ModelPriceWatch.com
Last scan 2026-09-22 Models tracked 267 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

DeepSeek V4 Pro

by Together

Current mid tier mid tier

Today's price · per 1M tokens

Input

$1.32

per 1M tokens

Output

$3.96

per 1M tokens

Blended

$1.98

blended $/1M — 3:1 weighted input:output

Cached input

$0.130

10% of input — prompt caching

How this price is scoped: Together has moved this endpoint to the dated API string deepseek-ai/DeepSeek-V4-Pro-0813 and restated its price. Both of Together's own pages were read on 2026-09-06 and agree to the cent: the serverless models card lists deepseek-ai/DeepSeek-V4-Pro-0813 at $1.32 input / $0.13 cached input / $3.96 output per 1M tokens, a 1,048,576-token context window and NVFP4 quantization, and the together.ai/pricing table — the page this row cites — prints the same three prices. Until late August, Together sold two DeepSeek V4 Pro endpoints side by side: this dated one and an undated deepseek-ai/DeepSeek-V4-Pro at $1.74/$0.20/$3.48 with a 512,000-token window in FP4, which is the price this row previously carried. The undated endpoint has since left both pages — the pricing table on 2026-08-31 and the model card by 2026-09-02, still absent on 2026-09-06 — leaving exactly one DeepSeek V4 Pro at Together, so this row now quotes the endpoint you can actually buy. The two were genuinely different products while both were sold, which is why the change is dated to the day only one was left rather than to the day the dated string first appeared. The context window shown is the one Together serves on this endpoint, not DeepSeek's own figure.

Source: official Together pricing · read MODELPRICEWATCH.COM · 2026-09-22

Price receipt

We read Together's own pricing page on and found DeepSeek V4 Pro 0813 listed with a price on the same row — that read is where the number above comes from, recorded as a price change. We keep the page text we read; its content hash is b57861c9ad.

DeepSeek V4 Pro is available on 4 hosts. See the full cheapest-first comparison on the consolidated DeepSeek V4 Pro page →

Overview

DeepSeek V4 Pro hosted on Together. $1.32/$3.96 per 1M tokens; cached input $0.13.

Capabilities

struck through = not supported
Input 1/4
Text Image Audio Video
Output
Text
Features 3/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score73.5%
Perf per $/Mtok37.1
GPQA Diamond
90.1%
SWE-Bench Verified vendor
80.6%
LiveCodeBench
93.5%
MCP Atlas
73.6%
BrowseComp
83.4%
Humanity's Last Exam
48.2%
ARC-AGI 2
30%
AIME 2025
75%
MMMLU
82%
BFCL
72%
HumanEval
80.6%
MATH 500
80%
Independent composite scores
  • AA Intelligence Index: 36.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA-Omniscience Index: 0.8 (−100–100)
  • GDPval-AA v2: 1493.3 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
  • Ranks #31 of 84 benchmarked models by average score
  • Ranks #54 of 181 comparably-measured models by percentile score, across 14 independent measurements
  • Ranks #98 of 181 comparably-tested models by normalized performance per dollar
  • Strongest at LiveCodeBench — 93.5%, #3 of 26

80 tokens/sec output

Source: Artificial Analysis, DeepSeek model card, Artificial Analysis, Vellum LLM Leaderboard · updated · See full rankings →

Specifications

Provider
Together
Context window
1M tokens
Modality
text
Parameters
Proprietary
Open source
No — proprietary
Released
Status
Current
Last updated
Tags
reasoningcachingmid-tier

Availability verified: listed on Together's own page