Models

DeepSeek-R1

hyperbolic · 164K ctx · 15 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.400 Official list · Hyperbolic
Avg price
$2.25 /1M
providers
15
(3 × $0.400 + $0.400) ÷ 4 = $0.400/1M — 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 $0.400, 3:1 $0.400, 1:1 $0.400, output only $0.400 per 1M.

The board shows this model's cheapest measured offer ($0.400/1M); the smaller figure under it is the mean of the 18 offers listed below ($2.25/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
hyperbolic Pricebook (LiteLLM) $0.400$0.400 Official list
burncloud burncloud $0.500$2.18 API-measured
deepseek Pricebook (LiteLLM) $0.550$2.19 Official list
openrouter Pricebook (LiteLLM) $0.550$2.19 Official list
vercel_ai_gateway Pricebook (LiteLLM) $0.550$2.19 Official list
deepinfra Pricebook (LiteLLM) $0.700$2.40 Official list
novita HuggingFace Router $0.700$2.50 708ms 14 API-measured
Novita (fp8) OpenRouter $0.700$2.50 1253ms 16 100% API-measured
nebius Pricebook (LiteLLM) $0.800$2.40 Official list
requesty Requesty $0.850$2.50 API-measured
azure_ai Pricebook (LiteLLM) $1.35$5.40 Official list
snowflake Pricebook (LiteLLM) $1.35$5.40 Official list
Azure OpenRouter $1.49$5.94 API-measured
together_ai Pricebook (LiteLLM) $3.00$7.00 Official list
novita-ai Novita AI $4.00$4.00 API-measured
fireworks_ai Pricebook (LiteLLM) $3.00$8.00 Official list
replicate Pricebook (LiteLLM) $3.75$10.00 Official list
sambanova Pricebook (LiteLLM) $5.00$7.00 Official list

Who burns this model

Top apps routing traffic to this model over the last 30 days, via OpenRouter's public stats. Only apps that opted into tracking appear, and only the top few are published — this is not the full demand picture. These figures are a 30-day window and are NOT comparable with the cumulative totals on the Apps board.

AppTokens (30d)Requests
Janitor AI 3B 308K
Hermes Agent 712M 28K
Cline 631M 16K
Transsion-Assistant 437M 74K
SillyTavern 325M 31K

Price trend

$0.4 $0.4 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-07 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-08 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-09 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-10 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-11 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-12 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-13 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-14 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-15 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-16 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-17 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-18 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-19 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-20 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-21 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-22 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-23 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-24 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-25 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-26 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-27 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-28 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-29 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-30 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-07-31 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-08-01 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-08-02 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-08-03 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-08-04 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M2026-08-05 · O 0.4 H 0.4 L 0.4 C 0.4 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4 → $0.4

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-r1.json. Free reuse requires attribution to tkx.org.

About

DeepSeek-R1 is an AI model designed for machine learning tasks, particularly leveraging hyperbolic geometry for enhanced performance in certain applications. It is served by multiple inference providers on AI model marketplaces.

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

FAQ

How much does DeepSeek-R1 cost?

Cheapest measured offer right now: $0.4/1M input, $0.4/1M output via hyperbolic — across 15 tracked providers, refreshed hourly.

Who serves DeepSeek-R1?

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-R1 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