Spiral gives your agent every tool with one account. Browse the tools →

OpenRouterLLMAvailable nowReleased 2026-11-20

Thinking Machines: Inkling 2 Mini

thinkingmachines/inkling-2-mini

Generate and analyse text with Thinking Machines: Inkling 2 Mini from OpenRouter through one Spiral API key. Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). It runs in the background and returns text and structured JSON. Pay as you go, with no subscription.

Pricing

Up to $0.034084 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens.

Limits

Runs
In the background
Returns
text, json
Longest queue wait
1 hour
Run deadline
30 minutes
Longest run, end to end
225 minutes
Largest inline input
1 MB
Largest input file
2 GB
Largest output
5 GB

Input

FieldKindDefaultDescription
messages requiredJSON—

The conversation so far, oldest first.

seednumber (whole)—
stopJSON—
min_pnumber
0 to 1
—
toolsJSON—
top_knumber (whole)
0 to …
—
top_pnumber
0 to 1
—
logprobstrue or false—
reasoningJSON—

Reasoning effort; reasoning tokens count toward max_tokens.

max_tokensnumber (whole)
1 to 65536
—

The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length).

temperaturenumber
0 to 2
—
tool_choiceJSON—
top_logprobsnumber (whole)
0 to 20
—
response_formatJSON—
presence_penaltynumber
-2 to 2
—
reasoning_effortone of
none, minimal, low, medium, high, max
high

How much the model reasons.

frequency_penaltynumber
-2 to 2
—
repetition_penaltynumber
0 to 2
—

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "thinkingmachines/inkling-2-mini",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    }
  }'

Frequently asked questions

How much does Thinking Machines: Inkling 2 Mini cost?

Up to $0.034084 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

How do I use Thinking Machines: Inkling 2 Mini through an API?

Send `POST /v1/runs` with `"provider": "openrouter"`, `"model": "thinkingmachines/inkling-2-mini"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

Do I need an account with OpenRouter to use Thinking Machines: Inkling 2 Mini?

No. Spiral runs it on its own OpenRouter account and charges your Spiral balance.

Can my AI agent use Thinking Machines: Inkling 2 Mini?

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.