Recommended
Default SLA
TPS
Tokens per second
Set a sustained output rate for the workload you actually run.
Best starting point
Enterprise inference
Same workload.A smaller token bill.
Pick a model. Set your throughput. We'll profile your workload for a lower-cost serving configuration.
Workload profileServing plan
01 / Traffic
Representative requests
8K IN650 OUT
02 / Cached context
Route repeated prefixes together
03 / Matched compute
Prefill
PROMPT PHASE
Decode
OUTPUT PHASE
04 / Output SLA
Sustained generation target
TPS
DEFAULT
Example profiling path. The selected approach depends on model and workload behavior.
Model your inference costs.
Compare published token rates against your workload and cache profile.
Choose a model USD per 1M tokens
Across all requests, not one response.
01K1M1B
Eligible input only. Example, not a forecast.
0%100%
Assumes 4:1 input/output · 24h/day · 30 days · edit assumptions
Public-rate estimate 50% cache scenario
$16,070
per month · $192,845 annualized
Reference · 0% input cache hits$18,144
Scenario · 50% input cache hits$16,070
Fresh inputCached inputOutput
$2,074 lower per month in this scenario
Keep the model. Lower the cost.
Final pricing follows your workload benchmark.
DeepInfra via OpenRouter · 2026-09-06 · Rates & assumptions
USD per 1M tokens: $0.09 fresh input · $0.05 cached input · $0.34 output. Route: deepinfra/turbo, FP4. Model pricing · Provider rate source
Costs use aggregate output TPS × active hours × 3,600 × 30 days, plus input at your selected ratio. Annualized values use twelve 30-day months. Both scenarios use the same provider’s rates and output volume. Bar segments represent fresh input (gray), cached input (hatched), and output (black).
OpenRouter publishes a cache-read rate for this provider endpoint. Its endpoint metadata reported implicit caching as unavailable at retrieval. Do not assume a cache hit. Apply this rate only to input confirmed eligible by the provider's cache behavior and request configuration. Cache hits are an editable assumption, not a prediction. No separate cache-write rate is published. Additional cache-write, storage, network, platform fees, and taxes are excluded, not assumed free.
Market-reference provider route, not an OpenRelay availability or price quote. These token-charge scenarios are not your actual bill, measured savings, or an SLA. Final pricing and service targets require a workload benchmark. sales@openrelay.inc
Choose the outcome
Start with the SLA that matters.
Not sure which to pick? Start with tokens per second. Let us profile your workload and lower the bill.
Interactive
TTFT + ITL
Latency
Set response targets for chat, copilots, and user-facing agents.
User experience
Scheduled
TOKENS / WINDOW
Batch deadline
Set a token volume and the time by which it must finish.
Completion time
What we profile
Where we look for savings.
Approaches benchmarked per workload
01
Context reuse
Test cache-aware routing and shared-prefix reuse.
02
Kernel + batch tuning
Benchmark kernels, quantization, and batch shape.
03
Fit the hardware
Match prefill and decode phases to measured demand.
Bring the workload
Let's find the expensive tokens.
Send your model, traffic shape, and target SLA. We will define a representative benchmark.
Email sales@openrelay.incFinal pricing and SLA follow a workload benchmark.