Sypha AI Docs
Provider config

Fireworks AI

Learn how to configure and use Fireworks AI models with Sypha. Access high-performance open-source language models with fast, cost-effective APIs.

Sypha accommodates model access through the Fireworks AI platform, which provides rapid, cost-efficient access to a diverse range of cutting-edge open-source language models. Engineered for velocity and reliability, Fireworks AI delivers serverless deployment capabilities with OpenAI-compatible APIs and context windows extending to 256,000 tokens.

Website: https://fireworks.ai/

Obtaining an API Key

  1. Account Creation/Login: Access Fireworks AI and establish an account or authenticate.
  2. Navigate to API Keys: Following authentication, proceed to the API Keys page in the account settings.
  3. Generate a Key: Select "Create API key" and assign your key a meaningful name (for instance, "Sypha").
  4. Retrieve the Key: Critical: Copy the API key right away. This is your only opportunity to view it. Keep it in a secure location.

Available Models

Sypha accommodates the following Fireworks AI models:

  • accounts/fireworks/models/kimi-k2-instruct (Default)
  • accounts/fireworks/models/qwen3-235b-a22b-instruct-2507
  • accounts/fireworks/models/qwen3-coder-480b-a35b-instruct
  • accounts/fireworks/models/deepseek-r1-0528
  • accounts/fireworks/models/deepseek-v3

Model Specifications:

ModelContext WindowBest ForPricing (per 1M tokens)
Kimi K2128KGeneral tasks, agentic capabilities$0.60 input, $2.50 output
Qwen3 235B256KCost-effective general use$0.22 input, $0.88 output
Qwen3 Coder256KCode generation and debugging$0.45 input, $1.80 output
DeepSeek R1160KComplex reasoning, function calling$3.00 input, $8.00 output
DeepSeek V3128KStrong general performance$0.90 input, $0.90 output

Sypha Configuration

  1. Access Sypha Configuration: Select the settings icon (⚙️) within the Sypha panel.
  2. Choose Provider: Pick "Fireworks AI" from the "API Provider" selector.
  3. Insert API Key: Place your Fireworks AI API key into the "Fireworks AI API Key" field.
  4. Choose Model: Select your preferred model from the "Model" selector. The default model is Kimi K2.

Important Considerations

  • Economic Efficiency: Fireworks AI provides substantially reduced pricing versus proprietary models while sustaining competitive performance.
  • Extensive Context Windows: Most models accommodate 128K-256K tokens, appropriate for processing substantial documents and maintaining prolonged conversations.
  • OpenAI Compatibility: The provider employs an OpenAI-compatible API format with streaming support and usage tracking.
  • Rate Constraints: Fireworks AI implements usage-based rate limitations. Track your consumption in the dashboard and evaluate upgrading your plan if necessary.
  • API Keys: Stored locally on your machine for security.
  • Cost Structure: Consult the Fireworks AI pricing page for current rates. Displayed prices are per million tokens.

On this page