Inkling (256K) API Pricing
Thinking Machines · released Jul 15, 2026 · 262K context · API model ID thinkingmachines/Inkling:peft:262144
Inkling (256K) by Thinking Machines API pricing: $3.74 per 1M input tokens and $9.36 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $3.74 |
| Output | $9.36 |
| Cache read | $0.748 |
| Cache write | Not published |
Thinking Machines' list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$2,526
per month
- per day
- $84.20
- per request
- $0.00842
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $2,526/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $5,190/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $2,581/mo |
Context and capabilities
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Input
- text, image
- Output
- text
- Knowledge cutoff
- Not published
- Open weights
- Yes
- Tool calling
- Yes
- Reasoning
- Yes
- Structured outputs
- No
Capabilities and limits as listed by models.dev.
Similarly priced models
- Gemini 3.1 Pro Preview · $2.00 in / $12.00 out
- Kimi K3 · $3.00 in / $15.00 out
- Claude Sonnet 5.5 · $2.00 in / $10.00 out
- GPT-6.1 Sol · $2.00 in / $10.00 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does Inkling (256K) cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Inkling (256K) costs about $2,526 per month at Thinking Machines' list prices ($3.74 per 1M input tokens, $9.36 per 1M output tokens).
- Does Inkling (256K) support prompt caching?
- Yes. Cached input costs $0.748 per 1M tokens, compared with $3.74 for regular input.
- How long is Inkling (256K)'s context window?
- Inkling (256K) accepts up to 262,144 tokens (262K) of context and returns up to 262,144 tokens per response.