API pricing and cost

Inkling 2 Mini pricing

Inkling 2 Mini official API pricing is $0.15 per million input tokens and $0.50 per million output tokens.

Covers the 2026-11-20 Inkling 2 Mini release.

$0.15

Official input / 1M

Standard tier

$0.50

Official output / 1M

Standard tier

$0.123

Blended / 1M

4:1 input/output, 90% input cached

$12.28

Example monthly cost

10K requests, 8K input + 2K output/request, 90% input cached

Token charges only; tool calls, taxes, and other non-token fees are excluded.

Official API pricing

USD / 1M text tokens · Standard · Effective from 2026-11-20

InputStandard text tier, per million tokens
$0.15
Cached inputInput served from the prompt cache
$0.015
OutputStandard text tier, per million tokens
$0.50

What Inkling 2 Mini costs to run

Four workloads costed at official standard rates. Cached-input share is an estimation assumption, not a provider guarantee; when no cached rate is published, all input is billed at the uncached rate. Non-token fees are excluded.

Estimated monthly cost of four workloads on Inkling 2 Mini
WorkloadPer requestMonthly tokensInputOutputPer month
Chatbotshort turns1,500 in · 500 out× 100,000 requests150M in · 50M out$22.50$25.00$47.50$0.000475 / request
Assistant8K context · 90% cached8,000 in · 2,000 out× 10,000 requests80M in · 20M out$2.28$10.00$12.28$0.001228 / request
RAGlong input, cached · 50% cached24,000 in · 800 out× 20,000 requests480M in · 16M out$39.60$8.00$47.60$0.00238 / request
Coding agentlong output · 70% cached15,000 in · 4,000 out× 20,000 requests300M in · 80M out$16.65$40.00$56.65$0.002833 / request
Start from

Monthly cost

$12.28

on Inkling 2 Mini

Per request

$0.001228

80M in · 20M out a month

Split

$2.28 + $10.00

input + output

Inkling 2 Mini against comparable models

Benchmark-overlap peers and price-comparable same-type models, costed on the assistant workload above. All figures use the same workload and caching rule; lower price does not imply equivalent capability or service terms.

Blended price and monthly cost of Inkling 2 Mini and comparable models
ModelBasisBlended / 1MPer monthvs Inkling 2 Mini
Claude Haiku 5.5AnthropicLower-cost option$0.115$11.526.2%cheaper
Phi-4-mini-reasoningMicrosoftLower-cost option$0.12$12.002.3%cheaper
Qwen3-32BAlibabaLower-cost option$0.12$12.002.3%cheaper
Inkling 2 MiniThinking Machines Lab · this modelThis model$0.123$12.28—
Nemotron 3.5 Super VLNVIDIAShared benchmark coverage$0.126$12.642.9%dearer
Muse Glimmer-30BFacebook AI Research LabShared benchmark coverage$0.293$29.28138%dearer · 2.4×
Qwen3.8-27BAlibabaShared benchmark coverage$0.712$71.20480%dearer · 5.8×

Catalog price position: #41 cheapest of 269 active priced models in the LLMLearner catalog (cheaper than 85% at the 4:1 mix with 90% of input assumed cached where published; official headline rates).

Inkling 2 Mini pricing questions

How much does Inkling 2 Mini cost per million tokens?
Inkling 2 Mini official API pricing is $0.15 per million input tokens and $0.50 per million output tokens. Cached input is billed at $0.015 per million tokens. At the default 4:1 input-to-output mix with 90% of input assumed cached, that is $0.123 per million blended tokens.
What does Inkling 2 Mini cost per month, and what is included?
On the example Assistant workload (10,000 requests/month, 8,000 input and 2,000 output tokens/request, 90% input cached), Inkling 2 Mini costs about $12.28/month ($0.001228/request). This includes token charges at the official rate only; tool calls, off-peak or batch tiers, and taxes are excluded.
Is there a cheaper alternative to Inkling 2 Mini?
Among the comparable models shown on this page, Claude Haiku 5.5 is cheaper at $0.115 per million blended tokens vs $0.123 for Inkling 2 Mini. Compare benchmarks before switching, as a lower rate does not guarantee equivalent quality or service terms. Across all 269 active priced models in the LLMLearner catalog, Inkling 2 Mini ranks 41st cheapest (cheaper than 85% at the default 4:1 mix).
Does Inkling 2 Mini charge for cached input?
Yes, at a discount: $0.015 per million cached input tokens against $0.15 uncached.