Models · Best vision
Inkling (free)
by Thinkingmachines
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Our verdict
We have not reviewed Inkling (free) yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Inkling (free)
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Notes
Inkling (free) is listed in the EDNA Models directory from the OpenRouter catalogue.
Key facts
What we have checked
- Price on together
- $0.170 per million cached input tokens
- Price on together
- $1.00 per million input tokens
- Price on together
- $4.05 per million output tokens
- Latest version
- thinkingmachines/inkling-20260715
- Time to first token (ms)
- 2,170
- Time to first token (ms) on together
- 22,510
- Output speed (tokens a second)
- 188.5
- Output speed (tokens a second) on together
- 13
- Gpqa diamond
- 88.3% (for 15 July 2026)
- Frontiermath tiers 1 3 v2 private
- 33.3% (for 15 July 2026)
- Simpleqa verified
- 40.3% (for 15 July 2026)
- Arc agi 2
- 36.5% (for 15 July 2026)
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
API access
How to call it
Call via OpenRouter with model id `thinkingmachines/inkling:free`.
- openrouter ·
thinkingmachines/inkling:free· Docs
OpenRouter id: thinkingmachines/inkling:free
Price
What Inkling (free) costs, over time
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| togetherCached input | $0.170 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| togetherInput | $1.00 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| togetherOutput | $4.05 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Scores
How Inkling (free) scores
Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.
| Score | Value | Source | Checked |
|---|---|---|---|
| Apex agents (best-across-versions) | 33.8percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Arc agi (best-across-versions) | 79.5percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Arc agi 2 (best-across-versions) | 36.5percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Chess puzzles (best-across-versions) | 21percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Dtbench (best-across-versions) | 87.5percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Frontiercode (best-across-versions) | 14percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Frontiermath tier 4 v2 private (best-across-versions) | 4.9percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Frontiermath tiers 1 3 v2 private (best-across-versions) | 33.3percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Frontierswe (best-across-versions) | 4.1percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Gpqa diamond (best-across-versions) | 88.3percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Lmca (best-across-versions) | 37.6percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Otis mock aime 2024 2025 (best-across-versions)Saturated | 88.9percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) |
Show 5 more scores
| Score | Value | Source | Checked |
|---|---|---|---|
| Proofbench (best-across-versions) | 0percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Simplebench (best-across-versions) | 50percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Simpleqa verified (best-across-versions) | 40.3percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Weirdml (best-across-versions) | 32.3percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) | |
| Weirdml v3 (best-across-versions) | 4.4percentAs of 15 July 2026 | Epoch AI (CC BY 4.0) |
- Saturated
- Top models score close to the maximum, so this test no longer separates them.
Sources
Where this comes from
- OpenRouter models APIRegistry
- OpenRouter models APIThird party
- Artificial AnalysisThird party
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Price changed
input per mtok: 0.95 to 1
Price changed
input per mtok: 1 to 0.95
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Inkling (free).
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.
thinkingmachines/inkling:free- Tool calling
- Listed support
- Structured output
- Not established
- Reasoning controls
- Listed support
- Availability
- unknown
- Price basis
- token
- Licence verification
- Apache 2.0, open weights
- Context length
- 1M tokens
- Knowledge cutoff
- Not established
- Developer release date
- Not established
- First seen in the catalogue
- 17 Jul 2026
- Listed retirement date
- 4 Nov 2026
- Last listed by its catalogue
- 3 Nov 2026
Not in the OpenRouter catalogue when checked; last listed 2026-11-03. Retirement is not confirmed by a source.
Inspect the sources and their scope
thinkingmachines/inkling:free: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-11-03Source for reasoning controls, first seen, tool calling, last listed, context length, retirement date, input, output.
Checked 2026-11-03Licence declared in the thinkingmachines/Inkling model repository on Hugging Face, which holds the weights files. Read the licence terms before use.
Checked 2026-10-31FROM SPECIFICATIONS TO YOUR WORK
Is this the right model for your job?
Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.
What would it cost?
Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.
Enter a whole number of runs from 1 to 100,000,000.
Working out the cost...
Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗
Check the source
No token price is known for this model yet. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.
Model source & availability ↗Understand the evidence
Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.
Intelligence Index: 12.5 (2026-11-07) ↗Coding Index: 52.1 (2026-11-07) ↗Agentic Index: 22.5 (2026-11-07) ↗Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.