Models

DeepSeek V4 Flash 0423

deepseek ↗ · 1049K ctx · 28 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.110 via OpenRouter
Avg price
$0.182 /1M
providers
28
Tokens (24h)
2.0T
Volume (24h)
$344.2K est.
(3 × $0.088 + $0.176) ÷ 4 = $0.110/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.088, 3:1 $0.110, 1:1 $0.132, output only $0.176 per 1M.

The board shows this model's cheapest measured offer ($0.110/1M); the smaller figure under it is the mean of the 34 offers listed below ($0.182/1M). Add those up and divide — it matches. 24h token volume (2.0T) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here. Cross-check — Vercel AI Gateway: 14.43% of gateway token volume, —% of spend (2026-08-04; share-of-traffic, daily, data CC BY 4.0).

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
Baidu (fp8) OpenRouter $0.088$0.176 634ms 65 100.0% API-measured
StreamLake (fp8) OpenRouter $0.088$0.176 1084ms 45 99.9% API-measured
deepinfra HuggingFace Router $0.090$0.180 598ms 36 API-measured
DeepInfra (fp4) OpenRouter $0.090$0.180 704ms 34 99.8% API-measured
GMICloud (fp8) OpenRouter $0.094$0.188 2212ms 56 97.1% API-measured
pinstripes Pricebook (LiteLLM) $0.100$0.200 Official list
requesty Requesty $0.100$0.200 API-measured
DigitalOcean OpenRouter $0.112$0.224 1086ms 20 97.5% API-measured
SiliconFlow (fp8) OpenRouter $0.130$0.280 1175ms 66 99.9% API-measured
Alibaba (fp8) OpenRouter $0.134$0.268 968ms 74 99.8% API-measured
burncloud burncloud $0.137$0.274 API-measured
0g-teetls 0G Router $0.138$0.275 API-measured
Venice OpenRouter $0.138$0.275 1913ms 43 99.8% API-measured
Morph OpenRouter $0.139$0.278 1345ms 19 91.6% API-measured
fireworks_ai Pricebook (LiteLLM) $0.140$0.280 Official list
tensormesh Pricebook (LiteLLM) $0.140$0.280 Official list
deepseek Pricebook (LiteLLM) $0.140$0.280 Official list
tencent Pricebook (LiteLLM) $0.140$0.280 Official list
novita HuggingFace Router $0.140$0.280 1114ms 94 API-measured
fireworks-ai HuggingFace Router $0.140$0.280 984ms 94 API-measured
novita-ai Novita AI $0.140$0.280 API-measured
Parasail (fp8) OpenRouter $0.140$0.280 726ms 81 99.7% API-measured
Fireworks OpenRouter $0.140$0.280 1215ms 73 99.1% API-measured
Novita (fp8) OpenRouter $0.140$0.280 1246ms 65 99.9% API-measured
Ambient (fp4) OpenRouter $0.140$0.280 API-measured
Cloudflare OpenRouter $0.140$0.280 917ms 38 100% API-measured
AtlasCloud (fp4) OpenRouter $0.140$0.280 2174ms 72 95.5% API-measured
OpenInference (fp8) OpenRouter $0.140$0.280 3083ms 22 85.1% API-measured
CoreWeave (fp8) OpenRouter $0.140$0.280 267ms 50 87.9% API-measured
DeepSeek OpenRouter $0.140$0.280 873ms 84 100.0% API-measured
Phala OpenRouter $0.200$0.400 1849ms 23 85.1% API-measured
azure_ai Pricebook (LiteLLM) $0.190$0.510 Official list
Mancer 2 (fp4) OpenRouter $0.200$0.500 1148ms 27 95.2% API-measured
libertai Pricebook (LiteLLM) $0.250$1.75 Official list

Volume trend

2.0T 30d d-29 · 618B tokensd-28 · 749B tokensd-27 · 806B tokensd-26 · 839B tokensd-25 · 759B tokensd-24 · 735B tokensd-23 · 707B tokensd-22 · 629B tokensd-21 · 763B tokensd-20 · 823B tokensd-19 · 806B tokensd-18 · 777B tokensd-17 · 805B tokensd-16 · 738B tokensd-15 · 672B tokensd-14 · 714B tokensd-13 · 858B tokensd-12 · 913B tokensd-11 · 889B tokensd-10 · 1.0T tokensd-9 · 944B tokensd-8 · 1.0T tokensd-7 · 1.1T tokensd-6 · 1.1T tokensd-5 · 1.2T tokensd-4 · 1.2T tokensd-3 · 1.1T tokensd-2 · 1.3T tokensd-1 · 1.5T tokensd-0 · 2.0T tokens

Last 30 days: 618B → 2.0T (+218%); range 618B–2.0T tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/deepseek-v4-flash.json. Free reuse requires attribution to tkx.org.

About

DeepSeek-V4-Flash is an AI model, a machine-learning system, served by multiple inference providers on AI model marketplaces. It is known for its role in natural language processing tasks.

AI-generated summary from public information — is this yours?

FAQ

How much does DeepSeek V4 Flash 0423 cost?

Cheapest measured offer right now: $0.0882/1M input, $0.1764/1M output via Baidu (fp8) — across 28 tracked providers, refreshed hourly.

Who serves DeepSeek V4 Flash 0423?

28 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is DeepSeek V4 Flash 0423 used?

DeepSeek V4 Flash 0423 routed 2.0T tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings