AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
13 matches for "cost optimization"
Coding agent evaluation guide · GitHub · Intermediate to advanced
You want GitHub's September 2, 2026 evidence for measuring coding-agent efficiency across the whole task, including selective output compression, preserving useful context, benchmark regressions, and controlled production experiments.
github copilot, coding agents, context engineering, evals, cost optimization
Model orchestration research preview · GitHub · Intermediate to advanced
You want GitHub's September 4, 2026 technical explanation of runtime model orchestration for coding tasks, including plan decomposition, draft-critique-revise patterns, model cascading, evaluation design, and quality-versus-cost tradeoffs.
github copilot, model orchestration, model selection, coding agents, evals
Guide · OpenAI · Intermediate to advanced
Your agent has a large function, namespace, or MCP catalog and you want GPT-5.4 or later models to load only the tool definitions needed at runtime, reducing context use while preserving prompt-cache efficiency.
openai, agents, tool search, deferred tools, mcp
Guide · OpenAI · Intermediate
You need the current OpenAI guidance for trading higher spend for lower latency in interactive or tool-heavy workflows instead of assuming standard processing is the only mode.
openai, fast mode, latency, gpt-5.6, interactive workflows
Guide · OpenAI · Intermediate
You want the official OpenAI pattern for queueing large asynchronous jobs such as eval runs, backfills, classification batches, or dataset generation.
openai, batch api, async workflows, cost optimization, offline processing
Guide · OpenAI · Intermediate
You need the current OpenAI guidance for trading latency for lower cost on non-urgent workloads instead of pushing everything through the default realtime path.
openai, flex processing, cost optimization, latency tradeoffs, batch workloads
Guide · OpenAI · Intermediate
You need the official pattern for compressing long agent conversations and preserving the right context instead of letting transcripts grow until quality or cost breaks down.
openai, compaction, context management, long-running agents, reasoning
Guide · Anthropic · Intermediate
You need Anthropic's current guidance for reusing repeated long context efficiently instead of paying full price and latency on every Claude request.
anthropic, prompt caching, claude, cost optimization, latency
Guide · Google AI for Developers · Intermediate
You want the official Gemini route for high-volume asynchronous generation, evaluation, extraction, or backfill workloads.
gemini, batch api, async workflows, cost optimization, offline processing
Guide · DeepSeek · Intermediate
You want the official DeepSeek KV-cache guidance before building repeated long-context workflows or comparing caching behavior with other providers.
deepseek, context caching, kv cache, cost optimization, latency
Guide · xAI · Intermediate to advanced
You want xAI's official guidance for shrinking long conversations into reusable compact state before teaching Grok-heavy agent workflows at scale.
xai, context compaction, agents, long context, cost optimization
Guide · OpenRouter · Intermediate
You want the official explanation of sticky provider routing, cache-hit behavior, and cost tradeoffs before using OpenRouter as a long-context or agent backend.
openrouter, prompt caching, routing, cost optimization, latency
Guide · OpenRouter · Intermediate
You want the official OpenRouter request-level caching model before building repeated eval, agent, or research workflows that can benefit from cache hits above the provider layer.
openrouter, response caching, cost optimization, latency, agents