Model
Underlying LLM(s); primary + fallback + routing.
Claude Sonnet 4.6
Anthropic's workhorse coding/agent model; strong tool use, long context.
used in
19
commercial
usage
Claude Opus 4.7
Anthropic's deepest-reasoning model; planning, complex synthesis.
used in
6
commercial
usage
Gemini 2.5 Pro
Google's frontier multimodal model with very long context.
used in
6
commercial
usage
Claude Haiku 4.5
Fast, cheap small model for classification, routing, high-volume work.
used in
4
commercial
usage
Voyage-3
General-purpose text embedding model tuned for retrieval quality.
used in
1
commercial
usage
Voyage-3-large
Higher-capacity Voyage embedding model for retrieval-quality-sensitive RAG.
used in
1
commercial
usage
Claude Fable 5
Anthropic's most capable widely released model, built for demanding reasoning and long-horizon agentic work.
used in
0
commercial
usage
Claude Opus 4.8
Anthropic's Opus-tier model (May 2026) with improved coding, agentic, and honesty behavior over Opus 4.7.
used in
0
commercial
usage
Cohere Command R+
Cohere's RAG-optimized model with strong tool use + citation grounding.
used in
0
commercial
free
Cohere Rerank v4.0
Cohere's current-generation reranking models (Pro and Fast variants) for boosting retrieval relevance in RAG and agent search.
used in
0
commercial
usage
DeepSeek V3
Open-weights model with strong reasoning at very low inference cost.
used in
0
open source
free
DeepSeek V4
DeepSeek's V4 generation of open-weight MoE models with 1M-token context and agent-focused reasoning modes.
used in
0
open source
free
Gemini 2.5 Flash
Google's fast, cheap small model; long context, native multimodal.
used in
0
commercial
free
Gemini 3.5 Flash
Google's stable frontier model for sustained agentic and coding work, the current GA workhorse of the Gemini 3 family.
used in
0
commercial
usage
GLM-5
Zhipu AI's MIT-licensed 744B-parameter MoE model targeting complex systems engineering and agentic tasks.
used in
0
open source
free
GPT-5
OpenAI's frontier model; broad capability, strong tool use.
used in
0
commercial
usage
GPT-5.4
OpenAI's more affordable frontier model for coding and professional work, sitting below GPT-5.5.
used in
0
commercial
usage
GPT-5.5
OpenAI's flagship frontier model, positioned as a new class of intelligence for coding and professional work.
used in
0
commercial
usage
Grok 3
xAI's frontier model with real-time X data access.
used in
0
commercial
free
Grok 4.3
xAI's flagship API model, billed as its most intelligent and fastest, with strong agentic tool calling.
used in
0
commercial
usage
Kimi K2.6
Moonshot AI's flagship 1T-parameter open-weight MoE model with native multimodal input and interleaved-thinking tool use.
used in
0
open source
free
Llama 4 Maverick
Meta's open-weights frontier model; self-hostable on any infra.
used in
0
open source
free
Mistral Large
Mistral's frontier model — strong multilingual + EU-data-residency story.
used in
0
commercial
free
Qwen3.5 (397B-A17B)
Alibaba's Apache-2.0 open-weight Qwen3.5 flagship MoE with very low active-parameter cost and broad multilingual coverage.
used in
0
open source
free
Qwen 3 Max
Alibaba's open-weights frontier model; very strong on Chinese + code.
used in
0
open source
free
OpenAI text-embedding-3-large
OpenAI's most capable embedding model for English and non-English retrieval, served via usage-priced API.
used in
0
commercial
usage