Choose from the models that matter.

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

Context

1,000,000

Providers

12

Input / 1M

$2

Output / 1M

$6

Fast Grok coding model tuned for agentic engineering and iterative edits

Context

256,000

Providers

13

Input / 1M

$0

Output / 1M

$0

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Context

262,144

Providers

8

Input / 1M

$0

Output / 1M

$0

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Context

1,048,576

Providers

6

Input / 1M

$1

Output / 1M

$4.05

Thinking Kimi model for slower research passes, planning, and hard technical questions

Context

262,144

Providers

22

Input / 1M

$0.3

Output / 1M

$1.2

Kimi reasoning model for long-horizon research, planning, and tool use

Context

262,144

Providers

4

Input / 1M

$1.15

Output / 1M

$8

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Context

262,144

Providers

45

Input / 1M

$0

Output / 1M

$0

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Context

262,144

Providers

54

Input / 1M

$0

Output / 1M

$0

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Context

262,144

Providers

33

Input / 1M

$0

Output / 1M

$0

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

Context

262,144

Providers

8

Input / 1M

$1.9

Output / 1M

$7.999

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

Context

1,048,576

Providers

11

Input / 1M

$3

Output / 1M

$15

Poolside's open-weight model for agentic coding and long-horizon work

Context

262,144

Providers

3

Input / 1M

$0

Output / 1M

$0