> ## Documentation Index
> Fetch the complete documentation index at: https://cyberpaisa-dof-mesh-40-27.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Config Reference

> Provider chains per role, temperatures, and llm_config.py configuration.

## Provider Chains per Role

Defined in `core/llm_config.py`. Primary provider is `minimax` across all roles.
Fallbacks are tried in order when the primary fails or rate-limits.

```python theme={null}
PROVIDER_CHAINS = {
    "code_architect":    ["minimax", "groq/kimi-k2", "cerebras", "zhipu", "nvidia/kimi-k2.5"],
    "research_analyst":  ["minimax", "groq/llama-3.3", "cerebras", "zhipu", "nvidia/deepseek"],
    "mvp_strategist":    ["minimax", "cerebras", "groq/llama-3.3", "zhipu", "nvidia/qwen3.5"],
    "qa_reviewer":       ["minimax", "cerebras", "groq/llama-3.3", "zhipu", "nvidia/deepseek"],
    "data_engineer":     ["minimax", "cerebras", "groq/llama-3.3", "zhipu", "nvidia/deepseek"],
    "project_organizer": ["minimax", "groq/qwen3-32b", "cerebras", "zhipu", "nvidia/deepseek"],
    "narrative_content": ["minimax", "cerebras", "groq/llama-3.3", "zhipu", "nvidia/deepseek"],
    "verifier":          ["minimax", "cerebras", "groq/llama-3.3", "zhipu", "nvidia/deepseek"],
}
```

***

## Temperatures per Role

```python theme={null}
TEMPERATURES = {
    "code_architect":    0.2,  # deterministic
    "qa_reviewer":       0.2,  # strict
    "verifier":          0.2,  # deterministic
    "data_engineer":     0.1,  # minimal variance
    "project_organizer": 0.3,  # structured
    "research_analyst":  0.5,  # balanced
    "mvp_strategist":    0.6,  # creative
    "narrative_content": 0.7,  # creative
}
```

***

## Provider Notes

| Provider   | Model                                  | Limits             | Special config                          |
| ---------- | -------------------------------------- | ------------------ | --------------------------------------- |
| MiniMax    | MiniMax-M2.1                           | 1,000 req/day free | Primary — no special config             |
| Groq       | llama-3.3-70b, kimi-k2, qwen3-32b      | 12K TPM            | Key expires frequently                  |
| NVIDIA NIM | qwen3.5-397b, kimi-k2.5, deepseek-v3.2 | 1,000 NIM credits  | Prefix `nvidia_nim/`                    |
| Cerebras   | gpt-oss-120b                           | 1M tokens/day      | —                                       |
| SambaNova  | DeepSeek-V3.2                          | 24K context        | Backup only                             |
| Gemini     | gemini-2.5-flash                       | 20 req/day         | 1M context                              |
| Zhipu      | glm-4.7-flash                          | —                  | `extra_body={"enable_thinking": False}` |
| OpenRouter | hermes-3-llama-3.1-405b                | Free tier          | —                                       |

***

## TTL Backoff

When a provider fails:

```python theme={null}
TTL_BACKOFF = [5, 10, 20]  # minutes: 1st, 2nd, 3rd+ failures
```

After the backoff period, the provider is retried with an exponential cooldown cap.
Circuit breaker state: `CLOSED → OPEN → HALF_OPEN → CLOSED`.

***

## Using a Custom Provider Chain

```python theme={null}
from core.llm_config import LLMConfig

config = LLMConfig()
config.set_chain("code_architect", [
    "minimax",
    "groq/llama-3.3",
    "local-agi-m4max"
])
```

***

## Environment Variables

```bash theme={null}
MINIMAX_API_KEY=
GROQ_API_KEY=gsk_...
NVIDIA_API_KEY=
CEREBRAS_API_KEY=
SAMBANOVA_API_KEY=
OPENROUTER_API_KEY=
GEMINI_API_KEY=
```

For local nodes: `LOCAL_MODEL_ENDPOINT=http://localhost:11434`

***

<CardGroup cols={2}>
  <Card title="Providers & Agents" icon="robot" href="/guides/providers-and-agents">
    17 agents and 11 crews
  </Card>

  <Card title="Mesh Nodes" icon="network-wired" href="/concepts/mesh-nodes">
    Local node table with system prompts
  </Card>
</CardGroup>