# Particle-1 is now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/particle-1-is-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/particle-1-is-now-available-on-ai-gateway-0qh3hfc  
Published: 2026-10-28T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Particle-1 adds another coding model to Vercel AI Gateway, with a 1M-token context window and support for Claude Code, Codex and Cursor after CLI setup.

## Source Summary

Particle-1 is post-trained on DeepSeek V4.1 Flash and targets software engineering tasks with fewer tokens. It has a **1M-token context window** and is available through Vercel AI Gateway as `particle/particle-1`.

## Practical Implication

Try it for debugging, code-change planning or multi-step tasks in your coding agent. Set `AI_GATEWAY_API_KEY`, install the latest Vercel CLI, run setup and select the model.

## Agent-Ready Context

Particle-1 is post-trained on DeepSeek V4.1 Flash and targets software engineering tasks with fewer tokens. It has a **1M-token context window** and is available through Vercel AI Gateway as `particle/particle-1`.

Try it for debugging, code-change planning or multi-step tasks in your coding agent. Set `AI_GATEWAY_API_KEY`, install the latest Vercel CLI, run setup and select the model.

Particle describes its reasoning and repair loops as more efficient; the material provides no comparative measurements. Gateway also offers usage and cost tracking, routing and retries.

## Connected Context

Feed7 judgment across 955 accumulated Signals:

Particle-1 adds another coding-focused, million-token model route through AI Gateway, with an efficiency claim but no comparative measurements. It broadens the candidates for debugging and multi-step work without establishing an advantage over other long-context options; Gateway routing and cost tracking can support evaluation, not substitute for it.

- [Hy4 Preview now available on AI Gateway](https://feed7.dev/p/hy4-preview-now-available-on-ai-gateway-0knvicj) — Both add million-token coding-agent routes through Gateway without comparative results, reinforcing the need for matched workload evaluation.
- [Mercury 3 now available on AI Gateway](https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32) — Mercury 3 emphasizes claimed generation speed, while Particle-1 emphasizes token efficiency; neither supplied brief establishes coding-quality results to guide routing.
- [GLM 5.3 now available on AI Gateway](https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv) — Both pair a million-token context with efficiency or long-horizon claims but lack comparative measurements, leaving repository trials necessary.

## Context Map

- Layer: model
- Domains: coding
- Topics: model-selection, coding-agents

## Uncertainty

- Particle describes its reasoning and repair loops as more efficient; the material provides no comparative measurements. Gateway also offers usage and cost tracking, routing and retries.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.