Agent guide

Best AI models for agents

This page prioritizes models with tool use and structured output support because those signals matter most for automations, task routing, and production agent behavior.

Live signalTool support for calling actions and external systems

Live signalStructured output support for reliable machine-readable payloads

Live signalContext room for multi-step agent state and instructions

Live signalLive pricing for production automation budgeting

Fast answer

Start with the live shortlist, then validate the route

Agent stacks need reliable action calls and predictable output formats. Those features usually matter more than raw model popularity when you build repeatable workflows.

Data source and freshness

Catalog-backed, not a static price sheet

TVP refreshes this page from the live OpenRouter model catalog. This render used 587 public model records and was synchronized Sep 11, 2026, 6:28 AM UTC. Pricing, availability, and context values can change.

Verify the exact route before sending production traffic, then use the linked model and provider pages as the source for current values. Read the TVP data methodology.

Shortlist

Top live candidates right now

x-ai

SpaceXAI: Grok 4.20

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

Context2,000,000

Input$1.25

Output$2.50

2,000,000 token context, tool support, and structured workflows make this a strong agent candidate.

text
image
file
tools
structured

Model details Provider page

~deepseek

DeepSeek V4 Flash Latest

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Context1,310,720

Input$0.04

Output$0.16

1,310,720 token context, tool support, and structured workflows make this a strong agent candidate.

text
tools
structured

Model details Provider page

deepseek

DeepSeek: DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Context1,310,720

Input$0.065

Output$0.18

1,310,720 token context, tool support, and structured workflows make this a strong agent candidate.

text
tools
structured

Model details Provider page

~z-ai

Z.ai: GLM Flash Latest

This model always redirects to the latest model in the GLM Flash family.

Context1,310,720

Input$0.075

Output$0.25

1,310,720 token context, tool support, and structured workflows make this a strong agent candidate.

text
image
video
tools
structured

Model details Provider page

z-ai

Z.ai: GLM 5.3 Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Context1,310,720

Input$0.15

Output$0.5

1,310,720 token context, tool support, and structured workflows make this a strong agent candidate.

text
image
video
tools
structured

Model details Provider page

FAQ

What buyers usually ask

Why are tools and structured output the main signals here?

Agent stacks need reliable action calls and predictable output formats. Those features usually matter more than raw model popularity when you build repeatable workflows.

Can an agent model also be a good coding model?

Yes. Many strong coding models also do well in agents because both workloads benefit from reasoning, tool use, and larger context windows.

Next step

Use the guide, then validate the route in live TVP data.

TVP keeps the shortlist connected to the current catalog, provider coverage, and token pricing so buyers can move from research to routing without starting over.

Open marketplace View rankings