Verified November 2026

Home › Compare › Gemini 4 Argon vs Gemini 3.1 Pro (Preview)

Gemini 4 Argon vs Gemini 3.1 Pro (Preview)

A straight cost comparison of Gemini 4 Argon (Google Gemini) and Gemini 3.1 Pro (Preview) (Google Gemini), per 1,000,000 tokens, verified November 2026.

$2Gemini 4 Argon input / 1M
$2Gemini 3.1 Pro (Preview) input / 1M
10%Blended price gap
Gemini 4 ArgonCheaper blended

Rate-by-rate comparison

USD per 1M tokens · November 2026
MetricGemini 4 ArgonGemini 3.1 Pro (Preview)Winner
Input / 1M$2$2Tie
Cached input / 1M$0.10$0.20Gemini 4 Argon
Cache write / 1M——Tie
Output / 1M$10$12Gemini 4 Argon
Context window1,000,0001,000,000Tie
Batch APIYesYesTie
Long-context tierNone> 200,000—

For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.

Blended cost: 1M input + 250K output

ModelBlended costDifference
Gemini 4 Argon$4.50Cheaper
Gemini 3.1 Pro (Preview)$5+$0.50

Ten workloads, two bills

The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.

WorkloadGemini 4 ArgonGemini 3.1 Pro (Preview)Winner
Classification
100K reqs · 500 in / 10 out
$110$112Gemini 4 Argon
Data extraction
10K reqs · 2K in / 200 out
$60$64Gemini 4 Argon
Support chat
1K reqs · 4K in / 600 out
$14$15.20Gemini 4 Argon
Code review
2K reqs · 8K in / 1.5K out
$62$68Gemini 4 Argon
Summarisation
1K reqs · 20K in / 1K out
$50$52Gemini 4 Argon
Agent loop
5K reqs · 12K in / 2K out
$220$240Gemini 4 Argon
Translation
500 reqs · 15K in / 15K out
$90$105Gemini 4 Argon
Long-document QA
200 reqs · 120K in / 800 out
$49.60$49.92Gemini 4 Argon
Cached RAG
1K reqs · 50K in (45K cached) / 1K out
$24.59$31.08Gemini 4 Argon
Nightly batch
10K reqs · 10K in / 2K out
$200$220Gemini 4 Argon

Gemini 4 Argon wins 10 of 10, Gemini 3.1 Pro (Preview) wins 0 of 10. The winner is set by the token mix, not by the headline rate.

Where the two bills cross over

The two are priced identically on one side of the token mix ($2 input, $10 output), so the crossover is decided entirely by the other side — the cheaper model on that side wins at every ratio.

Cost at four scales

The same support-chat workload (4K input, 600 output per request) at four monthly volumes.

Requests / monthGemini 4 ArgonGemini 3.1 Pro (Preview)Difference
100$1.40$1.52Gemini 4 Argon cheaper by $0.12
1,000$14$15.20Gemini 4 Argon cheaper by $1.20
10,000$140$152Gemini 4 Argon cheaper by $12
100,000$1,400$1,520Gemini 4 Argon cheaper by $120

What caching does to each bill

Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.

Cached share of the promptGemini 4 ArgonGemini 3.1 Pro (Preview)Winner
0%$14$15.20Gemini 4 Argon
50%$10.20$11.60Gemini 4 Argon
80%$7.93$9.45Gemini 4 Argon
95%$6.79$8.37Gemini 4 Argon

Both models publish a cached-read rate, so the discount is comparable: Gemini 4 Argon reads cache at $0.10 per million, Gemini 3.1 Pro (Preview) at $0.20.

Which one should you pick?

Gemini 4 Argon wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch, while Gemini 3.1 Pro (Preview) wins on none of the ten workloads above.

Beyond price, the two differ on output rate ($10 vs $12); cached-input rate ($0.10 vs $0.20); long-context tier (none vs yes, above 200,000).

Batch mode is available on Gemini 4 Argon and Gemini 3.1 Pro (Preview), which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.

FAQ

Is Gemini 4 Argon cheaper than Gemini 3.1 Pro (Preview)?

On a blended 1M-input-plus-250K-output workload, Gemini 4 Argon is cheaper by 10% ($4.50 vs $5). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.

Which handles longer prompts, Gemini 4 Argon or Gemini 3.1 Pro (Preview)?

Both models share the same 1,000,000-token context window. Watch the long-context threshold on Gemini 3.1 Pro (Preview): rates rise once input passes it.

Do both models support prompt caching?

Gemini 4 Argon bills cached reads at $0.10 per 1M; Gemini 3.1 Pro (Preview) at $0.20.

Related comparisons

Run your own token volumes