Inkling
by Thinkingmachines · thinkingmachines/inkling · #219 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.00
per 1M tokens
Output
$4.05
per 1M tokens
Blended (3:1)
$1.76
3 input : 1 output
Cache read
$0.17
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Inkling with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.76 | $0.1061 | — |
| 50% | $1.45 | $0.0646 | −39% |
| 90% | $1.20 | $0.0313 | −70% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.001715 | $1.71 |
| Document summary | 8,000 | 1,000 | $0.012 | $12.05 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0381 | $38.10 |
| Long-context analysis | 150,000 | 5,000 | $0.1702 | $170.25 |
Performance
Intelligence Index
40.7
AA composite quality
Coding Index
52.1
Math Index
—
Agentic Index
32.3
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
524K
tokens
Max output
—
tokens
Input modalities
text, image, audio
Tokenizer
Other