DeepSeek

DeepSeek V3.1

Type
language model
Context
164K tokens
Max output
161K
Released
21 August 2025
API string
deepseek-ai/DeepSeek-V3.1
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
submodel $0.2 $0.8 31 Jul 2026
NanoGPT deepseek-ai/DeepSeek-V3.1 $0.2 $0.7 31 Jul 2026
Vercel $0.25 $0.95 31 Jul 2026
novita-ai $0.27 $1 31 Jul 2026
meganova $0.27 $1 31 Jul 2026
DeepInfra $0.27 $1 31 Jul 2026
Jiekou.AI $0.27 $1 31 Jul 2026
Novita AI $0.27 $1 31 Jul 2026
SiliconFlow $0.27 $1 31 Jul 2026
Baseten $0.5 $1.5 31 Jul 2026
Abacus.AI $0.55 $1.66 31 Jul 2026
Weights & Biases $0.55 $1.65 31 Jul 2026
Fireworks AI $0.56 $1.68 1 Aug 2026
alibaba-cn $0.574 $1.721 31 Jul 2026
Google Vertex AI deepseek-ai/deepseek-v3.1-maas $0.6 $1.7 31 Jul 2026
Together AI $0.6 $1.7 31 Jul 2026
Replicate $0.672 $2.016 31 Jul 2026
NanoGPT TEE/deepseek-v3.1 $1 $2.5 31 Jul 2026
Microsoft Foundry $1.23 $4.94 31 Jul 2026
Google Vertex AI vertex_ai/deepseek-ai/deepseek-v3.1-maas $1.35 $5.4 31 Jul 2026
SambaNova $3 $4.5 31 Jul 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.

A single provider appears several times if it sells this model under different identifiers and at different prices — for example, at different weight precision. The identifier is shown next to the name. Identical offers that arrived from two sources under different spellings are merged into one row.

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 in French 1,455.24 1,418–1,492
Arena Score in English 1,430.47 1,423–1,438
Arena Score, mathematics 1,421.33 1,403–1,440
Arena Score, overall 1,419.4 1,413–1,425
Arena Score, hard prompts 1,415.1 1,407–1,423
Arena Score, programming 1,414.76 1,403–1,426
Arena Score in Spanish 1,412.11 1,380–1,444
Arena Score, expert questions 1,403.19 1,381–1,425
Arena Score, multi-turn dialogue 1,401.41 1,390–1,413
Arena Score in Russian 1,400.62 1,380–1,421
Arena Score, long queries 1,400.15 1,390–1,411
Arena Score, instruction following 1,389.19 1,379–1,399
Arena Score, creative writing 1,387.55 1,374–1,401