Reasoning Council
Deep thinking models for complex analysis, logic puzzles, mathematical proofs, and research workloads. These models prioritize accuracy over speed.
๐ฌ Use case: Complex analysis, logic puzzles, research
7
Models
5
Providers
52
Max tok/s
Free
Best price
๐ Council Models
| Model | Provider | Speed | โ | Context | Price | Notes |
|---|---|---|---|---|---|---|
| deepseek-v4-pro | OpenCode | 52 t/s | โ โ โ โ โ | 128K | $10/mo | Flagship reasoning model |
| cogito-2.1:671b | OllamaCloud | 45 t/s | โ โ โ โ โ | 128K | Free | 671B params, massive model |
| dola-seed-2.0-pro | BytePlus | 50 t/s | โ โ โ โ ยฝ | 64K | $9/mo | BytePlus reasoning flagship |
| claude-opus-4-6 | Venice | 33 t/s | โ โ โ โ โ | 200K | $20/mo | Uncensored Claude Opus via Venice |
| claude-opus-4-6 | ORBIT | 29 t/s | โ โ โ โ โ | 200K | Free | Free Claude Opus (2B tokens/mo) |
| qwen3-235b-thinking | Chutes TEE | 28 t/s | โ โ โ โ โ | 128K | $9/mo | Thinking model, TEE-secured |
| deepseek-v3.2-tee | Chutes TEE | 28 t/s | โ โ โ โ โ | 128K | $9/mo | Deep reasoning, TEE-secured |
โ๏ธ Pros & Cons
โ Pros
- Claude Opus via ORBIT is free (2B tokens/mo)
- TEE-secured options for confidential analysis
- Thinking models (qwen3-235b, deepseek-v4-pro) show reasoning steps
- 671B parameter model available (cogito-2.1)
- Claude Opus has 200K context window
โ ๏ธ Cons
- Slower generation speeds (28-52 t/s)
- Premium models cost $9-20/mo
- TEE models are slower than non-TEE equivalents
- Large models may have longer time-to-first-token
๐ Try This Council
Send a complex reasoning prompt and compare deep analysis across models.
# Reasoning Council: Deep analysis with thinking model
curl -X POST https://api.opencode.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Prove that the square root of 2 is irrational using proof by contradiction."}],
"temperature": 0.1,
"max_tokens": 2000
}'