Skip to content

Inkling

Reasoning
thinkingmachines/inkling

1M context · Jul 2026 · 7 upstreams

Inkling is Thinking Machines Lab's first open-weights foundation model: a 975B-parameter multimodal Mixture-of-Experts transformer (41B active, 256 experts) with a 1M token context window, switchable reasoning effort, and tool use. Accepts text, image, and audio inputs; outputs text. Pretrained on 45T tokens.

Bring your own keyAnyRouter has no platform route for Inkling. Requests use your key and bill your provider account. AnyRouter adds no fee.
context
1M
input / 1M (list)
$0.95
output / 1M (list)
$4.05
routes
8
speed, 24h
—

Upstreams

8
  1. 1OpenRouterYour key · not addedyour planTPS —TTFT ——
  2. 2OpenRouterYour key · not addedyour planTPS —TTFT ——
  3. 3CommandCodeYour key · not addedyour planTPS —TTFT ——
  4. 4Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
  5. 5DeepInfraYour key · not addedyour planTPS —TTFT ——
  6. 6Hugging FaceYour key · not addedyour planTPS —TTFT ——
  7. 7Venice AIYour key · not addedyour planTPS —TTFT ——
  8. 8Nous ResearchYour key · not addedyour planTPS —TTFT ——

Try it

Send a prompt

Uptime, last 48 hours

No health checks yet.

  • Up
  • No traffic
  • Down

Details

Owner
Thinkingmachines
Kind
Vision
Released
Jul 2026
Context
1M
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "thinkingmachines/inkling",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'