Advertise here
#53

Particle-1

Particle AI Release: 2026-10-28 Tested on: 2026-11-10 00:38 particle-ai/particle-1::low
~748B total (~16B active)MoEClosedEstimated
(max) (xhigh) (high) (medium) (low) (minimal) (none)

Summary

Particle-1 scores 9.1 on AI BENCHY and ranks #53. It has 9.8 reliability, a 72.5% pass rate, $0.134 total cost, and 18.93s average response time.

What makes Particle-1 unique: Its total benchmark cost is unusually low for its score range.

Model facts

Researched on 2026-11-09

Estimated
Parameters
~748B total (~16B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Particle AI describes Particle-1 as a token-efficient coding model post-trained on DeepSeek V4.1 Flash; no weights are released. Counts are inherited from the MIT DeepSeek V4.1 Flash base (748B total / 16B active); the open base does not make this API checkpoint open.

Parameter source 1 Parameter source 2 Availability source

Score

9.1

Consistency

9.3

Reliability

9.8

Total Cost (Current Price)

$0.134

Total Output Tokens

241,020

Total Input Tokens

264,977

Input Price

$0.050 / 1M

Output Price

$0.500 / 1M

Cache Read Price

$0.003 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 7

Attempt pass rate: 72.5%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

18.93s

Response Time (max): 173.97s

Response Time (total): 435.48s

Wrong answer: 5 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#53 Particle-1

low
Cost
$0.006
Time
42.6s
Tokens
10,625 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Particle-1lowvsClaude Fable 5.2mediumParticle-1lowvsMuse Spark OpenxhighParticle-1lowvsMuse WonderminimalParticle-1lowvsGemini 3.5 FlashlowParticle-1lowvsSeed 2.1 TurbohighParticle-1lowvsQwen3.8 Max (0902)mediumParticle-1lowvsParetodefaultParticle-1lowvsMuse Spark 1.3mediumParticle-1lowvsMuse WonderlowParticle-1lowvsGemini 3.5 Flash Litehigh

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 8.3 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 2.9 7.2
General Intelligence 10.0 10.0
Instructions following 9.9 10.0
Puzzle Solving 5.9 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models