Skip to main content

Using Fireworks AI With PostQode

Fireworks AI is a high-performance platform for running AI models that offers fast access to a wide range of open-source and proprietary language models. Built for speed and reliability, Fireworks AI provides both serverless and dedicated deployment options with OpenAI-compatible APIs.

Website: https://fireworks.ai/

Getting an API Key​

  1. Sign Up/Sign In: Go to Fireworks AI and create an account or sign in.
  2. Navigate to API Keys: After logging in, go to the API Keys page in the account settings.
  3. Create a Key: Click "Create API key" and give your key a descriptive name (e.g., "PostQode").
  4. Copy the Key: Copy the API key immediately and store it securely. You will not be able to see it again.

Supported Models​

PostQode supports the following Fireworks AI models across coding, deep reasoning, and general-purpose foundation tiers:

Coding & Agentic Execution​

  • accounts/fireworks/models/qwen2p5-coder-32b-instruct - (Recommended for Coding) High-precision coding, unified diffs, and tool calling
  • accounts/fireworks/models/qwen3-coder-480b-a35b-instruct - Qwen 3 Coder frontier code generation engine
  • accounts/fireworks/models/deepseek-v3 - DeepSeek V3 671B MoE flagship model for agentic coding and general instruction

Deep Reasoning & Planning​

  • accounts/fireworks/models/deepseek-r1 (or accounts/fireworks/models/deepseek-r1-0528) - (Recommended for Planning) Frontier 671B open-weights chain-of-thought reasoning
  • accounts/fireworks/models/deepseek-r1-distill-llama-70b - Fast distilled reasoning on Llama 70B architecture

General Purpose & Long Context​

  • accounts/fireworks/models/llama-v3p3-70b-instruct - Meta Llama 3.3 70B versatile reasoning and generation
  • accounts/fireworks/models/llama-v3p1-405b-instruct - Meta Llama 3.1 405B frontier open-weights model
  • accounts/fireworks/models/llama-v3p1-8b-instruct - Ultra-fast lightweight model for quick edits and commit generation
  • accounts/fireworks/models/kimi-k2-instruct - Moonshot Kimi K2 high-efficiency long-context instruct model
  • accounts/fireworks/models/qwen3-235b-a22b-instruct-2507 - Qwen 3 235B instruction-tuned model
  • accounts/fireworks/models/mixtral-8x22b-instruct - High-throughput Mixture-of-Experts model

Configuration in PostQode​

  1. Open PostQode Settings: Click the gear icon () in the PostQode panel.
  2. Select Provider: Choose "Fireworks AI" from the "API Provider" dropdown.
  3. Enter API Key: Paste your Fireworks AI API key into the "Fireworks AI API Key" field.
  4. Select Model: Choose your desired model from the "Model" dropdown.

Tips and Notes​

  • Performance: Fireworks AI is optimized for speed and offers excellent performance for both chat and completion tasks.
  • Pricing: Refer to the Fireworks AI Pricing page for current pricing information.
  • Rate Limits: Fireworks AI has usage-based rate limits. Monitor your usage in the dashboard and consider upgrading your plan if needed.
Is this documentation incorrect or incomplete? Report an issue on GitHub