Thinking Machines: Inkling (batch)✓ Catalog verified
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Overview
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Access: available through the official Thinkingmachines API. Context window: 524K.
Specifications
| API identifier | thinkingmachines/inkling:batch |
| Provider | Thinkingmachines |
| Model type | Multimodal LLM |
| Context window | 524K catalog |
| Input modalities | text · image · audio |
| Output modalities | text |
| Released | Jul 17, 2026 |
| Moderated | No |
| Architecture modality | text+image+audio->text |
API defaults
{
"top_k": null,
"top_p": null,
"temperature": null,
"presence_penalty": null,
"frequency_penalty": null,
"repetition_penalty": null
}Pricing
Live pricing components for thinkingmachines/inkling:batch as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $5e-7 | $0.50 / 1M | Per input token |
| Completion tokens | $0.000002025 | $2.02 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.66Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | ✓ Supported | Image and document analysis support |
| Audio Processing | ✓ Supported | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Thinking Machines: Inkling (batch) through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="thinkingmachines/inkling:batch",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| MiniMax: MiniMax M3 (batch) | Minimax | 524K | $0.15 | View → |
| NVIDIA: Nemotron 3 Ultra | Nvidia | 512K | $0.60 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Thinking Machines: Inkling (batch) cost?
$0.50 per 1M input tokens and $2.02 per 1M output tokens on the official Thinkingmachines API.
What is the context window of Thinking Machines: Inkling (batch)?
Thinking Machines: Inkling (batch) supports up to 524K tokens of context.
Does Thinking Machines: Inkling (batch) support tool / function calling?
Yes, Thinking Machines: Inkling (batch) supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Thinking Machines: Inkling (batch)?
Use the official Thinkingmachines API with the model id `thinkingmachines/inkling:batch`. See the Quick start section above for code examples.