Last refreshed 2026-06-24. Next refresh: weekly.
Why use DeepSeek V4 Pro on Fireworks AI?
Fireworks AI offers DeepSeek V4 Pro with pay-as-you-go pricing at $1.74/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Compare DeepSeek V4 Pro across 5 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport FIREWORKS_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],deepseek-v4-proRequest example
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="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
- The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.
Compare DeepSeek V4 Pro Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| DeepSeek Platform | $0.43 | $0.87 |
| Fireworks AI | $1.74 | $3.48 |
| OpenRouter | $0.44 | $0.87 |
| Vercel AI Gateway | $0.43 | $0.87 |
| Novita AI | $1.60 | $3.20 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.74 |
| Output tokens | $3.48 |
Capabilities
About DeepSeek V4 Pro
DeepSeek V4 Pro is DeepSeek's flagship open-weights model, released April 24 2026 under the MIT license. Architecture: 1.6T total / 49B active parameters, MoE with Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) hybrid — requiring only 27% of inference FLOPs vs standard 1M-context transformers — plus Manifold-Constrained Hyper-Connections (mHC) and Muon Optimizer. Context window: 1,000,000 tokens; max output: 384,000 tokens (Think Max mode requires >=384K context). Text-only (no vision/image input). Supports three reasoning modes: Non-Think, Think High, Think Max. Function calling, tool use, and structured outputs supported.