// Thinking Machines
Inkling
A Thinking Machines model. 2 prices across 2 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.95 / $4.05
- Context
- 524K
- AA index
- 25
Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Thinking Machines |
|---|---|
| Context window | 524K (524,288 tokens) |
| Max output | 262K |
| Input | Text · Image · Audio |
| Output | Text |
| Tool calling / JSON | Yes / No |
| Weights & licence | Open weights · Apache-2.0 · Hugging Face |
| Parameters | 952B (from weight files) |
| Released | Jul 17, 2026 |
| Model IDs | thinkingmachines/inkling |
02Prices on 2 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| DeepInfra · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.95 | $4.05 | $0.16 | 1.73 | 524K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against DeepInfra's own page |
| Together · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $1 | $4.05 | $0.17 | 1.76 | 524K | Together price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against Together's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Via OpenRouter / provider listed there
DeepInfra · Together - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
Inkling (OpenRouter)→ - Free option
Inkling→
04Performance
All results →Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexInkling (Xhigh)
- 25
- Output speed (median)
- 178 tok/s
- Time to first token
- 1.81s
- AA index per $ (blended)
- 14.48
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1441 | official | 2026-10-08 |
| LMArena WebDev | 1413 | official | 2026-10-08 |
| GPQA Diamond | 88.3% | independent | 2026-08-05 |
| AIME (OTIS Mock AIME 2024–2025) | 88.9% | independent | 2026-08-05 |
| τ²-bench | 25.0% | official | 2026-07-24 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from Thinking Machines
FAQ
How much does the Inkling API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.95 / $4.05 on DeepInfra.
What is the context window of Inkling?
524K tokens of context, up to 262K output tokens. Platforms may cap it lower – see the table.
Is Inkling open source?
Yes, the weights are published on Hugging Face (thinkingmachines/Inkling). Licence: Apache-2.0.