particle-ai
Particle AI: Particle-1
particle-ai/particle-1
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, Particle-1 (particle-ai/particle-1) is a text-and-image-to-text model from Particle AI, described there as a token-efficient agentic coding model post-trained on DeepSeek V4.1 Flash. The catalog lists a context window of about one million tokens, reasoning enabled by default at high effort with adjustable levels, and support for tool calling and structured outputs. No independent model card was available in this source pack, so these capabilities are catalog-reported rather than independently verified.[1]
Strengths
- Catalog-listed context window of about one million tokens, which could accommodate very long inputs such as large codebases.[1]
- Reasoning is enabled by default at high effort but is not mandatory, and the catalog lists several effort levels that can be tuned per request.[1]
- Accepts image and text inputs with text output, and the catalog lists tool calling, tool choice, and structured output parameters.[1]
Limitations
- Evidence comes only from the OpenRouter catalog; no independent model card was available in this source pack, and catalog-described qualities such as token efficiency are unverified vendor claims.[1]
- No benchmark results appear in the catalog entry, so real-world performance is unmeasured here; validate behavior on your own workloads before adoption.[1]
- Knowledge cutoff, licensing, and hardware requirements are not specified in the supplied data.[1]
Where to use it
- Agentic software engineering work, such as terminal workflows and codebase edits, matching the catalog's own positioning.[1]
- Applications that need long-context prompts or mixed image-and-text inputs with text-only output.[1]
- Tool-using pipelines that could benefit from structured outputs and adjustable reasoning effort.[1]
Sources
- [1] OpenRouter catalog · Particle AI: Particle-1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...
Specifications
- Model ID
- particle-ai/particle-1
- Canonical ID
- particle-ai/particle-1-20261027
- Creator
- particle-ai
- Added to OpenRouter
- 28.10.2026
- Context length
- 1,048,576
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.050 / out $0.500
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default high · efforts: max, xhigh, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: max, xhigh, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Particle AI | 1,048,576 | $0.050 | $0.500 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.