Every model.One place.
Explore the models available through Noumen. Compare capabilities, context windows, and reference pricing, then see which models people use most and how they score on public benchmarks.
Just landed
Recently added
The newest models available through Noumen, ready to use in the app and the API.
- FrontierNew
- FrontierNew
- Open weightsNew
- EfficientNew
Kimi K2.7 Code TEEMoonshotCapabilities: Reasoning, Tools, Vision, Parallel toolsContext262.1KInput / 1M$0.95Output / 1M$4Show model details
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode while running inside a Trusted Execution Environment (TEE) with attestation support.
- Model ID
TEE/kimi-k2.7-code- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.7 Code High-SpeedMoonshotCapabilities: Reasoning, Tools, Vision, Parallel toolsContext262.1KInput / 1M$1.9Output / 1M$8Show model details
Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.
- Model ID
moonshotai/kimi-k2.7-code-highspeed- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.7 CodeMoonshotCapabilities: Reasoning, Tools, Vision, Parallel toolsContext262.1KInput / 1M$0.6725Output / 1M$3.1Show model details
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.
- Model ID
moonshotai/kimi-k2.7-code- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.6 TEEMoonshotCapabilities: Tools, VisionContext262.1KInput / 1M$1.5Output / 1M$5.25Show model details
Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
- Model ID
TEE/kimi-k2.6- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.6MoonshotCapabilities: Tools, VisionContext262.1KInput / 1M$0.39Output / 1M$1.8Show model details
Kimi K2.6 is an open-source, native multimodal agentic model built for long-horizon coding, coding-driven design, and large-scale task orchestration. It can turn simple prompts and visual inputs into production-ready interfaces and full-stack workflows, and is designed to coordinate complex multi-agent plans with thousands of steps across code, documents, and spreadsheets.
- Model ID
moonshotai/kimi-k2.6- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.6 ThinkingMoonshotCapabilities: Reasoning, Tools, Vision, Parallel toolsContext262.1KInput / 1M$0.39Output / 1M$1.8Show model details
Kimi K2.6 Thinking is the reasoning-optimized K2.6 variant for deeper multi-step planning and execution. It is tuned for long-horizon coding and design workflows, including complex orchestration across many specialized sub-agents and autonomous end-to-end output generation.
- Model ID
moonshotai/kimi-k2.6:thinking- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.5MoonshotCapabilities: Tools, VisionContext262.1KInput / 1M$0.375Output / 1M$2Show model details
Kimi K2.5 is Moonshot AI's native multimodal model built on Kimi K2 with ~15T mixed visual and text tokens, delivering strong general reasoning, visual coding, and agentic tool-calling. This route uses instant (non-thinking) mode for faster responses.
- Model ID
moonshotai/kimi-k2.5- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2.5 ThinkingMoonshotCapabilities: Reasoning, Tools, Vision, Parallel toolsContext262.1KInput / 1M$0.375Output / 1M$2Show model details
Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.
- Model ID
moonshotai/kimi-k2.5:thinking- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2 0711 FastMoonshotCapabilities: PDF inputContext131.1KInput / 1M$0.4Output / 1M$1.8Show model details
Deprecated. This model now routes to Kimi K2 0711.
- Model ID
kimi-k2-instruct-fast- Discovery tier
- Open weights
- Context window
- 131,072 tokens
Kimi K2 ThinkingMoonshotCapabilities: Reasoning, Tools, Structured outputContext262.1KInput / 1M$0.6Output / 1M$2.5Show model details
Moonshot AI's distinct Kimi K2 Thinking checkpoint is a mandatory-reasoning model for long-horizon agentic workflows and multi-step tool use.
- Model ID
moonshotai/kimi-k2-thinking- Discovery tier
- Open weights
- Context window
- 262,144 tokens
Kimi K2 0905MoonshotCapabilities: Tools, Structured outputContext262.1KInput / 1M$0.4Output / 1M$1.8Show model details
Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.
- Model ID
moonshotai/Kimi-K2-Instruct-0905- Discovery tier
- Open weights
- Context window
- 262,144 tokens
K2-Thinkk2Capabilities: Text generationContext128KInput / 1M$0.17Output / 1M$0.68Show model details
K2-Think is a 32B open-weights general reasoning model with strong competitive math performance. Benchmarks: AIME 2024 90.83, AIME 2025 81.24, GPQA-Diamond 71.08, LiveCodeBench v5 63.97.
- Model ID
LLM360/K2-Think- Discovery tier
- Open weights
- Context window
- 128,000 tokens
Kimi K2 0711MoonshotCapabilities: ToolsContext128KInput / 1M$0.4Output / 1M$1.8Show model details
Kimi K2 0711 version. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.
- Model ID
moonshotai/kimi-k2-instruct-0711- Discovery tier
- Open weights
- Context window
- 128,000 tokens
Kimi K2 0711 Instruct FP4MoonshotCapabilities: Text generationContext131.1KInput / 1M$0.4Output / 1M$1.8Show model details
Deprecated. This model now routes to Kimi K2 0711.
- Model ID
baseten/Kimi-K2-Instruct-FP4- Discovery tier
- Open weights
- Context window
- 131,072 tokens
Kimi K2 InstructMoonshotCapabilities: Tools, Structured outputContext256KInput / 1M$0.4Output / 1M$1.8Show model details
Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.
- Model ID
moonshotai/kimi-k2-instruct- Discovery tier
- Open weights
- Context window
- 256,000 tokens
Reference pricing in USD per 1M tokens, as published by model providers. Discovery tiers describe model metadata, rather than benchmark rankings.