Inkling 2 Small API Pricing / Price per 1M tokens
Thinking Machines Inkling 2 Small, announced 2026-11-05. MoE, 594B total / 17B active, Hybrid + Vision, image and text input. Initially available on Tinker with closed weights. The announcement says the full weights are intended for Apache 2.0 next week after external safety testing and red-teaming; no calendar date and no weight URL were published, so open_source is false and license is NULL. Base context is published as 64K with no raw token integer (65536 is not stored). Extended and serverless context is 256K; the Tinker id suffix is 262144, stored as context_window. Prefill $0.30, cached prefill $0.03 and sample $1.00 per million tokens apply to both contexts and to serverless inference. Train is $1.50 per million tokens at 64K and $3.00 at 256K. No supported-regions list was published. Catalog 2026-11-06 Inkling 2 Small. Verified 2026-11-06. Source: https://thinkingmachines.ai/news/inkling-2-small/ ; https://tinker-docs.thinkingmachines.ai/tinker/models/models_and_pricing/ ; https://tinker-docs.thinkingmachines.ai/tinker/models.json ; https://tinker-docs.thinkingmachines.ai/tinker/serverless.json
thinkingmachines β’ API Price Comparison
Also known as: thinkingmachines-inkling-2-small Β· thinkingmachines inkling 2 small Β· thinkingmachinesinkling2small Β· thinkingmachines-inkling2-small Β· thinkingmachines inkling2 small Β· inkling-2-small Β· inkling2small Β· inkling2-small Β· inkling2 small
API pricing and token costs at a glance
Updated on Β· Published currencies / per 1M tokens; cheapest ranked by input
| Channel | Input / 1M | Output / 1M | Cache read / 1M | Updated / verified on |
|---|---|---|---|---|
| thinkingmachinesOfficialLowest input | USD 0.3 | USD 1 | USD 0.03 | 2026-11-06 |
Metered API cost = input tokens / 1M Γ input rate + output tokens / 1M Γ output rate. At the lowest-input-rate channel, 1M input plus 250K output tokens costs approximately USD 0.55. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.
β means the price or date is not recorded. Cross-currency ranking uses exchange rates.
Inkling 2 Small is a large language model by thinkingmachines with a 262K-token context window. Across the 1 API channels tracked here, input pricing ranges from $0.30 per 1M input tokens; the cheapest is thinkingmachines at $0.30 per 1M input tokens. The official channel (thinkingmachines) charges $0.30 per 1M input tokens and $1.00 per 1M output tokens. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.
| Channel | Type | Input / 1M | Output / 1M | Rate Limit | vs Official | |
|---|---|---|---|---|---|---|
thinkingmachinesπ° Best Priceπ’ Official | Official | $0.30 | $1.00 | - | Baseline |
| Usage Level | Tokens/Month | thinkingmachines |
|---|---|---|
| π£ Light | 0.1M in + 0.1M out | $0.08 |
| π Medium | 1.0M in + 0.5M out | $0.80 |
| π Heavy | 10.0M in + 5.0M out | $8.00 |
| π’ Enterprise | 100.0M in + 50.0M out | $80.00 |
Frequently asked questions about Inkling 2 Small
How much does the Inkling 2 Small API cost?
The lowest input rate is USD 0.3 per 1M tokens; output on that channel is USD 1 per 1M tokens.
Which channel has the cheapest Inkling 2 Small API?
thinkingmachines has the lowest input rate: USD 0.3 per 1M tokens. Cross-currency ranking uses exchange rates; compare output and cache prices separately.
What is the Inkling 2 Small cache-read price?
thinkingmachines: USD 0.03 per 1M cache-read tokens.
When was Inkling 2 Small pricing last updated?
Updated on 2026-11-06. This is the latest recorded price update or verification; see the table for individual channel dates.
Is there a free Inkling 2 Small API?
No available recorded channel lists both input and output at zero. Missing prices, free cache reads or a free chat tier do not establish a free API; check provider terms for trial credits.
How do I calculate Inkling 2 Small token costs and monthly spend?
Metered API cost = input tokens / 1M Γ input rate + output tokens / 1M Γ output rate. At the lowest-input-rate channel, 1M input plus 250K output tokens costs approximately USD 0.55. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.