Models

DeepSeek-R1-Distill-Llama-70B

deepinfra · 131K ctx · 10 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.300 Official list · DeepInfra
Avg price
$0.680 /1M
providers
10
(3 × $0.200 + $0.600) ÷ 4 = $0.300/1M — 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 $0.300, 1:1 $0.400, output only $0.600 per 1M.

The board shows this model's cheapest measured offer ($0.300/1M); the smaller figure under it is the mean of the 13 offers listed below ($0.680/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
deepinfra Pricebook (LiteLLM) $0.200$0.600 — — — Official list
requesty Requesty $0.230$0.690 — — — API-measured
nscale Pricebook (LiteLLM) $0.375$0.375 — — — Official list
nebius Pricebook (LiteLLM) $0.250$0.750 — — — Official list
ovhcloud Pricebook (LiteLLM) $0.670$0.670 — — — Official list
novita Pricebook (LiteLLM) $0.800$0.800 — — — Official list
Novita (bf16) OpenRouter $0.800$0.800 1034ms 15 100% API-measured
novita HuggingFace Router $0.800$0.800 937ms 14 — API-measured
novita-ai Novita AI $0.800$0.800 — — — API-measured
vercel_ai_gateway Pricebook (LiteLLM) $0.750$0.990 — — — Official list
sambanova Pricebook (LiteLLM) $0.700$1.40 — — — Official list
fireworks_ai Pricebook (LiteLLM) $0.900$0.900 — — — Official list
gradient_ai Pricebook (LiteLLM) $0.990$0.990 — — — 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 42M 8961
Schwartz PGG Experiment 26M 10K
SillyTavern 21M 5017
Chub AI 19M 4719
BRR LLM Unified Benchmark Suite 18M 12K

Price trend

$0.3 $0.3 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-07 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-08 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-09 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-10 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-11 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-12 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-13 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-14 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-15 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-16 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-17 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-18 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-19 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-20 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-21 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-22 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-23 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-24 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-25 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-26 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-27 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-28 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-29 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-30 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-07-31 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-08-01 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-08-02 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-08-03 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-08-04 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M2026-08-05 · O 0.3 H 0.3 L 0.3 C 0.3 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3 → $0.3

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-distill-llama-70b.json. Free reuse requires attribution to tkx.org.

About

DeepSeek-R1-Distill-Llama-70B is a large language model designed for natural language processing tasks, served by multiple inference providers on AI model marketplaces under the "deepinfra" tag.

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

FAQ

How much does DeepSeek-R1-Distill-Llama-70B cost?

Cheapest measured offer right now: $0.2/1M input, $0.6/1M output via deepinfra — across 10 tracked providers, refreshed hourly.

Who serves DeepSeek-R1-Distill-Llama-70B?

10 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-Distill-Llama-70B 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