BroadRouter

GPT-5.6 Luna vs Inkling 2 Small API pricing

Updated

GPT-5.6 Luna: USD 0.20 input, USD 1.20 output per 1M tokens (OpenAI and 3 others). Inkling 2 Small: USD 0.285 input, USD 0.95 output per 1M tokens (DeepInfra, promotional). At 3 input tokens per output token, Inkling 2 Small costs 0.3% more than GPT-5.6 Luna (USD 0.4512 vs USD 0.45 per 1M).

Picked by the same-tier rule: both are in the second quarter of the indexed models by price (USD 0.1556 to USD 0.4512 per 1M tokens at 3:1) and in the same size class, small (a tier word such as Flash, Mini or Haiku, or 40B parameters or fewer). Inkling 2 Small is the 1st-closest-priced model from another maker to GPT-5.6 Luna in that bucket. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-16), with no claim about quality, speed or accuracy.

How do GPT-5.6 Luna and Inkling 2 Small differ on price?

GPT-5.6 Luna and Inkling 2 Small prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

GPT-5.6 Luna and Inkling 2 Small API prices compared
PriceGPT-5.6 LunaInkling 2 Small
Model pageGPT-5.6 Luna
OpenAI · 6 providers
Inkling 2 Small
Thinking Machines · 4 providers
Cheapest standard price, blended 3:1USD 0.45 lower
USD 0.20 in / USD 1.20 out at OpenAI and 3 others
OpenAI page checked 2026-11-14
USD 0.4512 promo
USD 0.285 in / USD 0.95 out at DeepInfra
DeepInfra page checked 2026-11-14
Cheapest inputUSD 0.20 lower
OpenAI source
USD 0.285 promo
DeepInfra source
Cheapest cached inputUSD 0.02 lower
OpenAI source
USD 0.0285 promo
DeepInfra source
Cheapest outputUSD 1.20
OpenAI source
USD 0.95 lower promo
DeepInfra source
Cheapest non-promotional priceThe cheapest price is not promotional.USD 0.30 / USD 1
Cloudflare Workers AI, USD 0.475 blended source
Maker's own APIUSD 0.20 / USD 1.20
OpenAI source
Thinking Machines publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.20 / USD 1.20
input / output, 6 prices
USD 0.30 / USD 1
input / output, 4 prices
Context window1,050,000 tokens, largest stated1,048,576 tokens, largest stated
Providers with a standard price64

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do GPT-5.6 Luna and Inkling 2 Small cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on GPT-5.6 Luna and Inkling 2 Small
WorkloadGPT-5.6 LunaInkling 2 SmallDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 29.88
OpenAI
USD 28.90
DeepInfra
USD 0.98
Inkling 2 Small lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 53.04
OpenAI
USD 64.18
DeepInfra
USD 11.14
GPT-5.6 Luna lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 192.60
OpenAI
USD 206.05
DeepInfra
USD 13.45
GPT-5.6 Luna lower

The cheaper model depends on the workload: Inkling 2 Small for Support chatbot, GPT-5.6 Luna for RAG over documents, GPT-5.6 Luna for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on RAG over documents: the dearer model costs 21% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 2.9 input tokens per output token, Inkling 2 Small is cheaper; above 2.9, GPT-5.6 Luna is cheaper. At the site's 3:1 blend, GPT-5.6 Luna is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of GPT-5.6 Luna and Inkling 2 Small at different input:output mixes
Input : output tokensGPT-5.6 LunaInkling 2 Small
1 : 3 (long answers)USD 0.95
OpenAI
USD 0.7837 lower
DeepInfra
1 : 1USD 0.70
OpenAI
USD 0.6175 lower
DeepInfra
3 : 1 (the site’s blend)USD 0.45 lower
OpenAI
USD 0.4512
DeepInfra
10 : 1 (retrieval, long prompts)USD 0.2909 lower
OpenAI
USD 0.3455
DeepInfra
30 : 1 (agents, big contexts)USD 0.2323 lower
OpenAI
USD 0.3065
DeepInfra

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do GPT-5.6 Luna and Inkling 2 Small cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and GPT-5.6 Luna and Inkling 2 Small are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: GPT-6 Luna vs GPT-5.6 Luna · Qwen3.8 27B vs GPT-5.6 Luna · GPT-5.6 Terra vs GPT-5.6 Luna · GPT-5.6 Luna vs GPT-5.5 · Qwen3.8 27B vs Inkling 2 Small · every GPT-5.6 Luna comparison · every Inkling 2 Small comparison · all 662 price comparisons

Questions

Is GPT-5.6 Luna cheaper than Inkling 2 Small?

Yes. On a blend of 3 input tokens to 1 output token, GPT-5.6 Luna costs USD 0.45 per 1M tokens and Inkling 2 Small USD 0.4512, at each model's cheapest standard price. For input alone, GPT-5.6 Luna is cheaper (USD 0.20 against USD 0.285 per 1M); for output alone, Inkling 2 Small is (USD 0.95 against USD 1.20). This compares price only, not quality.

What do GPT-5.6 Luna and Inkling 2 Small cost per 1M tokens?

GPT-5.6 Luna: from USD 0.20 input and USD 1.20 output at OpenAI and 3 others; OpenAI's own API charges USD 0.20 / USD 1.20; median of 6 standard prices USD 0.20 / USD 1.20. Inkling 2 Small: from USD 0.285 input and USD 0.95 output at DeepInfra (promotional); median of 4 standard prices USD 0.30 / USD 1. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both GPT-5.6 Luna and Inkling 2 Small?

None of the providers we track sells both at a standard price. GPT-5.6 Luna is cheapest at OpenAI and 3 others and Inkling 2 Small at DeepInfra, so running both means two accounts.

Which is cheaper for a coding agent or a chatbot, GPT-5.6 Luna or Inkling 2 Small?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 192.60 a month on GPT-5.6 Luna (OpenAI) against USD 206.05 on Inkling 2 Small (DeepInfra), a difference of USD 13.45. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 29.88 a month on GPT-5.6 Luna (OpenAI) against USD 28.90 on Inkling 2 Small (DeepInfra), a difference of USD 0.98. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of GPT-5.6 Luna and Inkling 2 Small change?

The cheaper model changes with the mix: below 2.9 input tokens per output token, Inkling 2 Small is cheaper; above 2.9, GPT-5.6 Luna is cheaper. At the site's 3:1 blend, GPT-5.6 Luna is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Do GPT-5.6 Luna and Inkling 2 Small have cached input pricing?

GPT-5.6 Luna from USD 0.02 per 1M cached input tokens (OpenAI; 6 of 6 standard prices list a discount). Inkling 2 Small from USD 0.0285 per 1M cached input tokens (DeepInfra; 4 of 4 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, GPT-5.6 Luna or Inkling 2 Small?

GPT-5.6 Luna: up to 1,050,000 tokens, against 1,048,576 for Inkling 2 Small, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity