Pricing
Same weights. Pay for volume.
Every plan runs the same TimesFM 2.5 weights. What changes is throughput: calls per month, requests per minute, and how large a single request may be. These numbers are read straight from the API, so what you see here is what the server enforces.
Free
$0/month
Developer tier — kick the tyres on real TimesFM weights.Monthly calls300
Rate limit10/min · burst 5
Series / request4
Context window1,024 points
Max horizon64 steps
- ✓300 forecast calls / month (~10 a day)
- ✓10 requests / minute, burst 5
- ✓Up to 4 series per call, horizon 64
- ✓1,024-point context window
- ✓Quantile bands (P10–P90)
- ✓Community support
Starter
$49/month
For a first production forecasting job.Monthly calls50,000
Rate limit60/min · burst 30
Series / request32
Context window2,048 points
Max horizon128 steps
- ✓50,000 forecast calls / month
- ✓60 requests / minute, burst 30
- ✓Up to 32 series per call, horizon 128
- ✓2,048-point context window
- ✓Quantile bands (P10–P90)
- ✓Email support, 2 business days
Pro
Most popular$249/month
Batch forecasting at business scale.Monthly calls500,000
Rate limit300/min · burst 120
Series / request128
Context window4,096 points
Max horizon256 steps
- ✓500,000 forecast calls / month
- ✓300 requests / minute, burst 120
- ✓Up to 128 series per call, horizon 256
- ✓Full 4,096-point context window
- ✓Covariate support
- ✓Priority email support, 1 business day
Enterprise
Custom
Dedicated capacity, your compliance rules.Monthly callsUnmetered
Rate limit2000/min · burst 500
Series / request512+
Context window4,096+ points
Max horizon512 steps
- ✓Unmetered forecast calls
- ✓2,000 requests / minute, burst 500
- ✓512+ series per call, batch sizing on request
- ✓4,096+ point context window
- ✓Dedicated inference capacity
- ✓VPC peering & data residency options
- ✓Audit log export
- ✓Dedicated support channel, SLA agreed per contract
Compare
Side by side
| Limit | Free | Starter | Pro | Enterprise |
|---|---|---|---|---|
| Price / month | $0 | $49 | $249 | Custom |
| Forecast calls / month | 300 | 50,000 | 500,000 | Unmetered |
| Requests / minute | 10 | 60 | 300 | 2000 |
| Burst size | 5 | 30 | 120 | 500 |
| Series per request | 4 | 32 | 128 | 512+ |
| Context window | 1,024 points | 2,048 points | 4,096 points | 4,096+ points |
| Max horizon | 64 steps | 128 steps | 256 steps | 512 steps |
| API keys | 2 | 5 | 20 | 100+ |
| Quantile bands | Yes | Yes | Yes | Yes |
| Covariates | No | No | Yes | Yes |
| Support & SLA | — | — | — | — |
How metering worksOne HTTP call to POST /v1/forecast counts as one request, whether it carries 1 series or 512. Requests rejected for a validation error, a rate limit, or an upstream failure are not billed. The counter resets at the start of each UTC month; every response carries the live numbers in X-Quota-Used and X-Quota-Limit.