THE COUNCIL

Pick your council. Up to 12 models + 1 chairman.

Mix and match frontier and specialist models to build the right council for your use case. Drop-in compatible with the OpenAI SDK.

Assemble your council

The full catalog

Anthropic
Claude Opus 4.7
anthropic/claude-opus-4.7
Context: 200k · Input: 5.00/M · Intelligence: 76.0
OpenAI
GPT-5.1
openai/gpt-5.1
Context: 256k · Input: $2.50/M · Intelligence: 73.0
Anthropic
Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
Context: 200k · Input: $3.00/M · Intelligence: 70.0
Alibaba
Qwen 3.6 Plus
qwen/qwen3.6-plus
Context: 1000k · Input: $0.40/M · Intelligence: 66.0
Moonshot
Kimi K2.5
moonshotai/kimi-k2.5
Context: 200k · Input: $0.50/M · Intelligence: 64.0
Zhipu
GLM 5.1
z-ai/glm-5.1
Context: 128k · Input: $0.40/M · Intelligence: 60.0
Cohere
Command A
cohere/command-a
Context: 256k · Input: $2.50/M · Intelligence: —
Google
Gemini 3.1 Pro
google/gemini-3.1-pro-preview
Context: 1049k · Input: $2.00/M · Intelligence: —
xAI
Grok 4.3
x-ai/grok-4.3
Context: 1000k · Input: .25/M · Intelligence: —
DeepSeek
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
Context: 1049k · Input: $0.44/M · Intelligence: —
Meta
Llama 3.3 70B
meta-llama/llama-3.3-70b-instruct
Context: 131k · Input: $0.10/M · Intelligence: —
Mistral
Mistral Large 3
mistralai/mistral-large-2512
Context: 262k · Input: $0.50/M · Intelligence: —

See the live benchmark scores for any of these models.

Pre-built council presets

Frequently asked questions

Which models are in the default council?

GPT-5.1, Claude Sonnet 4.5, Gemini 3 Pro, Grok 4, Kimi K2.5, Qwen 3.6 Plus, and GLM 5.1. You can swap any of them, add others from the catalog, or save your own preset.

Can I bring my own API keys?

No — Counsel runs through a single billing relationship to keep usage predictable. Per-model token costs are passed through transparently in the dashboard.

How many models can be in one council?

Up to 12 council members plus 1 chairman — the same limit applies across every plan. The chairman synthesises the council's responses and is never also a member.

Do you support open-source models?

Yes — Llama 3.1 405B, Mistral, DeepSeek V4, Qwen, GLM, and Kimi are all available. Mixing closed and open in the same council is a common pattern for cost-aware quality.