DeepSeek R1 Distill Qwen 1 5B
DeepSeek-R1-Distill-Qwen-1.5BPricing
List prices at Nscale, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.09 | $0.09 |
What it costs a month
At Nscale list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$33.75
- RAG over documents2,000 requests a day, 8K in / 0.6K out$46.44
- Coding agent1,000 requests a day, 40K in / 2K out$113
- Overnight batch20,000 requests a day, 4K in / 0.4K out$238
Where to run it
2 hosts serve DeepSeek R1 Distill Qwen 1 5B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
NscaleInference DeepSeek-R1-Distill-Qwen-1.5B | $0.09 / $0.09 | DeepSeek-R1-Distill-Qwen-1.5B | |
Fireworks AIInference deepseek-r1-distill-qwen-1p5b | $0.10 / $0.10 +11% vs headline | deepseek-r1-distill-qwen-1p5b |
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: Apache-2.0Runtimes: Ollama, SGLang, 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
- 3% less
- 8% less
- 3% less
- 17% less
Call it
Using Nscale's API.
from litellm import completion
response = completion(
model="nscale/DeepSeek-R1-Distill-Qwen-1.5B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek R1 Distill Qwen 1 5B cost?
On Nscale, DeepSeek R1 Distill Qwen 1 5B costs $0.09 per million input tokens and $0.09 per million output tokens.
Which APIs offer DeepSeek R1 Distill Qwen 1 5B?
DeepSeek R1 Distill Qwen 1 5B runs on 2 APIs: Nscale and Fireworks AI.
What is DeepSeek R1 Distill Qwen 1 5B's context window?
131K tokens, with up to 131K tokens in one reply.
Is DeepSeek R1 Distill Qwen 1 5B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek R1 Distill Qwen 1 5B?
Models that cost less and keep most of what it can do: Nemotron 3 Nano 30B A3B on DeepInfra (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek R1 Distill Qwen 1 5B's API model id?
Use DeepSeek-R1-Distill-Qwen-1.5B with Nscale. Other hosts use their own ids: deepseek-r1-distill-qwen-1p5b on Fireworks AI.
Sources
Raw catalog entry for DeepSeek-R1-Distill-Qwen-1.5B on Nscale
{
"input_cost_per_token": 9e-8,
"litellm_provider": "nscale",
"metadata": {
"notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
},
"mode": "chat",
"output_cost_per_token": 9e-8,
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}