name = "DeepSeek Math V2"
description = "Compact GPT model for low-latency assistance and high-volume workloads"
release_date = "2025-12-03"
last_updated = "2025-12-03"
attachment = false
reasoning = false
tool_call = false
structured_output = false
open_weights = false

[cost]
input = 0.6
output = 2.2

[limit]
context = 128_000
input = 128_000
output = 65_536

[modalities]
input = ["text"]
output = ["text"]