Models

DeepSeek-V3

hyperbolic · 1049K ctx · 15 providers · updated 2026-11-03 07:16 UTC

Cheapest
$0.200 Official list · Hyperbolic
Avg price
$0.754 /1M
providers
15
(3 × $0.200 + $0.200) ÷ 4 = $0.200/1M — 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 $0.200, 3:1 $0.200, 1:1 $0.200, output only $0.200 per 1M.

The board shows this model's cheapest measured offer ($0.200/1M); the smaller figure under it is the mean of the 17 offers listed below ($0.754/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
hyperbolic Pricebook (LiteLLM) ↗ $0.200$0.200 — — — Official list
inferenceapis Pricebook (LiteLLM) ↗ $0.190$0.380 — — — Official list
requesty Requesty ↗ $0.256$0.712 — — — API-measured
deepinfra Pricebook (LiteLLM) ↗ $0.320$0.890 — — — Official list
deepinfra HuggingFace Router ↗ $0.320$0.890 451ms 15 — API-measured
deepseek Pricebook (LiteLLM) ↗ $0.270$1.10 — — — Official list
streamlake Pricebook (LiteLLM) ↗ $0.286$1.14 — — — Official list
burncloud burncloud ↗ $0.287$1.15 — — — API-measured
kyma Pricebook (LiteLLM) ↗ $0.518$0.757 — — — Official list
nebius Pricebook (LiteLLM) ↗ $0.500$1.50 — — — Official list
novita Pricebook (LiteLLM) ↗ $0.890$0.890 — — — Official list
novita-ai Novita AI ↗ $0.890$0.890 — — — API-measured
fireworks_ai Pricebook (LiteLLM) ↗ $0.900$0.900 — — — Official list
vercel_ai_gateway Pricebook (LiteLLM) ↗ $0.900$0.900 — — — Official list
together_ai Pricebook (LiteLLM) ↗ $1.25$1.25 — — — Official list
replicate Pricebook (LiteLLM) ↗ $1.45$1.45 — — — Official list
azure_ai Pricebook (LiteLLM) ↗ $1.14$4.56 — — — Official list

Price trend

$0.4725 $0.2 2026-09-05 → 2026-11-03 · 60d 2026-09-05 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-06 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-07 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-08 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-09 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-10 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-11 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-12 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-13 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-14 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-15 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-16 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-17 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-18 · O 0.2 H 0.4725 L 0.2 C 0.4725 $/1M2026-09-19 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-20 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-21 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-22 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-23 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-24 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-25 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-26 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-27 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-28 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-29 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-09-30 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-01 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-02 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-03 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-04 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-05 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-06 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-07 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-08 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-09 · O 0.2 H 0.4625 L 0.2 C 0.4625 $/1M2026-10-10 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-11 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-12 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-13 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-14 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-15 · O 0.2 H 0.2375 L 0.2 C 0.2375 $/1M2026-10-16 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-17 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-18 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-19 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-20 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-21 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-22 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-23 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-24 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-25 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-26 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-27 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-28 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-29 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-30 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-10-31 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-11-01 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-11-02 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M2026-11-03 · O 0.2 H 0.2 L 0.2 C 0.2 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2 → $0.2

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-v3.json. Free reuse requires attribution to tkx.org.

About

DeepSeek-V3 is an AI model designed for machine learning tasks, served by multiple inference providers on AI model marketplaces and listed under the "hyperbolic" serving-platform tag.

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

FAQ

How much does DeepSeek-V3 cost?

Cheapest measured offer right now: $0.2/1M input, $0.2/1M output via hyperbolic — across 15 tracked providers, refreshed hourly.

Who serves DeepSeek-V3?

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

Is the price of DeepSeek-V3 going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings