Thinking Machines: Inkling
thinkingmachines/inkling
Inkling is Thinking Machines's open-weight contender, ranking #53 of 235 on the TryAii Score. Its best showing is #34 on LiveCodeBench. API pricing starts at $1/$4.05 per million input/output tokens, though similar scores now sell for about $2.5 per million output tokens, with 3 independent hosts serving it. It's among the fastest models we track, at roughly 112-143 tokens/sec.
Prompt $/1M
$1.000
Completion $/1M
$4.050
Context
1,048,576 tok
Best provider
189 tok/s · DeepInfra
Specs
- Model id
- thinkingmachines/inkling
- Display name
- Thinking Machines: Inkling
- Modality
- text+image+audio->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 471,859
- Prompt $/1M
- $1.000
- Completion $/1M
- $4.050
- Free tier
- no
Capabilities
- Function callingyes
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| DeepInfrafastest | 189 |
| Together | 128 |
| BaseTen | 125 |
| Artificial Analysis | 75 |