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.
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.
Overview
DeepSeek V4 Pro hosted on Together. $1.32/$3.96 per 1M tokens; cached input $0.13.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is better- 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)
- 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
Availability verified: — listed on Together's own page