Model Metadata
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- license
- Apache-2.0
- modalities
- input: text, image/png, image/jpeg, audio/wav; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 1,048,576; output: 1,048,576
- weights
- label: Hugging Face; url: https://huggingface.co/thinkingmachines/Inkling
Provider Variants 10
deepinfra thinkingmachines/Inkling
Context 524,288 · Output 1,048,576
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg, audio/wav; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No; prompt_cache_key: Yes
- limit
- context: 524,288; output: 1,048,576
- id
- thinkingmachines/Inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- status
- deprecated
- api
- chat-completions: base_url: https://api.deepinfra.com/v1/openai; sdk: aisdk: @ai-sdk/deepinfra; opencodeai: @opencode/ai/providers/deepinfra; capabilities: tools: updates: No
Fireworks accounts/fireworks/models/inkling
Context 1,048,576 · Output 1,048,576
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: Yes; effort_updates: No
- limit
- context: 1,048,576; output: 1,048,576
- id
- accounts/fireworks/models/inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- status
- deprecated
- api
- chat-completions: base_url: https://api.fireworks.ai/inference/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/fireworks; capabilities: tools: updates: No; responses: base_url: https://api.fireworks.ai/inference/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No; messages: base_url: https://api.fireworks.ai/inference/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: updates: No
huggingface thinkingmachines/Inkling
Context 1,048,576 · Output 1,048,576
- name
- Inkling
- description
- Multimodal model for analyzing text, images, documents, and rich media
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: low, medium, high; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 1,048,576; output: 1,048,576
- id
- thinkingmachines/Inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- chat-completions: base_url: https://router.huggingface.co/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; compatibility: max_tokens_field: max_tokens; capabilities: tools: updates: No; responses: base_url: https://router.huggingface.co/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No
OpenRouter thinkingmachines/inkling
Context 524,288 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Inkling
- description
- Multimodal reasoning model for visual analysis, planning, and tool use
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg, audio/wav; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, max; structured_output: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 524,288; output: 128,000; input: 396,288
- id
- thinkingmachines/inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- chat-completions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @openrouter/ai-sdk-provider; opencodeai: @opencode/ai/providers/openrouter; capabilities: tools: choice: auto, none, required, tool; updates: No; responses: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: choice: auto, none, required, tool; updates: No; messages: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, none, required, tool; updates: No
OpenRouter thinkingmachines/inkling:free
Context 1,182,720 · Output 262,144
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Inkling (free)
- description
- Multimodal reasoning model for visual analysis, planning, and tool use
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg, audio/wav; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, max; structured_output: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 1,182,720; output: 262,144; input: 920,576
- id
- thinkingmachines/inkling:free
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- chat-completions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @openrouter/ai-sdk-provider; opencodeai: @opencode/ai/providers/openrouter; capabilities: tools: updates: No; responses: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No; messages: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: updates: No
Thinking Machines thinkingmachines/Inkling
Context 65,536 · Output 65,536
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; effort: low, medium, high, xhigh, max; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 65,536; output: 65,536
- id
- thinkingmachines/Inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- messages: base_url: https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, required, tool, none; updates: No
Thinking Machines thinkingmachines/Inkling:peft:262144
Context 262,144 · Output 262,144
- name
- Inkling (256K)
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; effort: low, medium, high, xhigh, max; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 262,144
- id
- thinkingmachines/Inkling:peft:262144
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- messages: base_url: https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, required, tool, none; updates: No
Thinking Machines thinkingmachines/Inkling:peft:262144:sampling-nvfp4
Context 262,144 · Output 262,144
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; effort: low, medium, high, xhigh, max; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 262,144; output: 262,144
- id
- thinkingmachines/Inkling:peft:262144:sampling-nvfp4
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- messages: base_url: https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, required, tool, none; updates: No
togetherai thinkingmachines/Inkling
Context 524,288 · Output 131,072
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg, image/gif, image/webp, audio/wav; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, xhigh, max; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: Yes; effort_updates: No; prompt_cache_key: Yes
- limit
- context: 524,288; output: 131,072
- id
- thinkingmachines/Inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- chat-completions: base_url: https://api.together.xyz/v1; sdk: aisdk: @ai-sdk/togetherai; opencodeai: @opencode/ai/providers/togetherai; capabilities: tools: updates: No
vercel thinkingmachines/inkling
Context 256,000 · Output 128,000
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- Inkling
- description
- Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- family
- ling
- open weights
- Yes
- release date
- 2026-07-15
- modalities
- input: text, image/png, image/jpeg, application/pdf; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, minimal, low, medium, high, xhigh, max; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 256,000; output: 128,000; input: 128,000
- id
- thinkingmachines/inkling
- canonical id
- thinkingmachines/inkling
- type
- chat
- last updated
- 2026-07-15
- api
- chat-completions: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/gateway; opencodeai: @opencode/ai/providers/vercel-ai-gateway; capabilities: system_updates: Yes; tools: choice: auto, none, required, tool; updates: No; responses: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/open-responses; opencodeai: @opencode/ai/providers/vercel-ai-gateway/responses; capabilities: tools: choice: auto, none, required, tool; updates: No; messages: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/vercel-ai-gateway/messages; capabilities: tools: choice: auto, none, required, tool; updates: No