Fireworks AI
Fast, production-grade inference platform
SpeedFunction callingFine-tuningProduction reliabilityOpenAI-compatible
About Fireworks AI
Fireworks AI provides high-performance inference for open-source and custom models with a focus on production reliability. They offer fine-tuning capabilities, function calling, and structured output with excellent latency.
Key Models
Llama 4 MaverickQwen 3.5Firefunction
Live Performance Data
Fireworks AI Models on Antbase
| Model | Score | Requests | Success Rate | Avg Latency | p95 Latency | Capabilities |
|---|---|---|---|---|---|---|
| Deepseek V4 Pro 0813 | 61.0 | 1 | 10000.0% | 2042ms | 2042ms | 🔧 |
| Kimi K2 Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| Flux Kontext Max | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁 |
| Gpt Oss 20b | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2 Instruct 0905 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Mixtral 8x22b Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Cogito 671b V2 P1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Deepseek V3p1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Deepseek V3p2 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Glm 5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Flux Kontext Pro | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁 |
| Glm 4p7 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Deepseek V4 Flash 0731 | 45.0 | 5 | 10000.0% | 61156ms | 101091ms | 🔧 |
| Deepseek V4 Pro | 45.0 | 1 | 10000.0% | 19278ms | 19278ms | 🔧 |
| Kimi K2p5 | 32.0 | 1 | 0.0% | 1919ms | 1919ms | 👁🔧 |
How to Use Fireworks AI on Antbase
All Fireworks AI models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Fireworks AI model or let ANT's intelligent router automatically select the best model for your task.
python
from openai import OpenAI
client = OpenAI(
base_url="https://antbase.ai/v1",
api_key="your-ant-api-key",
)
# Let ANT auto-route (may use Fireworks AI if optimal)
response = client.chat.completions.create(
model="ant:auto",
messages=[{"role": "user", "content": "Hello!"}],
)
# Or route directly to a Fireworks AI model
response = client.chat.completions.create(
model="fireworks/llama-4-maverick",
messages=[{"role": "user", "content": "Hello!"}],
)Why Use Fireworks AI Through Antbase?
- •No separate account needed — access Fireworks AI models instantly through your Antbase API key.
- •Intelligent routing — ANT automatically selects the best Fireworks AI model for each task, or falls over to another provider if Fireworks AI is slow or down.
- •Same token prices — Antbase charges zero markup on Fireworks AI token prices. You pay exactly what Fireworks AI charges.
- •Automatic failover — if Fireworks AI has an outage, your requests seamlessly route to an equivalent model on another provider.