Browse Inference Router Models

Compare capabilities, pricing, and features across leading open-weight models.

Featured models

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Reasoning

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

DeepSeek V4.1 Flash model for reasoning and agentic coding

Structured output

Tool use

Web search

All models

Inference Router models. Prices in USD per 1M tokens.

Model

Context

Input

Cached

Output

Providers

ZDR

No training

Regions

Capabilities

Muse Wonder

Meta · muse-wonder-1.0

Input: $4.00
Cached: $0.20
Output: $20.00

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Tool use

DeepSeek V4.1 Flash

DeepSeek · deepseek-v4.1-flash

Input: $0.30
Cached: $0.007
Output: $1.20

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Structured output
Tool use
Web search
Implicit caching

Muse Spark 1.3

Meta · muse-spark-1.3

Input: $1.25
Cached: $0.15
Output: $4.25

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Tool use

GLM 5.3 Flash

Z.ai · glm-5.3-flash

Input: $0.14
Cached: $0.029
Output: $0.48

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Tool use

Qwen3.8 Flash

Alibaba · qwen3.8-flash

Input: $0.14
Cached: $0.015
Output: $0.43

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Tool use

GLM 5.3

Z.ai · glm-5.3

Input: $1.35
Cached: $0.26
Output: $4.25

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Structured output
Tool use
Implicit caching

Qwen3.8 Max

Alibaba · qwen3.8-max

Input: $1.85
Cached: $0.23
Output: $5.55

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Structured output
Tool use
Web search
Explicit caching

Kimi K3

Moonshot AI · kimi-k3

Input: $2.85
Cached: $0.28
Output: $14.25

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Tool use
Web search
Implicit caching

MiniMax M3

MiniMax · minimax-m3

Input: $0.29
Cached: $0.058
Output: $1.16

Context: 512K tokens
Regions: US
ZDR
No training

Capabilities: Text
Tool use

DeepSeek V4 Pro

DeepSeek · deepseek-v4-pro

Input: $1.65
Cached: $0.10
Output: $3.65

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Structured output
Tool use
Web search
Implicit caching

GPT-OSS 120B

OpenAI · gpt-oss-120b

Input: $0.097
Cached: $0.053
Output: $0.73

Context: 125K tokens
Regions: US
ZDR
No training

Capabilities: Text
Reasoning
Structured output
Tool use

Mercury 3

Inception · mercury-3

Input: $0.10
Cached: $0.01
Output: $0.35

Context: 1M tokens
Regions: US
ZDR
No training

Capabilities: Text

Build with Inference Router

Tell us what you run today, and a solutions engineer will show you what it costs on open-weight models.

Get an API key Talk to sales