Search
“research”
Showing 1–7 of 7 for “research”
- 0.582score
Ember-1
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).
ModelAFreshness: A$3 / $151M ctx - 0.582score
Pareto 26.10
Pareto 26.10
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of…
ModelAFreshness: A$0.8 / $3.21M ctx - 0.582score
Pareto 26.9
Pareto 26.9
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of…
ModelAFreshness: A$2.5 / $7.5262K ctx - 0.582score
Relace Search
Relace
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request.
ModelAFreshness: A$1 / $3256K ctx - 0.432score
Hermes-4.3-36B
NousResearch
Open-weights 36.15B-parameter text model from NousResearch on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights - 0.587score
Qwen3.8 27B
Qwen (Alibaba)
Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
ModelAFreshness: A$0.2 / $2.51M ctxOpen weights - 0.547score
GPT-6 Astra
OpenAI
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
ModelAFreshness: A$10 / $501.1M ctx