tokenstat
tokenstat

DeepSeek V4 Pro

deepseek-ai/DeepSeek-V4-Pro · rates as of · Benchmarks · Plans · Calculator

Open MoE flagship with million-token context for coding and long agent runs

Cheapest input
$0.435
$/MTok · models.dev
Cheapest output
$0.87
$/MTok
Context
1.0M
tokens
Offers
13
1 source

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek-ai/DeepSeek-V4-ProHugging Face$0.435$0.87$0.00361.0M
models.devdeepseek-ai/deepseek-v4-proNVIDIA$0.435$0.87$0.00361.0M
models.devdeepseek-ai/DeepSeek-V4-ProPioneer$0.435$0.87$0.00361M
models.devdeepseek-ai/deepseek-v4-proAi&$1$2.50$01.0M
models.devdeepseek-ai/DeepSeek-V4-ProDeepInfra$1.30$2.60$0.11.0M
models.devdeepseek-ai/DeepSeek-V4-ProGMI Cloud$1.39$2.78$0.1161.0M
models.devdeepseek-ai/DeepSeek-V4-ProAbacus$1.74$3.48$0.151M
models.devdeepseek-ai/DeepSeek-V4-ProBaseten$1.74$3.48$0.145262K
models.devdeepseek-ai/DeepSeek-V4-ProSiliconFlow (China)$1.74$3.48$0.1451.0M
models.devdeepseek-ai/DeepSeek-V4-ProSiliconFlow$1.74$3.48$0.1451M
models.devdeepseek-ai/DeepSeek-V4-ProTogether AI$1.74$3.48$0.2512K
models.devdeepseek-ai/DeepSeek-V4-ProWeights & Biases$1.74$3.48$0.141.0M
models.devdeepseek-ai/DeepSeek-V4-ProNebius$1.75$3.50$0.151M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-05Released: 2026-04-24Family: deepseek-thinking

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash