Amazon logo

Chronos-Bolt (Base)

online
amazon/chronos-bolt-base

205M params | 2K context | $0.00025 per forecast

Chronos-Bolt Base is the larger, high-accuracy checkpoint in Amazon's Chronos-Bolt family, at 205M parameters. The official model card positions it as more accurate than the original Chronos-Large while remaining dramatically faster, making it the quality tier of the Bolt line and well suited to longer-horizon forecasting.

That combination comes from the shared Bolt design: a patch-based T5 encoder-decoder that produces direct multi-step quantile forecasts over patchified history instead of autoregressive token-by-token rollout. Predicting the whole horizon at once is what keeps it fast despite the larger parameter count. It is pretrained on nearly 100B time-series observations drawn from large public corpora and synthetic pretraining data, as documented by the official Chronos-Bolt model cards.

On TSFM.ai, choose Base when you want a stronger quality ceiling than the smaller Bolt checkpoints without moving to the older autoregressive Chronos-T5 stack. Drop to Chronos-Bolt Small, Mini, or Tiny when latency and cost per series outweigh peak accuracy, or move to Chronos-2 when you need covariates or multivariate cross-learning rather than fast univariate forecasting.

Model Classification

Family

Chronos

Type

time series foundation model

Pretrained time-series model exposed on TSFM.ai for zero-shot or few-shot forecasting workloads.

Training Data

Nearly 100B time-series observations from large public corpora and synthetic pretraining data, as documented by the official Chronos-Bolt model cards.

Recommended For

  • Fast zero-shot probabilistic forecasting in production APIs
  • Teams replacing classic Chronos-T5 with lower latency inference

Strengths

  • Direct multi-step forecasting avoids autoregressive rollout cost
  • Strong default for quantile forecasts with lightweight serving

Limitations

  • Focused on forecasting rather than broader multi-task time-series work
  • Less natural fit when you need model behavior tuned around rich multivariate covariates

Capabilities

forecastingquantile-forecastingzero-shotlong-horizon

Tags

amazonchronosprobabilisticquality-tier

Specifications

Parameters
205M
Architecture
patch-based T5 encoder-decoder with direct multi-step quantile forecasting
Context length
2,048
Max context
2,048
Minimum history
n/a
Recommended history
n/a
Input step
n/a
Required target series
1
Temperature
Ignored
Top P
Ignored
Max output
1,024
Avg latency
n/a
Uptime
n/a
Plan limits
1,000 rpm free · 1,000,000 rpm with billing
Accelerator
T4
Regions
Virginia, US
License
n/a

Pricing

Per forecast
$0.00025

Performance

Average latency
n/a
Availability
n/a
Plan limits
1,000 rpm free · 1,000,000 rpm with billing

Related models