Skip to content
ProviderBench home

Arcee AI

HQ: United StatesDatacenters: United States

Average response time

7.02 s

Estimated 500-token answer. Across 1 model with recent complete speed data.

Average response start

0.93 s

Wait until the first token. Across 1 model with recent response start data.

Average output speed

82.0 tok/s

Generated tokens per second. Across 1 model with recent output speed data.

AI Models available from Arcee AI

Prices and recent speed measurements below are for Arcee AI endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.

Models

Showing 1 model

  • Model
    Arcee AI: Trinity Large Thinking

    arcee-ai/trinity-large-thinking

    Text
    Current pricing & context
    Input price
    $0.25 / 1M tokens
    Context
    262.1K
    Speed measurements
    500-token response
    7.02 s
    Response starts
    0.93 s
    Output speed
    82.0 tok/s
    Model details
    Model type
    Text
    Provider options
    1

Model data fetched .

Practical comparison guide

How to evaluate Arcee AI as an AI inference provider

Arcee AI currently has 1 indexed model on this site, including 1 text. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Arcee AI with alternative hosts on each model page.

Review model coverage

Arcee AI offers model-specific routes rather than one interchangeable service. Check modality, context window, supported inputs, and parameter support before comparing price. The largest published context window in this catalog is 262.1K tokens.

Interpret price and speed together

The lowest published input price shown here is $0.25 / 1M tokens. Recent 500-token response measurements are available for 1 model; missing measurements remain visible and are never estimated.

Confirm deployment requirements

Arcee AI lists its headquarters as US. Published datacenter coverage: US. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.