NVIDIA: Inkling Thinking
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (4 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestthinkingmachines/Inkling | DeepInfra | $0.95 | $4.05 | $0.16 | 524K |
| models.devdeepinfra/thinkingmachines/Inkling | Eden AI | $0.95 | $4.05 | $0.16 | 524K |
| models.devthinkingmachines/inkling | Kilo Gateway | $0.95 | $4.05 | $0.16 | 524K |
| models.devthinkingmachines/inkling | Baseten | $1 | $4.05 | $0 | 1.0M |
| models.devfireworks_ai/accounts/fireworks/models/inkling | Eden AI | $1 | $4.05 | $0.17 | 1.0M |
| models.devaccounts/fireworks/models/inkling | Fireworks AI | $1 | $4.05 | $0.17 | 1.0M |
| models.devthinkingmachines/Inkling | Hugging Face | $1 | $4.05 | $0 | 1.0M |
| models.devthinkingmachines/inkling | Merge Gateway | $1 | $4.05 | $0.17 | 1.0M |
| models.devthinkingmachines/inkling | NanoGPT | $1 | $4.05 | $0.17 | 1.0M |
| OpenRouterthinkingmachines/inkling | OpenRouter | $1 | $4.05 | $0.17 | 1.0M |
| models.devthinkingmachines/Inkling | Together AI | $1 | $4.05 | $0.17 | 524K |
| models.devthinkingmachines/inkling | Vercel AI Gateway | $1 | $4.05 | $0.17 | 256K |
| models.devinkling | Neon | $1 | $4.05 | $0.17 | 1.0M |
| models.devthinkingmachines/inkling:thinking | NanoGPT | $1 | $4.05 | $0.17 | 1.0M |
| LiteLLMaccounts/fireworks/models/inkling | N/A | $1 | $4.05 | $0.17 | N/A |
| LiteLLMthinkingmachines/Inkling | N/A | $1 | $4.05 | $0.17 | N/A |
| LiteLLMthinkingmachines/inkling:batch | N/A | $1 | $4.05 | $0.17 | N/A |
| LiteLLMInkling | N/A | $1 | $4.05 | $0.17 | N/A |
| models.devdatabricks/databricks-inkling | Eden AI | $1 | $4.05 | $0.17 | 1M |
| LiteLLMdatabricks/databricks-inkling | N/A | $1 | $4.05 | $0.17 | N/A |
| LiteLLMdatabricks-inkling | N/A | $1 | $4.05 | $0.17 | N/A |
| models.devinkling | Charm Hyper | $1.09 | $4.41 | $0.1851 | 1.0M |
| models.devinkling | Venice AI | $1.25 | $5.06 | $0.2125 | 524K |
| models.devthinkingmachines/inkling | Impossibl | $1.87 | $4.68 | $0.374 | 66K |
| models.devthinkingmachines/inkling | LLMTR | $1.87 | $4.68 | $0 | 262K |
| models.devthinkingmachines/Inkling | Thinking Machines | $1.87 | $4.68 | $0.374 | 66K |
| models.devinkling | Requesty | $1.87 | $4.68 | $0.374 | 66K |
| models.devthinkingmachines/Inkling | Abacus | $3.74 | $9.36 | $0.748 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: audio
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence25i
- AA coding52.1i
- AA agentic22.5i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
Run this model in a real workspace
Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.
Data and list-price estimates may contain mistakes. Not investment advice.