AI Kimi K2.7 Code

Vision

New

Jun 2026
$0.94 input

 / 

$0.19 cached

 / 

$4.00 output
262K
A 1T-parameter MoE model with 32B active parameters built for long-horizon agentic coding and software engineering

NVIDIA Nemotron 3 Ultra

New

Jun 2026
$0.75 input

 / 

$0.15 cached

 / 

$2.75 output
262K
A powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

JetBrains Mellum2 12B A2.5B

Text

New

Jun 2026
$.05 input

 / 

$.10 output
131K
Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflow
IBM

IBM Granite 4.1 8B

Apr 2026
$.05 input

 / 

$.10 output
131K
Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat

DeepSeek V4-Pro

Text

Apr 2026
$1.74 input

 / 

$0.14 cached

 / 

$3.46 output
1M
DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning and coding

DeepSeek V4-Flash

Experimental

Apr 2026
$0.01 input

 / 

$0.01 output
1M
DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads.

Qwen3.6 27B

Vision

New

Apr 2026
$0.60 input

 / 

$0.12 cached

 / 

$3.60 output
262K
Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.

Moonshot AI Kimi K2.6

Vision

Apr 2026
$0.95 input

 / 

$0.16 cached

 / 

$4.00 output
262K
Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters

Z.AI GLM 5.1

Text

New

Apr 2026
$1.40 input

 / 

$0.26 cached

 / 

$4.40 output
203K
Powerful MoE model for long-horizon agentic engineering and advanced reasoning.

Google Gemma 4 31B

Text

Vision

Apr 2026
$0.30 input

 / 

$1.25 output
262K
Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 1

Qwen3.6 35B A3B

Vision

Apr 2026
$0.25 input

 / 

$1.25 output
262K
Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.

NVIDIA Nemotron 3 Super 120B

Text

Mar 2026
$0.20 input

 / 

$0.80 output
262K
Nemotron 3 is a LatentMoE model designed to deliver strong agentic, reasoning, and conversational capabilities.

Qwen3.5 27B

Vision

Experimental

Feb 2026
$0.39 input

 / 

$0.08 cached

 / 

$3.12 output
262K
Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.

Qwen3.5 35B A3B

Text

Vision

Feb 2026
$0.25 input

 / 

$1.25 output
262K
Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.

MiniMax M2.5

Text

Feb 2026
$0.30 input

 / 

$1.20 output
197K
MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities

Moonshot AI Kimi K2.5

Text

Vision

Jan 2026
$0.60 input

 / 

$0.10 cached

 / 

$3.00 output
262K
Multimodal MoE language model featuring 32 billion activated parameters and a total of 1 trillion parameters

Deepseek V3.1

Text

Aug 2025
$0.55 input

 / 

$1.65 output
128K
A large hybrid model that supports both thinking and non-thinking modes via prompt templates.

OpenAI GPT OSS 20B

Text

Aug 2025
$0.05 input

 / 

$0.20 output
131K
Lower latency Mixture-of-Experts model trained on OpenAI’s Harmony response format with reasoning capabilities.

OpenAI GPT OSS 120B

Text

Aug 2025
$0.15 input

 / 

$0.60 output
131K
Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.

Qwen3 30B A3B

Text

Jul 2025
$0.10 input

 / 

$0.30 output
262K
Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.

Qwen3 235B A22B-2507

Text

Jul 2025
$0.10 input

 / 

$0.10 output
262K
Efficient multilingual, Mixture-of-Experts, instruction-tuned model, optimized for logical reasoning.

Qwen3 Coder 480B A35B

Text

Jul 2025
$1.00 input

 / 

$1.50 output
262K
Mixture-of-Experts model optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning.

Qwen3 235B A22B Thinking-2507

Text

Jul 2025
$0.10 input

 / 

$0.10 output
262K
High-performance Mixture-of-Experts model optimized for structured reasoning, math, and long-form generation.

OpenPipe Qwen3 14B Instruct

Text

Apr 2025
$0.05 input

 / 

$0.22 output
33K
An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.

Microsoft Phi 4 Mini 3.8B

Text

Feb 2025
$0.08 input

 / 

$0.35 output
128K
Compact, efficient model ideal for fast responses in resource-constrained environments.

Meta Llama 3.3 70B

Text

Dec 2024
$0.71 input

 / 

$0.71 output
128K
Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.

Meta Llama 3.1 70B

Text

Jul 2024
$0.80 input

 / 

$0.80 output
128K
Efficient conversational model optimized for responsive multilingual chatbot interactions.

Meta Llama 3.1 8B

Text

Jul 2024
$0.22 input

 / 

$0.22 output
128K
Efficient conversational model optimized for responsive multilingual chatbot interactions.