{
  "key": "inkling",
  "name": "Inkling",
  "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
  "lab": "nvidia",
  "family": "ling",
  "release_date": "2026-07-15",
  "knowledge": null,
  "open_weights": true,
  "has_free_offering": true,
  "published": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "audio"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": true,
    "tool_call": true,
    "structured_output": null,
    "attachment": true,
    "reasoning_options": []
  },
  "limit": {
    "context": 1048576,
    "output": 1048576
  },
  "offerings": [
    {
      "provider": "abacus",
      "provider_model_id": "thinkingmachines/Inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 3.74,
        "output": 9.36,
        "cache_read": 0.748,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 262144,
        "output": 131072,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "baseten",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "deepinfra",
      "provider_model_id": "thinkingmachines/Inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.95,
        "output": 4.05,
        "cache_read": 0.16,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "edenai",
      "provider_model_id": "deepinfra/thinkingmachines/Inkling",
      "name": "Inkling (Deep Infra)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.95,
        "output": 4.05,
        "cache_read": 0.16,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "edenai",
      "provider_model_id": "fireworks_ai/accounts/fireworks/models/inkling",
      "name": "Inkling (Fireworks AI)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "edenai",
      "provider_model_id": "together_ai/thinkingmachines/Inkling",
      "name": "Inkling (Together AI)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "fireworks-ai",
      "provider_model_id": "accounts/fireworks/models/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "huggingface",
      "provider_model_id": "thinkingmachines/Inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 1048576,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "hyper",
      "provider_model_id": "inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.0888,
        "output": 4.40964,
        "cache_read": 0.185096,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2026-09-05"
    },
    {
      "provider": "impossibl",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.87,
        "output": 4.68,
        "cache_read": 0.374,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 65536,
        "output": 65536,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "kilo",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.95,
        "output": 4.05,
        "cache_read": 0.16,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 471859,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "llmtr",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.87,
        "output": 4.68,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 262144,
        "output": 262144,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "merge-gateway",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048000,
        "output": 32000,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048000,
        "output": 32768,
        "input": 1048000
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "thinkingmachines/inkling:thinking",
      "name": "Inkling Thinking",
      "variants": [
        "thinking"
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048000,
        "output": 32768,
        "input": 1048000
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "neon",
      "provider_model_id": "inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 65536,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "nvidia",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": false,
      "cost": {
        "input": 0,
        "output": 0,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "openrouter",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 471859,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "openrouter",
      "provider_model_id": "thinkingmachines/inkling:free",
      "name": "Inkling (free)",
      "variants": [
        "free"
      ],
      "free": true,
      "priced": false,
      "cost": {
        "input": 0,
        "output": 0,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 262144,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "requesty",
      "provider_model_id": "inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.87,
        "output": 4.68,
        "cache_read": 0.374,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 65536,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "thinkingmachines",
      "provider_model_id": "thinkingmachines/Inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.87,
        "output": 4.68,
        "cache_read": 0.374,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 65536,
        "output": 65536,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "togetherai",
      "provider_model_id": "thinkingmachines/Inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 131072,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    },
    {
      "provider": "venice",
      "provider_model_id": "inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.25,
        "output": 5.0625,
        "cache_read": 0.2125,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 524288,
        "output": 65536,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-17"
    },
    {
      "provider": "vercel",
      "provider_model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 4.05,
        "cache_read": 0.17,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 256000,
        "output": 256000,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-15"
    }
  ]
}