Choose from the models that matter.

Kimi K2.7 Code Highspeed

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

Open weightsReasoningText inputImage inputVideo input

Kimi K2 Thinking

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

Open weightsReasoningText input

Kimi K2 Thinking Turbo

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

Context: 262,144
Providers: 4
Input / 1M: $1.15
Output / 1M: $8

Open weightsReasoningText input

Kimi K3

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

Open weightsReasoningText inputImage inputVideo input

Poolside

Laguna M.1

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

Context: 262,144
Providers: 3
Input / 1M: $0
Output / 1M: $0

Open weightsReasoningText input

Poolside

Laguna XS.2

Agentic coding model from Poolside in the XS size class for local deployment

Context: 262,144
Providers: 2
Input / 1M: $0
Output / 1M: $0

Open weightsReasoningText input

Poolside

Laguna XS 2.1

Agentic coding model from Poolside in the XS size class for local deployment

Context: 262,144
Providers: 2
Input / 1M: $0
Output / 1M: $0

Open weightsReasoningText input

Llama 3.1 Nemotron 70B Instruct

Nemotron model for efficient reasoning, coding, and specialized AI agents

Context: 128,000
Providers: 0
Input / 1M: Unknown
Output / 1M: Unknown

Open weightsText input

Llama 3.1 Nemotron Safety Guard 8B v3

Safety model for policy screening, moderation, and risk-aware routing workflows

Context: 128,000
Providers: 1
Input / 1M: $0
Output / 1M: $0

Open weightsText input

Llama 3.1 Nemotron Ultra 253B

Flagship Nemotron model for high-throughput reasoning and complex agents

Context: 128,000
Providers: 1
Input / 1M: $0.6
Output / 1M: $1.8

Open weightsReasoningText input

Llama-3.3-70B-Instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Context: 131,072
Providers: 22
Input / 1M: $0
Output / 1M: $0

Open weightsText input

Llama 3.3 Nemotron Super 49B v1

Nemotron model for efficient reasoning, coding, and specialized AI agents

Context: 131,072
Providers: 1
Input / 1M: $0.15
Output / 1M: $0.15

Open weightsReasoningText input