hybrid-llm-routing-for-23-stage-pipelines
For AutoResearchClaw’s 23-stage pipeline, use Opus 4.6 only for the 8 critical reasoning stages (hypothesis generation, experiment design, paper writing, peer review simulation — stages 2, 7, 8, 9, 14, 15, 17, 18) and Haiku 4.5 for the 15 routine stages (topic init, resource planning, export, status checks). AutoResearchClaw natively supports primary + fallback model configuration. Stay within the Anthropic ecosystem (Haiku not GPT-4o-mini) to avoid managing external API keys and billing.
Related
- autoresearchclaw-hybrid-llm-opus-haiku-stage-split
- hybrid-opus-haiku-llm-routing-for-multi-stage-research-pipel
- hybrid-opus-haiku-llm-config-for-autoresearchclaw-stages
- researchclaw-hybrid-llm-haiku45-for-routine-stages
- oracle-researchclaw-hybrid-llm-opus-haiku-split
- researchclaw-hybrid-llm-opus-for-8-critical-stages-haiku-for
- researchclaw-hybrid-llm-opus-haiku-not-external-providers
- oracle-researchclaw-hybrid-model-opus-haiku-not-gpt