Last refreshed 2026-04-19. Next refresh: weekly.
Why use Phi-4 14B on Fireworks AI?
Fireworks AI offers Phi-4 14B with pay-as-you-go pricing at $0.90/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Compare Phi-4 14B across 3 providers to find the best fit for your use caseInput / 1M
$0.90
Output / 1M
$0.90
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export FIREWORKS_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],Model ID
phi-4Request 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="phi-4",
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 Phi-4 14B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.07 | $0.14 |
| Fireworks AI | $0.90 | $0.90 |
| Microsoft Foundry | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
Structured Outputs
FAQ
What does Phi-4 14B cost on Fireworks AI?
On Fireworks AI, Phi-4 14B costs $0.9 per 1M input tokens and $0.9 per 1M output tokens.
How does Fireworks AI compare to other Phi-4 14B providers?
Phi-4 14B is available from 3 providers. The cheapest input pricing is $0.065/1M tokens from OpenRouter.
Who created Phi-4 14B?
Phi-4 14B was created by Microsoft Research as part of the Phi-4 model family.
Is Phi-4 14B open source?
Phi-4 14B is open source according to the seed data.
Get Started
Model Specs
Released2024-12-13
Parameters14B
ArchitectureDecoder Only