Kimi K2.5 by Meganova | AI model information

$10 off the fastest Kimi K3 and GLM 5.2$10 off the fastest Kimi K3 and GLM 5.2

Model details

Kimi K2.5

Kimi K2.5 continues the lineage of Moonshot AI's K2 family by layering native multimodal capability on top of the existing K2 base. According to the OpenRouter description, the model was built through continued pretraining over roughly fifteen trillion mixed visual and text tokens, giving it a unified view of language and imagery rather than bolting vision on as an afterthought. The result is a single system that handles text and image inputs, produces text outputs, and is positioned as a general reasoning engine rather than a narrow vision specialist.

Beyond raw multimodality, the design emphasizes how the model works as an agent. The same source describes Kimi K2.5 as delivering state-of-the-art visual coding ability alongside a self-directed agent swarm paradigm, meaning the model can break down complex tasks and coordinate tool use across many subtasks without constant prompting. Combined with its 262K token context window and strong agentic tool-calling, this makes Kimi K2.5 well suited to long-horizon workflows such as repository-scale code generation, visual debugging from screenshots, and multi-step research pipelines where planning, perception, and tool interaction all matter at once.

Meganovamoonshotai/Kimi-K2.5kimi-k2

Open provider page Provider docs

Quick Info

Provider: Meganova
Model key: moonshotai/Kimi-K2.5
Release date: Jan 27, 2026
Last updated: Jan 27, 2026
Knowledge cutoff: 2026-01
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.45
Output token cost: $2.80

Limits

Output tokens: 262,144 tokens
Context window: 262,144 tokens

Latest news about Kimi K2.5

Meganova

Coverage

Constellation Research's January 27, 2026 coverage of the Kimi K2.5 launch documents four operating modes (K2.5 Instant, K2.5 Thinking, K2.5 Agent, and the K2.5 Agent Swarm beta) and explains that the Agent Swarm acts as an orchestrator that dynamically creates specialized sub-agents such as "AI Researcher," "Physics R On benchmarks, the article paraphrases Moonshot AI's release note claiming K2.5 delivers strong performance on HLE, BrowseComp, and SWE-Verified at a fraction of the cost of OpenAI's ChatGPT 5.2, though these are vendor-reported numbers whose harness, sampling, and inference budget are unspecified. The piece also situa

Meganova

CoverageBenchmark

OpenRouter's catalog entry for moonshotai/kimi-k2.5 lists the model with a 262K context window, input/output modalities, and a release date of January 26, 2026, with headline pricing starting at $0.45 per 1M input tokens and $2.25 per 1M output tokens on DeepInfra (effective weighted averages around $0.1887 input / $2. A multi-provider routing table on the OpenRouter page spans DeepInfra, AtlasCloud, DigitalOcean, Moonshot AI, Amazon Bedrock, StreamLake, NovitaAI, Venice, Phala, and SiliconFlow with latency, throughput, uptime, and cache pricing; notably, Meganova does not appear in this provider list, so the data cannot directly cor

Meganova

Coverage

Per the official Ollama library page, Kimi K2.5 is an open-source, native multimodal agentic model from Moonshot AI built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base, integrating vision and language understanding with instant and thinking modes. The page hig Architecturally, the Ollama description frames K2.5 around cross-modal reasoning, visual knowledge, and agentic tool use grounded in visual inputs, which aligns with Meganova's OpenAI-compatible inference endpoint and gives developers a concrete picture of what the model can be invoked for (image-grounded tool use, vis