Particle-1
Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.
No cheaper ranked model scores higher: it is on the price frontier.
As of 16 Nov 2026, Particle-1 by Particle AI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $0.050 per 1M input tokens and $0.500 per 1M output tokens ($0.163 blended at 3:1), list price on 16 Nov 2026. It streams about 140 tokens/s (OpenRouter). Released 28 Oct 2026.
Key facts (as of 16 Nov 2026)
- Particle-1 API pricing: $0.050 per 1M input tokens and $0.500 per 1M output tokens ($0.163 blended at 3:1) (list price, 16 Nov 2026).
- Particle-1 streams about 140 tokens/s (OpenRouter, 16 Nov 2026).
- Particle-1 was released on 28 Oct 2026 (Particle AI).
In detail. Particle-1 is a Particle AI model, released 28 Oct 2026. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $0.170 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 141 tokens per second puts it in the fastest quarter, with a first token in 1.0 s. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them.
- Blended price
- $0.170/M
- $0.060 in · $0.500 out
- via OpenRouter
- Output speed
- 141 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.95 s
- Context
- 1.0M
- via OpenRouter
- Cost per task
- –
- Tokens per task
- –
- Released
- 28 Oct 2026
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoningbest | – | – | 141 tok/s | 0.95 s | $0.0002 | |
| high | – | – | 141 tok/s | 0.95 s | $0.0002 | |
| max | – | – | 141 tok/s | 0.95 s | $0.0002 | |
| not stated | – | – | 141 tok/s | 0.95 s | $0.0002 |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Coding
| Benchmark | no reasoning | high | max | not stated | Source |
|---|---|---|---|---|---|
| GameBench 2 Overallnot in indexacross settings | – | – | – | 58.1#20 | DuelLab GameBench 2 |
| GameBench 2 by reasoning settingnot in index | 39.8#137 | 62.7#58 | 71.7#35 | – | DuelLab GameBench 2 |
GameBench 2 Overall: 58.1. GameBench 2, best reasoning setting (Max): 71.7. Reference only, not part of the BenchLeader Index.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Particle AI | 108 tok/s | 0.78 s | $0.060 | $0.500 | 1.0M | – |
Usage
How much Particle-1 is used in practice, as the gateways that publish it report. Usage is not part of the Index. Most used models and labs.
| Provider on Vercel AI Gateway | Throughput | First token | Uptime, 1 day |
|---|---|---|---|
| Particle | 116 tok/s | 0.49 s | 100.00% |
Source: Usage: OpenRouter rankings · Vercel AI Gateway, CC BY 4.0 · data as of 16 Nov 2026.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.003 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | $0.0002 | 3.1 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0010 | $0.0005 | 5.2 s |
| Code edit | 6,000 / 1,500 | $0.0011 | $0.0009 | 11.6 s |
| Agentic coding session | 60,000 / 4,000 | $0.0056 | $0.0030 | 29.3 s |
| Structured extraction | 2,000 / 200 | $0.0002 | $0.0001 | 2.4 s |
See also
Questions people ask
- Why does Particle-1 have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 16 Nov 2026 Particle-1 does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does Particle-1 cost per 1M tokens?
- As of 16 Nov 2026, Particle-1 costs $0.060 per 1M input tokens and $0.500 per 1M output tokens, $0.170 blended (three input tokens per output token).
- When was Particle-1 released?
- Particle AI released Particle-1 on 28 Oct 2026. BenchLeader has results for it at 4 reasoning-effort settings.
Data as of 16 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “Particle-1: benchmarks, pricing, speed and rank”, data as of 16 Nov 2026, https://www.benchleader.com/models/particle-1.