{ "name": "Nebius Token Factory", "id": "nebius", "api_key": "$NEBIUS_API_KEY", "api_endpoint": "https://api.tokenfactory.nebius.com/v1", "type": "openai-compat", "default_large_model_id": "moonshotai/Kimi-K2.5", "default_small_model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "models": [ { "id": "deepseek-ai/DeepSeek-V3.2", "name": "DeepSeek-V3.2", "cost_per_1m_in": 0.3, "cost_per_1m_out": 0.45, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 163000, "default_max_tokens": 16300, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "deepseek-ai/DeepSeek-V3.2-fast", "name": "DeepSeek-V3.2 (fast)", "cost_per_1m_in": 0.4, "cost_per_1m_out": 2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "zai-org/GLM-5", "name": "GLM-5", "cost_per_1m_in": 1, "cost_per_1m_out": 3.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 202752, "default_max_tokens": 20275, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "NousResearch/Hermes-4-405B", "name": "Hermes-4-405B", "cost_per_1m_in": 1, "cost_per_1m_out": 3, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "NousResearch/Hermes-4-70B", "name": "Hermes-4-70B", "cost_per_1m_in": 0.13, "cost_per_1m_out": 0.4, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "PrimeIntellect/INTELLECT-3", "name": "INTELLECT-3", "cost_per_1m_in": 0.2, "cost_per_1m_out": 1.1, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "moonshotai/Kimi-K2.5", "name": "Kimi-K2.5", "cost_per_1m_in": 0.5, "cost_per_1m_out": 2.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "moonshotai/Kimi-K2.5-fast", "name": "Kimi-K2.5 (fast)", "cost_per_1m_in": 0.5, "cost_per_1m_out": 2.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "meta-llama/Llama-3.3-70B-Instruct", "name": "Llama-3.3-70B-Instruct", "cost_per_1m_in": 0.13, "cost_per_1m_out": 0.4, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": false, "supports_attachments": false }, { "id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "name": "Meta-Llama-3.1-8B-Instruct", "cost_per_1m_in": 0.02, "cost_per_1m_out": 0.06, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": false, "supports_attachments": false }, { "id": "MiniMaxAI/MiniMax-M2.5", "name": "MiniMax-M2.5", "cost_per_1m_in": 0.3, "cost_per_1m_out": 1.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 196608, "default_max_tokens": 19660, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "MiniMaxAI/MiniMax-M2.5-fast", "name": "MiniMax-M2.5 (fast)", "cost_per_1m_in": 0.3, "cost_per_1m_out": 1.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "name": "Nemotron-3-Nano-30B-A3B", "cost_per_1m_in": 0.06, "cost_per_1m_out": 0.24, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "nvidia/nemotron-3-super-120b-a12b", "name": "Nemotron-3-Super-120b-a12b", "cost_per_1m_in": 0.3, "cost_per_1m_out": 0.9, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "name": "Qwen3-235B-A22B-Instruct-2507", "cost_per_1m_in": 0.2, "cost_per_1m_out": 0.6, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": false, "supports_attachments": false }, { "id": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast", "name": "Qwen3-235B-A22B-Thinking-2507 (fast)", "cost_per_1m_in": 0.5, "cost_per_1m_out": 2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "name": "Qwen3-30B-A3B-Instruct-2507", "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": false, "supports_attachments": false }, { "id": "Qwen/Qwen3-32B", "name": "Qwen3-32B", "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 40960, "default_max_tokens": 4096, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "name": "Qwen3-Next-80B-A3B-Thinking", "cost_per_1m_in": 0.15, "cost_per_1m_out": 1.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 128000, "default_max_tokens": 12800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast", "name": "Qwen3-Next-80B-A3B-Thinking (fast)", "cost_per_1m_in": 0.15, "cost_per_1m_out": 1.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3.5-397B-A17B", "name": "Qwen3.5-397B-A17B", "cost_per_1m_in": 0.6, "cost_per_1m_out": 3.6, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "Qwen/Qwen3.5-397B-A17B-fast", "name": "Qwen3.5-397B-A17B (fast)", "cost_per_1m_in": 0.6, "cost_per_1m_out": 3.6, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "cost_per_1m_in": 0.15, "cost_per_1m_out": 0.6, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false }, { "id": "openai/gpt-oss-120b-fast", "name": "gpt-oss-120b (fast)", "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8000, "default_max_tokens": 800, "can_reason": true, "reasoning_levels": [ "low", "medium", "high" ], "default_reasoning_effort": "medium", "supports_attachments": false } ] }