Inkling Small
thinkingmachines/inkling-small
lightweight MoE reasoning at lower cost and latency.
cmd --model thinkingmachines/inkling-small
Intelligence index
41.2
Output speed
125.2 tok/s
Input
$0.50 /M
Output
$1.20 /M
Cache read
$0.10 /M
Agent-loop cost
$0.22 /M in
Context window
1M tokens
Released
July 30, 2026
Modalities
→
vs. the lineup
Inkling Small beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Muse Spark 1.2 Contributor | 56.8◆ | 72.2◆ | —◆ | $0.10◆ | $0.20◆ | $0.13◆ | 1.05M◆ |
| Inkling | 42.3◆ | 52.1◆ | 75.3◆ | $1◆ | $4.05◆ | $1.76◆ | 256K◆ |
| Tencent Hy3 | 42.2◆ | 58.8◆ | 65.3◆ | $0.14◆ | $0.58◆ | $0.25◆ | 262K◆ |
| Inkling Small ◆ | 41.2◆ | 52.9◆ | 125.2◆ | $0.50◆ | $1.20◆ | $0.68◆ | 1M◆ |
| Qwen 3.6 Max Preview | 41.1◆ | —◆ | —◆ | $1.30◆ | $7.80◆ | $2.92◆ | 200K◆ |
| Step 3.7 Flash | 30.9◆ | 39.6◆ | 391.3◆ | $0.20◆ | $1.15◆ | $0.44◆ | 256K◆ |
| DeepSeek V4 Pro (latest)pinned | 45.3◆ | 59.4◆ | 63.3◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 52◆ | 69.1◆ | 115.9◆ | $0.14◆ | $0.28◆ | $0.18◆ | 1M◆ |
coding performance
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Inkling Small has been left empty.
Coding Index
52.9
#33 of 40 scored
Terminal-Bench
55.1
#35 of 40 scored
Intelligence Index
41.2
#30 of 46 scored
Long-context reasoning
69.3
reasoning across a long context
SciCode
48.7
scientific coding
GPQA Diamond
89.5
graduate-level QA
usage calculator
How far a month of credits goes on Inkling Small.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0056 · in $0.50 · out $1.20 · cache $0.10 per M
fresh input 7%output 4%cache reads 89%
Requests / 30 days
1.8K
$10 credits ÷ $0.0056 per request
~356 quick fixes~71 bug fixes~12 feature PRs
what real work costs
Real coding tasks priced end to end on Inkling Small, from a quick lookup to a full-repo agent run.
One agent task
$0.05
180K in at 75% cache hit, 12K out
What you pay
$0.26 /M
all-in across every token that task touched
Sticker input
$0.50 /M
cache reads bill at $0.10 /M instead
| Task | Tokens in · out | Inkling Small | Muse Spark 1.2 Contributor | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0023 | $0.0003 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.02 | $0.0027 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.05 | $0.0072 | $0.12 |
| Refactor a module | 320K · 20K | $0.09 | $0.01 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.22 | $0.03 | $0.49 |
frequently asked
What is Inkling Small best for?+
lightweight MoE reasoning at lower cost and latency.
How much does Inkling Small cost?+
$0.50/M input and $1.20/M output, cache reads $0.10/M. In an agent loop most input is cache-read, so the effective input rate is about $0.22/M.Which plan do I need?+
Available on Go and above.
How do I switch to it?+
Run
cmd --model thinkingmachines/inkling-small, or type /model in a session and pick it. You can switch mid-session without losing context.Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.
Benchmarks from Artificial Analysis (v4.1)commandcode.ai/models/inkling-small