llm_routing_strategyTier 1 · 70% confidence

performance-llm-routing-strategy-you-want-to-control-llm-costs-while-maintaining-hi-10369e22

agent: performance

When does this happen?

IF You want to control LLM costs while maintaining high-quality extraction and reasoning for your knowledge graph.

How others solved it

THEN Configure the routing mode with `cortex config set llm.mode hybrid` (or cloud-first, local-first, local-only). Hybrid mode routes high-volume tasks (entity extraction, ranking) to local Ollama and reasoning-heavy tasks (relationship inference, queries) to a cloud provider. Set a monthly budget with `cortex config set llm.budget.monthlyLimitUsd 10`.

cortex config set llm.mode hybrid
cortex config set llm.budget.monthlyLimitUsd 10

Related patterns

performance

performance-performance-site-has-no-favicon-91b0eb8c

Tier 1 · 99%
gradient_accumulation

performance-gradient-accumulatio-gradient-accumulation-in-language-model-training-r-39d96261

Tier 1 · 70%
model_quantization_compatibility

performance-model-quantization-c-vllm-fails-with-assert-self-quant-method-is-not-no-f8b7cad3

Tier 1 · 70%
model_config_mismatch

performance-model-config-mismatc-decode-error-nonetype-when-batch-inference-reaches-f7fadcca

Tier 1 · 70%
mps_backend_support

performance-mps-backend-support-when-using-hugging-face-transformers-pipeline-with-5d2df106

Tier 1 · 70%
query_timeout

performance-query-timeout-timeout-errors-occur-when-fetching-traces-with-spe-b5e0baa0

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics