Inkling 2 Small
Thinking Machines1.05M context
As of Nov 14, 2026, Inkling 2 Small costs $0.15 per million input tokens and $0.50 per million output tokens from Prime Intellect. The cheapest of 4 providers is Prime Intellect at $0.15 / $0.50. No price change since Appndo started tracking it on Nov 14, 2026. Recent price changes
Providers (4)
Sorted by your monthly estimate. Prices per million tokens. Prime Intellect also lists cache writes $0.15 and up to 1.05M output tokens per request.
Prime IntellectCheapest
- Input / output
- $0.15 / $0.50
- Context
- 1.05M
- Per month
- $2.50
thinkingmachines/inkling-2-small
- Input / output
- $0.30 / $1.00
- Context
- 1.05M
- Per month
- $5.00
@cf/thinkingmachines/inkling-2-small
- Input / output
- $0.30 / $1.00
- Context
- 1.05M
- Per month
- $5.00
thinkingmachines/inkling-2-small
- Input / output
- $0.30 / $1.00
- Context
- 1.05M
- Per month
- $5.00
together_ai/thinkingmachines/Inkling-2-Small
Cloud and hosted providers may add regional pricing, minimums or platform fees. Supports: Vision, Reasoning, Tool calling.
Similar models
Step 3.5 Flash
Qwen3 VL 235B A22B Thinking
MiniMax M2.7
GPT-5Common questions
How much does the Inkling 2 Small API cost?
As of Nov 14, 2026, Inkling 2 Small costs $0.15 per million input tokens and $0.50 per million output tokens from Prime Intellect. Cached input costs $0.03 per million tokens.
Where is Inkling 2 Small cheapest?
As of Nov 14, 2026, the cheapest of 4 providers is Prime Intellect at $0.15 per million input tokens and $0.50 per million output tokens. Appndo lists no official price from Thinking Machines.
What is the context length of Inkling 2 Small?
Inkling 2 Small takes up to 1.05M tokens of context at Prime Intellect.
How does Inkling 2 Small compare with similar models?
On LMArena Inkling 2 Small scores 1403, #153 overall. Models with close scores and their cheapest price per million input / output tokens: Step 3.5 Flash ($0.10 / $0.30), Qwen3 VL 235B A22B Thinking ($0.22 / $0.88), and MiniMax M2.7 ($0.15 / $0.60).