Particle-1: Benchmarks, Pricing & Context Window
Particle-1 is a language model from Particle AI, released in October 2026, with multimodal input, a 1.0M-token context window, and pricing from $0.250/M input, $0.030/M cached input, $1.00/M output.
Particle-1 is Particle AI's first model, a reinforcement-learning post-train of DeepSeek V4.1 Flash (rank-64 LoRA over the experts in all layers, trained with GSPO in Cascade RL stages on internal coding and data-engineering environments).
Particle-1 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Particle-1 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Particle-1 holds up as conversations get longer.
Quality Tracker
Particle-1 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Oct 29 2026Particle-1 pricing
Providers
Particle-1 starts at $0.250 per million input tokens and $1.00 per million output tokens via Particle AI. Reused prompt prefixes cost $0.0300 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Particle AI | $0.250 | $0.0300 | $1.00 | 1.0M/131.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Particle-1 context window
Input and output token limits for Particle-1, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Particle-1.
Particle-1 latency
Particle-1 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Particle-1 examples
Recent arena outputs from Particle-1, picked from the highest-ranked matchups.
Particle-1 license
Particle-1 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Particle-1 resources
Official sources for Particle-1: provider documentation, official playground, official launch post.
Particle-1 vs other models
The most-compared alternatives to Particle-1 are Gemini 3 Flash, Llama 3.3 70B Instruct, GPT-4. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Particle-1
Models ranked just above and below Particle-1 by LLM Stats score.
FAQ
Common questions about Particle-1.