impulse

DeepSeek R1 Qwen3 8B

Open weights
API id deepseek-r1-0528-qwen3-8b
Input / 1M
$0.06
at Novita AI
Output / 1M
$0.09
at Novita AI
Context window
128K
tokens
Max output
32K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Novita AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.06$0.09

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$24.75
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$32.04
  • Coding agent1,000 requests a day, 40K in / 2K out$77.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$166
Use your own numbers

Where to run it

1 host serve DeepSeek R1 Qwen3 8B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Novita AIInference
0528
deepseek-r1-0528-qwen3-8b
$0.06 / $0.09

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-2.0
Runtimes: 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 Novita AI.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • gpt-oss-120b
    OpenAI · on W&B Inference
    $0.03 / $0.17
    Has every key capability
    4% less
  • Qwen3 32B
    Alibaba Qwen · on Lambda AI
    $0.05 / $0.10
    Has every key capability
    7% less
  • Gemma 4 E2B
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    26% less
  • Qwen3 8B
    Alibaba Qwen · on Novita AI
    $0.035 / $0.138
    Has every key capability
    10% less

Call it

Using Novita AI's API.

Python
from litellm import completion

response = completion(
    model="novita/deepseek-r1-0528-qwen3-8b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek R1 Qwen3 8B cost?

On Novita AI, DeepSeek R1 Qwen3 8B costs $0.06 per million input tokens and $0.09 per million output tokens.

Which APIs offer DeepSeek R1 Qwen3 8B?

DeepSeek R1 Qwen3 8B runs on 1 API: Novita AI.

What is DeepSeek R1 Qwen3 8B's context window?

128K tokens, with up to 32K tokens in one reply.

Is DeepSeek R1 Qwen3 8B being retired?

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

What are cheaper alternatives to DeepSeek R1 Qwen3 8B?

Models that cost less and keep most of what it can do: gpt-oss-120b on W&B Inference (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek R1 Qwen3 8B's API model id?

Use deepseek-r1-0528-qwen3-8b with Novita AI.

Sources

Raw catalog entry for deepseek-r1-0528-qwen3-8b on Novita AI
{
  "litellm_provider": "novita",
  "mode": "chat",
  "input_cost_per_token": 6e-8,
  "output_cost_per_token": 9e-8,
  "max_input_tokens": 128000,
  "max_output_tokens": 32000,
  "supports_system_messages": true,
  "supports_reasoning": true
}