All AI models · LLM benchmarks · Methodology

Motif Technologies

Motif 3

Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.5 per 1M tokens
Cheapest paid output
$2 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default47.463.5not measurednot measured
Beta45.362.0not measurednot measured

Observed price history

  • 2026-08-24: $0.5 input / $2 output per 1M tokens

API providers