Amux AI

DeepSeek: DeepSeek V4 Pro

Active

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

Input:
Output:
Context length:
1M
Max output:
393K
Published:
2026-08-12
toolsreasoningstructuredOutputstreamingcaching

Providers

Same model, different providers. Automatic routing spreads requests across healthy providers by default, or ranks them by price, latency and more.

Provider
Official25% offdeepseekPeak$1.32$0.99/1M tokensOff-Peak$0.66$0.495/1M tokensPeak$3.96$2.97/1M tokensOff-Peak$1.98$1.485/1M tokens
ReadPeak$0.044$0.033/1M tokensOff-Peak$0.022$0.0165/1M tokensWrite—
1M—1.3s67.8 tps
Official5% offalibaba-cloudOff-Peak$0.66$0.627/1M tokensPeak$1.32$1.254/1M tokensOff-Peak$1.98$1.881/1M tokensPeak$3.96$3.762/1M tokens
ReadOff-Peak$0.066$0.0627/1M tokensPeak$0.132$0.1254/1M tokensWrite—
1M—947ms32.3 tps
Official35% offLowestvolcenginePeak$1.32$0.858/1M tokensOff-Peak$0.66$0.429/1M tokensPeak$3.96$2.574/1M tokensOff-Peak$1.98$1.287/1M tokens
ReadPeak$0.044$0.0286/1M tokensOff-Peak$0.022$0.0143/1M tokensWrite—
1M—20.4s116.21 tps
Official20% offtencent-cloudPeak$1.32$1.056/1M tokensOff-Peak$0.66$0.528/1M tokensPeak$3.96$3.168/1M tokensOff-Peak$1.98$1.584/1M tokens
ReadPeak$0.044$0.0352/1M tokensOff-Peak$0.022$0.0176/1M tokensWrite—
1M—3.3s65.8 tps

Availability

24 hours · 11/03–11/17

Success rate of requests sent by the Amux AI gateway to each provider. Client errors are excluded.

Tok/s

24 hours · 11/03–11/17

Average output speed of streaming requests, in tokens per second (TPS).

TTFT

24 hours · 11/03–11/17

Average time to first token (TTFT) of streaming requests, measured from request dispatch to the first token received.

Activity

24 hours · 11/03–11/17

Relative request activity over time, broken down by serving provider. Indexed to the peak within the selected range (= 100); reflects trends and provider share, not absolute volume.

Related models

More models from DeepSeek

DeepSeek: DeepSeek V4.1 Flash1M contextfrom $0.195 / M tokens4 providersDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp(opens in new tab).