This model was retired on 2026-03-20. The pricing below is the last-known rate, kept for migration reference.

R1 Distill Llama 70BDeprecated

DeepSeekReleasedJan 1, 2025
Tool useReasoningStructured output
Context
131K
Max output
131K
Serving providers
9
Cheapest input
$0.20 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
19 t/s
tokens / second
Time to first token
6.14s
latency
Headline indices
Intelligence Index
9.9
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy215.9default
GPQA Diamond40%default
Humanity's Last Exam6%default
IFBench28%default
LiveCodeBench27%default
Long-Context Reasoning11%default
MMLU-Pro79%default
Omniscience-46.5default
SciCode31%default
TerminalBench Hard2%default
τ²-bench22%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfra$0.20$0.601
Nebius$0.25$0.751
Nscale$0.38$0.381
Ovhcloud$0.67$0.671
SambaNova$0.70$1.401
Vercel AI Gateway$0.75$0.991
Novita$0.80$0.801
Fireworks AI$0.90$0.901
Gradient AI is dearest at $0.99 / $0.99

Price history

input + output $/1M since we started tracking
Input Output
Input down 93% since first tracked
$0.000$0.500$1.00Jan 30Aug 9Oct 13Jun 22$0.050$0.050

Cost calculator

estimate your monthly spend on this model
$88
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70Bnebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70Bnscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70Bovhcloud/DeepSeek-R1-Distill-Llama-70Bsambanova/DeepSeek-R1-Distill-Llama-70Bvercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70bnovita/deepseek/deepseek-r1-distill-llama-70bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70bgradient_ai/deepseek-r1-distill-llama-70b

Frequently asked questions

R1 Distill Llama 70B pricing, context and availability

Is R1 Distill Llama 70B still available?

R1 Distill Llama 70B was retired on 2026-03-20. The pricing on this page is the last-known rate, kept for migration reference.

How much did R1 Distill Llama 70B cost?

R1 Distill Llama 70B's last-known pricing, before it was retired on 2026-03-20, was $0.20 per 1M input tokens and $0.38 per 1M output tokens.

What was the context window of R1 Distill Llama 70B?

R1 Distill Llama 70B had a 131K token context window and could return up to 131K output tokens.

What could R1 Distill Llama 70B do?

R1 Distill Llama 70B supported tool use, reasoning and structured output.

Other DeepSeek models

compare pricing across the DeepSeek lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI