Moonshot's native multimodal model with visual coding and agentic capabilities.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Moonshot's native multimodal model with visual coding and agentic capabilities. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Kimi K2.5 on OffRail starts at $0.40 per million input tokens and $1.98 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Kimi K2.5 supports a context window of up to 262,144 tokens on its largest provider deployment.
Kimi K2.5 is served by Moonshot AI, Alibaba Cloud, EmberCloud, DeepInfra through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Kimi K2.5 supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Kimi K2.5 was released on January 26, 2026.
Kimi K3
1,048,576 context$3.00 in / $15.00 out per 1M
Kimi K3 Fast
1,040,384 context$4.50 in / $22.50 out per 1M
Kimi K2.7 Code
262,144 context$0.95 in / $4.00 out per 1M
Kimi K2.7 Code Highspeed
262,144 context$1.90 in / $8.00 out per 1M
Kimi K2.6
262,144 context$0.22 in / $1.14 out per 1M
Kimi K2 Thinking
262,144 context$0.60 in / $2.50 out per 1M