Model Price Index
Updated 2026-07-14 · Changelog

DeepSeek V4 Pro

Together AI

DeepSeek's FP4 Pro model with tool calling, structured outputs, and a 512K context window for advanced reasoning

$1.74

Input

$3.48

Output

per 1M tokens

Ratesper 1M tokens

Input$1.74
Output$3.48
Cache Read$0.20

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $156.60/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Same Model, Other Providersper 1M tokens

Provider comparison for DeepSeek V4 Pro
ProviderInput / 1MOutput / 1MCache Read / 1MCache Write / 1Mvs This Page
DeepSeek$0.435$0.87$0.0036−75%
Together AIThis page$1.74$3.48$0.20

Specifications

API Model IDdeepseek-ai/DeepSeek-V4-Pro
Context Window512K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · reasoning · code

More Together AI Text / Chat Models

LFM2-24B-A2B · MiniMax M2.7 · MiniMax M3 · Qwen 2.5 7B Instruct Turbo · Qwen3 235B A22B Instruct 2507 · Qwen3.5 397B A17B · Qwen3.5 9B · Qwen3.6 Plus ·