Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Kimi K2.5@Us East 2 is listed in Requesty’s public model catalogue under the exact routing identifier bedrock/kimi-k2.5@us-east-2. Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
At the time this draft was collected, the catalogue records a context window of 128,000 tokens and a maximum output of 16,000 tokens. It records reasoning support, vision input support, tool-calling support, and no image-generation flag. These fields describe the routing catalogue entry and should be rechecked against the current provider documentation before production use.
The source catalogue reports input and output prices when available. Pricing can depend on the route, region, token tier, cache use, account, and date, so this record does not infer a commercial commitment from a single snapshot. Confirm current pricing, data handling, regional controls, rate limits, and availability with the current upstream documentation.
This is a source-backed draft imported from Requesty’s public catalogue. It is not published automatically. An editor must verify the exact model identifier, the material claims, and the chosen deployment path before approving it for public discovery or sitemap inclusion.
Use the recorded facts as a shortlist, then validate the model against representative inputs and production constraints.
Kimi K2.5@Us East 2 is categorized for Image-text-to-text, Text-to-text AI models. Its current record accepts text, image and produces text. Confirm file formats, preprocessing, and provider-specific request schemas before implementation.
The directory records 128K context and 16K maximum output. Listed token prices are $0.60 input and $3.00 output per 1M tokens. Treat missing values as unknown and recheck current commercial terms.
Recorded output speed is — and time to first token is —. Hosting route, region, prompt length, concurrency, and provider load can materially change both measurements.
This page separates sourced model facts from incomplete fields. Benchmark evidence is displayed only when its source is linked and verified. Before choosing Kimi K2.5@Us East 2, test task quality, tool reliability, safety behavior, data controls, rate limits, and total cost on the exact route you intend to use.
Related approved models in Text-to-text AI models. Compare specifications and verify fit for your workload.
Anthropic
The 2024 Sonnet that set the standard for practical coding work — now well behind the current Claude line at identical pricing.
OpenAI
OpenAI's omni-era workhorse — text and image in, text out, with a cached-input rate that halves the cost of repeated context.
Google's long-context multimodal model with up to 2M token windows.
Meta
Meta's largest open-weights model, competitive with frontier closed models.
Xai via Requesty
A frontier multimodal model optimized specifically for high-performance agentic tool calling.
DeepSeek
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding