diff --git a/dot_config/crush/crush.json b/dot_config/crush/crush.json index 72d65eae0892c4944fc726e1d2a9245c500f01bb..add431235e2530575ee7d47d95115b815f469811 100644 --- a/dot_config/crush/crush.json +++ b/dot_config/crush/crush.json @@ -66,6 +66,122 @@ "supports_attachments": true } ] + }, + "cerebras": { + "name": "Cerebras", + "type": "openai-compat", + "api_key": "$CEREBRAS_API_KEY", + "api_endpoint": "https://api.cerebras.ai/v1", + "models": [ + { + "id": "zai-glm-4.6", + "name": "GLM 4.6", + "cost_per_1m_in": 0, + "cost_per_1m_out": 0, + "context_window": 131072, + "default_max_tokens": 40960, + "can_reason": true, + "supports_attachments": false + }, + { + "id": "llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout", + "cost_per_1m_in": 0.65, + "cost_per_1m_out": 0.85, + "context_window": 32768, + "default_max_tokens": 4000, + "can_reason": false, + "supports_attachments": false + }, + { + "id": "llama3.1-8b", + "name": "Llama 3.1 8B", + "cost_per_1m_in": 0.1, + "cost_per_1m_out": 0.1, + "context_window": 32768, + "default_max_tokens": 4000, + "can_reason": false, + "supports_attachments": false + }, + { + "id": "llama-3.3-70b", + "name": "Llama 3.3 70B", + "cost_per_1m_in": 0.85, + "cost_per_1m_out": 1.2, + "context_window": 128000, + "default_max_tokens": 4000, + "can_reason": false, + "supports_attachments": false + }, + { + "id": "gpt-oss-120b", + "name": "gpt-oss-120b", + "cost_per_1m_in": 0.4, + "cost_per_1m_out": 0.8, + "context_window": 128000, + "default_max_tokens": 65536, + "can_reason": true, + "reasoning_levels": ["low", "medium", "high"], + "default_reasoning_efforts": "medium", + "supports_attachments": false + }, + { + "id": "qwen-3-32b", + "name": "Qwen 3 32B", + "cost_per_1m_in": 0.4, + "cost_per_1m_out": 0.8, + "context_window": 128000, + "default_max_tokens": 32768, + "can_reason": false, + "supports_attachments": false + }, + { + "id": "llama-4-maverick-17b-128e-instruct", + "name": "Llama 4 Maverick", + "cost_per_1m_in": 0.2, + "cost_per_1m_out": 0.6, + "context_window": 32768, + "default_max_tokens": 4000, + "can_reason": false, + "supports_attachments": false + }, + { + "id": "qwen-3-235b-a22b-instruct-2507", + "name": "Qwen 3 235B Instruct", + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 1.2, + "context_window": 131072, + "default_max_tokens": 16384, + "can_reason": true, + "reasoning_levels": ["low", "medium", "high"], + "default_reasoning_efforts": "medium", + "supports_attachments": false + }, + { + "id": "qwen-3-235b-a22b-thinking-2507", + "name": "Qwen 3 235B Thinking", + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 1.2, + "context_window": 128000, + "default_max_tokens": 32768, + "can_reason": true, + "reasoning_levels": ["low", "medium", "high"], + "default_reasoning_efforts": "medium", + "supports_attachments": false + }, + { + "id": "qwen-3-coder-480b", + "name": "Qwen 3 480B Coder", + "cost_per_1m_in": 2.0, + "cost_per_1m_out": 2.0, + "context_window": 131072, + "default_max_tokens": 65536, + "can_reason": true, + "reasoning_levels": ["low", "medium", "high"], + "default_reasoning_efforts": "medium", + "supports_attachments": false + } + ] } } } diff --git a/dot_config/private_fish/config.fish.tmpl b/dot_config/private_fish/config.fish.tmpl index 2570dff6423c43c2ac4fab0102bd60f956034436..b12c169b510745d6e0ebca29c955a9da917778b6 100644 --- a/dot_config/private_fish/config.fish.tmpl +++ b/dot_config/private_fish/config.fish.tmpl @@ -91,6 +91,7 @@ set -x PERPLEXITY_API_KEY '{{ onepasswordRead "op://Private/nkhcb2h2ecfh26hksdgp set -x PERPLEXITY_LENSES '{{ onepasswordRead "op://Private/nkhcb2h2ecfh26hksdgpw5txfu/lenses/text" }}' set -x SYNTHETIC_API_KEY '{{ onepasswordRead "op://Private/Synthetic/keys/main" }}' set -x GEMINI_API_KEY '{{ onepasswordRead "op://Private/Personal Google/gemini api" }}' +set -x CEREBRAS_API_KEY '{{ onepasswordRead "op://Private/Cerebras/api keys/cli" }}' set -x OLLAMA_HOST '100.108.156.33:11434' # PATHs