Create a Fireworks account at app.fireworks.ai, generate your API key, store it securely, then integrate with Bifrost for ultra-low-latency inference with virtual keys, budgets, and cost governance. Complete setup in minutes.
Bifrost supports Fireworks models through OpenAI-compatible HTTP APIs and standard JSON request shapes for ultra-low-latency inference.
| Property | Details |
|---|---|
| Description | Fireworks provides ultra-low-latency LLM inference for chat, reasoning, coding, and image workloads on popular open-source models. |
| Provider route on Bifrost | fireworks/<model> |
| Provider doc | Fireworks Documentation |
| API endpoint for provider | https://api.fireworks.ai/inference/v1 |
| Supported endpoints | /v1/models, /v1/completions, /v1/chat/completions, /v1/embeddings, /v1/images/generations |
Use these Fireworks-hosted links for console access, API documentation, and authentication details.
Before you begin, you will need:
[ QUICK START ]
Use the Fireworks console.
Go to app.fireworks.ai and sign up or log in with your email address. Verify your account to access the dashboard.
After signing in, open your profile menu and select Settings. In the sidebar, click API Keys to view existing keys and create new ones.
Your key is displayed once. Copy it immediately and store it securely.
Click Create API Key, give it a descriptive name (for example development or production), then copy the key. Fireworks will not show the full key again after you leave the page.
Export as an environment variable so SDKs can read it automatically.
Paste your key into a local environment variable (macOS / Linux):
export FIREWORKS_API_KEY="fw_..."
Authenticate with Bearer tokens per Fireworks' OpenAI-compatible API.
Fireworks' API is OpenAI-compatible and uses Authorization: Bearer FIREWORKS_API_KEY for REST calls:
$ curl https://api.fireworks.ai/inference/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $FIREWORKS_API_KEY" \ -d '{ "model": "accounts/fireworks/models/llama-v3p3-70b-instruct", "messages": [{"role":"user","content":"Hello!"}] }'
[ MODELS ]
| Model | API ID | Best for |
|---|---|---|
| Llama 3.3 70B Instruct | accounts/fireworks/models/llama-v3p3-70b-instruct | Flagship Llama on Fireworks. |
| Llama 3.1 405B Instruct | accounts/fireworks/models/llama-v3p1-405b-instruct | Largest Llama 3.1 deployment. |
| Llama 3.1 70B Instruct | accounts/fireworks/models/llama-v3p1-70b-instruct | Production open-weight chat. |
| Llama 3.1 8B Instruct | accounts/fireworks/models/llama-v3p1-8b-instruct | Fast, economical inference. |
| Qwen3 235B A22B | accounts/fireworks/models/qwen3-235b-a22b | Large MoE Qwen3 on Fireworks. |
| DeepSeek V3 | accounts/fireworks/models/deepseek-v3 | DeepSeek flagship reasoning. |
| DeepSeek R1 | accounts/fireworks/models/deepseek-r1 | Chain-of-thought reasoning model. |
| Mistral Small 3 | accounts/fireworks/models/mistral-small-24b-instruct-2501 | Efficient Mistral tier. |
| FLUX.1 Dev | accounts/fireworks/models/flux-1-dev-fp8 | Image generation on Fireworks. |
Models and availability change over time. See the Fireworks model catalog for the latest list and pricing.
[ TROUBLESHOOTING ]
| Error | Likely Cause | What to Do |
|---|---|---|
401 Unauthorized | Invalid or missing API key. | Verify your API key is correct. Generate a new key if needed. |
400 Bad Request | Invalid request format or unsupported model. | Check request format against OpenAI API reference. Verify model ID. |
429 Rate Limited | Rate limit exceeded for your plan. | Upgrade your plan or implement exponential backoff. Use Bifrost for intelligent load distribution. |
404 Model Not Found | Model not found or invalid model ID in request. | Confirm the model path matches the Fireworks catalog (for example accounts/fireworks/models/...). |
502/503 Service Error | Temporary Fireworks service unavailability. | Retry after a delay. Check Fireworks status page. Configure failover with Bifrost. |
[ PRODUCTION-READY ]
Bifrost is a drop-in replacement for direct Fireworks calls. Update your base URL and keep your client code. Bifrost handles cost tracking, virtual keys, budgets, and intelligent failover.
Run the Bifrost gateway and configure your Fireworks credentials in the Web UI.
$ npx -y @maximhq/bifrost
✓ Bifrost started ├─ HTTP server listening on http://localhost:8080 ├─ Web UI available at http://localhost:8080 └─ Configure providers and virtual keys in the dashboard
Update your SDK to route through Bifrost's OpenAI-compatible gateway instead of the direct Fireworks endpoint.
from openai import OpenAI # BEFORE # client = OpenAI( # api_key="your-fireworks-key", # base_url="https://api.fireworks.ai/inference/v1" # ) # AFTER: route via Bifrost + virtual key client = OpenAI( api_key="sk-bf-your-virtual-key", base_url="http://localhost:8080/openai" ) response = client.chat.completions.create( model="accounts/fireworks/models/llama-v3p3-70b-instruct", messages=[{"role": "user", "content": "Hello from Bifrost!"}] ) print(response.choices[0].message.content)
x-bf-vk or Authorization: Bearer sk-bf-* per the Bifrost documentation.[ WHAT'S NEXT ]
You have your API key. Add governance, guardrails, and MCP controls for production.
[ BIFROST FEATURES ]
Everything you need to run AI in production, from free open source to enterprise-grade features.
01 Governance
SAML support for SSO and Role-based access control and policy enforcement for team collaboration.
02 Adaptive Load Balancing
Automatically optimizes traffic distribution across provider keys and models based on real-time performance metrics.
03 Cluster Mode
High availability deployment with automatic failover and load balancing. Peer-to-peer clustering where every instance is equal.
04 Alerts
Real-time notifications for budget limits, failures, and performance issues on Email, Slack, PagerDuty, Teams, Webhook and more.
05 Log Exports
Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export capabilities for compliance, monitoring, and analytics.
06 Audit Logs
Comprehensive logging and audit trails for compliance and debugging.
07 Vault Support
Secure API key management with HashiCorp Vault, AWS Secrets Manager, Google Secret Manager, and Azure Key Vault integration.
08 VPC Deployment
Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls.
09 Guardrails
Automatically detect and block unsafe model outputs with real-time policy enforcement and content moderation across all agents.
[ SHIP RELIABLE AI ]
Change just one line of code. Works with OpenAI, Anthropic, Vercel AI SDK, LangChain, and more.
[ FAQ ]
Fireworks specializes in ultra-low-latency inference with sub-100ms response times through optimized infrastructure and quantized models, while hosting popular open-source models at scale.
Yes. Fireworks provides free credits to get started. Check your account dashboard for current free-tier allocations and usage limits.
Yes. Fireworks provides an OpenAI-compatible API. Use the official OpenAI Python or JavaScript SDKs with base URL https://api.fireworks.ai/inference/v1 and your Fireworks API key.
Fireworks offers popular open-source models including Llama, Mistral, Qwen, DeepSeek, and Code Llama with various parameter sizes. See the Fireworks model catalog for the latest list.
Yes. Bifrost integrates with Fireworks for low-latency inference, cost tracking, virtual keys, budgets, and automatic failover across providers.
Fireworks targets sub-100ms end-to-end latency for many models through its optimized inference engine. Actual latency depends on model size, request shape, and region.