Using DeepSeek R1 0528 on Fireworks AI
Implementation guide · DeepSeek R1 · DeepSeek
ServerlessOpen Source
Fireworks AI exposes DeepSeek R1 0528 through model ID accounts/fireworks/models/deepseek-r1-0528. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-05-21. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/deepseek-r1-0528— see the documentation for request format. - 3
Code Examples
Install
pip install openaiAPI key
FIREWORKS_API_KEYModel ID
accounts/fireworks/models/deepseek-r1-0528Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/deepseek-r1-0528",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.56 |
| Output tokens | $1.68 |
Capabilities
ReasoningStructured OutputsCode Execution
About DeepSeek R1 0528
DeepSeek R1 0528 is DeepSeek's DeepSeek R1 model with an optional reasoning mode. It offers a 130K-token context window with weights openly available for self-hosting and scores 81 on GPQA.
Model Specs
Released2025-05-28
Parameters685B total, 37B active (MoE)
Context130k
ArchitectureDecoder Only