impulse

DeepSeek R1 Distill Llama 70B

Open weights
API id DeepSeek-R1-Distill-Llama-70B
Input / 1M
$0.20
at DeepInfra
Output / 1M
$0.60
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
9
9 listings
Released
-
date not published

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$0.60

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$105
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$118
  • Coding agent1,000 requests a day, 40K in / 2K out$276
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$624
Use your own numbers

Where to run it

9 hosts serve DeepSeek R1 Distill Llama 70B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
DeepSeek-R1-Distill-Llama-70B
$0.20 / $0.60
GMI CloudInference
DeepSeek-R1-Distill-Llama-70B
$0.25 / $0.75
+25% vs headline
DeepSeek-R1-Distill-Llama-70B
$0.25 / $0.75
+25% vs headline
NscaleInference
DeepSeek-R1-Distill-Llama-70B
$0.375 / $0.375
+25% vs headline
DeepSeek-R1-Distill-Llama-70B
$0.67 / $0.67
+123% vs headline
Novita AIInference
deepseek-r1-distill-llama-70b
$0.80 / $0.80
+167% vs headline
deepseek-r1-distill-llama-70b
$0.75 / $0.99
+170% vs headline
Fireworks AIInference
deepseek-r1-distill-llama-70b
$0.90 / $0.90
+200% vs headline
deepseek-r1-distill-llama-70b
$0.99 / $0.99
+230% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than DeepInfra.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    33% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    33% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    13% less

Open-weight picks

  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    13% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    16% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    40% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    47% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/DeepSeek-R1-Distill-Llama-70B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek R1 Distill Llama 70B cost?

On DeepInfra, DeepSeek R1 Distill Llama 70B costs $0.20 per million input tokens and $0.60 per million output tokens.

Which APIs offer DeepSeek R1 Distill Llama 70B?

DeepSeek R1 Distill Llama 70B runs on 9 APIs: DeepInfra, GMI Cloud, Nebius AI Studio, Nscale, OVHcloud AI Endpoints, Novita AI, Vercel AI Gateway, Fireworks AI and GradientAI.

What is DeepSeek R1 Distill Llama 70B's context window?

131K tokens, with up to 131K tokens in one reply.

Is DeepSeek R1 Distill Llama 70B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to DeepSeek R1 Distill Llama 70B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (33% less), GPT-6 Luna on OpenAI (33% less) and Mistral Small 2603 on Mistral AI (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek R1 Distill Llama 70B's API model id?

Use DeepSeek-R1-Distill-Llama-70B with DeepInfra. Other hosts use their own ids: deepseek-r1-distill-llama-70b on Novita AI, deepseek-r1-distill-llama-70b on Vercel AI Gateway, deepseek-r1-distill-llama-70b on Fireworks AI, deepseek-r1-distill-llama-70b on GradientAI.

Sources

Raw catalog entry for DeepSeek-R1-Distill-Llama-70B on DeepInfra
{
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "input_cost_per_token": 2e-7,
  "output_cost_per_token": 6e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": false
}