OpenRouter 模型 ↗ · 2026-09-26
perceptron/perceptron-mk1.5
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-09-26 收录该模型(收录时间不等于模型正式发布日期);上下文:36,864 tokens;输入价:$0.1500/百万 tokens;输出价:$1.5000/百万 tokens;定位(来源描述):Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents.
Full text
Perceptron: Perceptron Mk1.5
perceptron/perceptron-mk1.5
Compare
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks, and clips.
It supports graded reasoning through the standard reasoning controls, function tool calling, and structured outputs via JSON Schema. Structured annotations are emitted inline with text only when requested via the annotation_format parameter ("point", "box", or "polygon" for spatial localization on images, "clip" for temporal segments in video). Video soundtracks are analyzed only when enabled per request via provider.options.perceptron.enable_audio_in_video: true.
Modalities
In / out price
$0.15 / $1.50per 1M
Context
37K
Released
Sep 25, 2026
Compare
Providers
This model is hosted by one provider. OpenRouter forwards every request without routing.
Latency / throughput
$0.15$1.501.04s138 tok/s
99.13%
ProviderInput / Output /M
Input $0.15 / Output $1.50
138 tok/s99.13% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.1495/M tokens
Output
$1.498/M tokens
Perceptron Mk1.5 — Price history
Price history
No effective price data for this selection
$0.149$1.500.0%100.0%
ProviderInput / Output /M
Token share
Effective in $0.149 / Effective out $1.50
Token share
100.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
138tok/s
P50, best across providers
Latency
1.04s
P50, best provider
Reasoning effort
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
94.42%
Availability over the last 3 days
Last 72 hours
Availability 94.42%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
91.64%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
AYBL Support Portal
new
27.2Mtokens
2.
ClipFactory Video Scoring
new
22.3Mtokens
3.
pi
There are many coding agents, but this one is yours.
4.09Mtokens
4.
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
3.32Mtokens
5.
Cline
Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.
3.19Mtokens
Top 5 Apps
8K
Rest of OpenRouter
42
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Frequently asked questions
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks, and clips. It supports graded reasoning through the standard reasoning controls, function tool calling, and structured outputs via JSON Schema.
Perceptron Mk1.5 costs $0.15/M input tokens and $1.50/M output tokens.
Perceptron Mk1.5 has a 36,864 token context window. It supports up to 8,192 completion tokens.
Yes. Perceptron Mk1.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Perceptron Mk1.5 accepts text, images, video, and audio as input and returns text.
Perceptron Mk1.5 is served by 1 provider on OpenRouter: Perceptron.
Perceptron Mk1 is another text model from Perceptron.
Perceptron Mk1.5 was released on September 25, 2026.