DeepSeek

DeepSeek V2.5

Type
language model
Context
33K tokens
Max output
33K
API string
fireworks_ai/accounts/fireworks/models/deepseek-v2p5

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Fireworks AI $1.2 $1.2 1 Aug 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score, programming 1,301.81 1,293–1,311
Arena Score in French 1,287.81 1,249–1,326
Arena Score in English 1,284.4 1,278–1,291
Arena Score, long queries 1,273.28 1,263–1,283
Arena Score, overall 1,271.41 1,267–1,276
Arena Score, mathematics 1,270.72 1,261–1,280
Arena Score, hard prompts 1,270.61 1,263–1,278
Arena Score, multi-turn dialogue 1,260.71 1,251–1,270
Arena Score in Russian 1,251.84 1,242–1,262
Arena Score, instruction following 1,249.61 1,243–1,256
Arena Score in Spanish 1,247.15 1,213–1,281
Arena Score, expert questions 1,239.32 1,225–1,254
Arena Score, creative writing 1,237.16 1,227–1,248