Inkling Small
Intelligence
26.09
#140 of 520 models
Output speed
173.9 tok/s
Measured generation rate
Cost / index task
$0.089
Measured evaluation workload
End-to-end latency
16ms
First answer 14ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
23 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $0.300
- Output / 1M
- $1.20
- Cache read / 1M
- $0.060
- Cache write / 1M
- —
- Cache-hit discount
- 80%
Response & usage
- Output speed
- 173.9 tok/s
- First chunk
- 2ms
- First answer
- 14ms
- Output / task
- 30.2k
- Reasoning / task
- 22.9k
Evaluation workload
- Canonical input
- 962.62M
- Canonical output
- 137.28M
- Answer / task
- 7.3k
- Index time / task
- 2.7m
- Run cost
- $240.846
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 188.9 tok/s | 2ms | 12ms | 15ms |
| Long | 173.9 tok/s | 2ms | 14ms | 16ms |
| Hundred K | 170.2 tok/s | 5ms | 17ms | 20ms |
| Medium Parallel | 161.6 tok/s | 2ms | 14ms | 17ms |
04 / Access
License & availability
Recorded license
Apache 2.0
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Permissive
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- thinkingmachines/inkling-small
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 3
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| DeepInfra | fp8 | 524.3k | — |
| BaseTen | fp8 | 1.05M | — |
| Together | unknown | 524.3k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.