BroadRouter

DeepSeek-V3.2-Exp vs Ripple-65B Preview API pricing

Updated

DeepSeek-V3.2-Exp: USD 0.27 input, USD 0.41 output per 1M tokens (GMI Cloud and 1 other). Ripple-65B Preview: USD 0.20 input, USD 0.60 output per 1M tokens (GMI Cloud and 1 other). At 3 input tokens per output token, DeepSeek-V3.2-Exp costs 1.7% more than Ripple-65B Preview (USD 0.305 vs USD 0.30 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, mid-size (no tier word, 40B to 200B parameters or no size in the name). Ripple-65B Preview is the 1st-closest-priced model from another maker to DeepSeek-V3.2-Exp in that bucket. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do DeepSeek-V3.2-Exp and Ripple-65B Preview differ on price?

DeepSeek-V3.2-Exp and Ripple-65B Preview 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.

DeepSeek-V3.2-Exp and Ripple-65B Preview API prices compared
PriceDeepSeek-V3.2-ExpRipple-65B Preview
Model pageDeepSeek-V3.2-Exp
DeepSeek · 2 providers
Ripple-65B Preview
Ricursive AI · 2 providers
Cheapest standard price, blended 3:1USD 0.305
USD 0.27 in / USD 0.41 out at GMI Cloud and 1 other
GMI Cloud page checked 2026-11-15
USD 0.30 lower
USD 0.20 in / USD 0.60 out at GMI Cloud and 1 other
GMI Cloud page checked 2026-11-15
Cheapest inputUSD 0.27
GMI Cloud source
USD 0.20 lower
GMI Cloud source
Cheapest cached inputNo standard price lists a cache price; cached tokens bill at the input price.USD 0.02
Together AI source
Cheapest outputUSD 0.41 lower
GMI Cloud source
USD 0.60
GMI Cloud source
Maker's own APIDeepSeek publishes no paid standard price on its own API that we found.Ricursive AI publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.27 / USD 0.41
input / output, 2 prices
USD 0.20 / USD 0.60
input / output, 2 prices
Context window163,840 tokens, largest stated1,000,000 tokens, largest stated
Providers with a standard price22

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

What do DeepSeek-V3.2-Exp and Ripple-65B Preview 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 DeepSeek-V3.2-Exp and Ripple-65B Preview
WorkloadDeepSeek-V3.2-ExpRipple-65B PreviewDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 31.68
GMI Cloud
USD 19.08
Together AI
USD 12.60
Ripple-65B Preview lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 70.95
GMI Cloud
USD 44.04
Together AI
USD 26.91
Ripple-65B Preview lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 522.90
GMI Cloud
USD 138.60
Together AI
USD 384.30
Ripple-65B Preview lower

Ripple-65B Preview is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 3.8× as much as the cheaper one.

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

The cheaper model changes with the mix: below 2.7 input tokens per output token, DeepSeek-V3.2-Exp is cheaper; above 2.7, Ripple-65B Preview is cheaper. At the site's 3:1 blend, Ripple-65B Preview 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 DeepSeek-V3.2-Exp and Ripple-65B Preview at different input:output mixes
Input : output tokensDeepSeek-V3.2-ExpRipple-65B Preview
1 : 3 (long answers)USD 0.375 lower
GMI Cloud
USD 0.50
GMI Cloud
1 : 1USD 0.34 lower
GMI Cloud
USD 0.40
GMI Cloud
3 : 1 (the site’s blend)USD 0.305
GMI Cloud
USD 0.30 lower
GMI Cloud
10 : 1 (retrieval, long prompts)USD 0.2827
GMI Cloud
USD 0.2364 lower
GMI Cloud
30 : 1 (agents, big contexts)USD 0.2745
GMI Cloud
USD 0.2129 lower
GMI Cloud

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

What do DeepSeek-V3.2-Exp and Ripple-65B Preview cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Ripple-65B Preview is not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: DeepSeek-V3.2-Exp vs DeepSeek V3.2 · every DeepSeek-V3.2-Exp comparison · every Ripple-65B Preview comparison · all 662 price comparisons

Questions

Is DeepSeek-V3.2-Exp cheaper than Ripple-65B Preview?

No. On a blend of 3 input tokens to 1 output token, Ripple-65B Preview costs USD 0.30 per 1M tokens and DeepSeek-V3.2-Exp USD 0.305, at each model's cheapest standard price. For input alone, Ripple-65B Preview is cheaper (USD 0.20 against USD 0.27 per 1M); for output alone, DeepSeek-V3.2-Exp is (USD 0.41 against USD 0.60). This compares price only, not quality.

What do DeepSeek-V3.2-Exp and Ripple-65B Preview cost per 1M tokens?

DeepSeek-V3.2-Exp: from USD 0.27 input and USD 0.41 output at GMI Cloud and 1 other; median of 2 standard prices USD 0.27 / USD 0.41. Ripple-65B Preview: from USD 0.20 input and USD 0.60 output at GMI Cloud and 1 other; median of 2 standard prices USD 0.20 / USD 0.60. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both DeepSeek-V3.2-Exp and Ripple-65B Preview?

1 provider has a standard price for both: GMI Cloud (USD 0.305 and USD 0.30 at 3:1). Buying each model from its own cheapest provider costs USD 0.305 and USD 0.30.

Which is cheaper for a coding agent or a chatbot, DeepSeek-V3.2-Exp or Ripple-65B Preview?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 522.90 a month on DeepSeek-V3.2-Exp (GMI Cloud) against USD 138.60 on Ripple-65B Preview (Together AI), a difference of USD 384.30. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 31.68 a month on DeepSeek-V3.2-Exp (GMI Cloud) against USD 19.08 on Ripple-65B Preview (Together AI), a difference of USD 12.60. 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 DeepSeek-V3.2-Exp and Ripple-65B Preview change?

The cheaper model changes with the mix: below 2.7 input tokens per output token, DeepSeek-V3.2-Exp is cheaper; above 2.7, Ripple-65B Preview is cheaper. At the site's 3:1 blend, Ripple-65B Preview 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 DeepSeek-V3.2-Exp and Ripple-65B Preview have cached input pricing?

DeepSeek-V3.2-Exp: no standard price lists a cached-input discount. Ripple-65B Preview from USD 0.02 per 1M cached input tokens (Together AI; 2 of 2 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, DeepSeek-V3.2-Exp or Ripple-65B Preview?

Ripple-65B Preview: up to 1,000,000 tokens, against 163,840 for DeepSeek-V3.2-Exp, 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