impulse

DeepSeek R1 Distill Llama 8B

Open weights
API id DeepSeek-R1-Distill-Llama-8B
Input / 1M
$0.025
at Nscale
Output / 1M
$0.025
at Nscale
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.025$0.025

What it costs a month

At Nscale list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$9.38
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$12.90
  • Coding agent1,000 requests a day, 40K in / 2K out$31.50
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$66.00
Use your own numbers

Where to run it

3 hosts serve DeepSeek R1 Distill Llama 8B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NscaleInference
DeepSeek-R1-Distill-Llama-8B
$0.025 / $0.025
Fireworks AIInference
deepseek-r1-distill-llama-8b
$0.20 / $0.20
+700% vs headline
GMI CloudInference
DeepSeek-R1-Distill-Llama-8B
$0.14 / $0.39
+710% 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 Nscale.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using Nscale's API.

Python
from litellm import completion

response = completion(
    model="nscale/DeepSeek-R1-Distill-Llama-8B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek R1 Distill Llama 8B cost?

On Nscale, DeepSeek R1 Distill Llama 8B costs $0.025 per million input tokens and $0.025 per million output tokens.

Which APIs offer DeepSeek R1 Distill Llama 8B?

DeepSeek R1 Distill Llama 8B runs on 3 APIs: Nscale, Fireworks AI and GMI Cloud.

What is DeepSeek R1 Distill Llama 8B's context window?

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

Is DeepSeek R1 Distill Llama 8B being retired?

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

What are cheaper alternatives to DeepSeek R1 Distill Llama 8B?

Models that cost less and keep most of what it can do: Llama 3.2 3B Instruct on DeepInfra (20% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek R1 Distill Llama 8B's API model id?

Use DeepSeek-R1-Distill-Llama-8B with Nscale. Other hosts use their own ids: deepseek-r1-distill-llama-8b on Fireworks AI.

Sources

Raw catalog entry for DeepSeek-R1-Distill-Llama-8B on Nscale
{
  "input_cost_per_token": 2.5e-8,
  "litellm_provider": "nscale",
  "metadata": {
    "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
  },
  "mode": "chat",
  "output_cost_per_token": 2.5e-8,
  "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}