Thinkingmachines
Inkling
Launched 2026-07-15 · Listed on OpenRouter 2026-07-17
Prices updated . Benchmarks updated .
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,...
You send / 1M
$1.00
tokens in
It replies / 1M
$4.05
tokens out
Context
1.05M
tokens it can read at once
Typical request
$0.0033
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 148.5 | Independent | 2026-07-15 | Epoch AI |
| GPQA DiamondExtra high effort | 88.3% | Independent | 2026-08-05 | Epoch AI |
| OTIS Mock AIMEExtra high effort | 88.9% | Independent | 2026-08-05 | Epoch AI |
| SimpleQA VerifiedExtra high effort | 40.3% | Independent | 2026-08-27 | Epoch AI |
| ARC-AGI-2 | 36.5% | Independent | 2026-07-15 | ARC Prize, republished by Epoch AI |
| CritPtExtra high effort | 5.4% | Independent | 2026-07-15 | CritPt, republished by Epoch AI |
| Arena Elo (text) | 1,443 | Independent | 2026-10-28 | LMArena |
| Arena Elo (webdev) | 1,415 | Independent | 2026-10-28 | LMArena |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Together | $1.00 | $4.05 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image, audio
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
- Repeated text is billed at $0.170 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with Inkling
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
