supported
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / GOOGLE
Gemini 3.1 Pro Preview
verified model reference.
Google's Preview long-context multimodal reasoning and coding model for complex agents and document analysis.
1,048,576context tokens
65,536max output
2026-10-12last verified
PRIMARY-SOURCE VERIFIED
Gemini 3.1 Pro Preview at a glance.
Google documents a 1,048,576-token context window. Input modalities: text + image + video + audio + PDF. Output: text. Pricing status: Official paid API.
MODEL IDgemini-3.1-pro-preview
CONTEXT WINDOW1,048,576tokens
MAX OUTPUT65,536
KNOWLEDGE CUTOFFNot published
GLOBAL ≤128K INPUT$2.00per million tokens, <=200K or >200K prompt tier
GLOBAL ≤128K OUTPUT$12.00per million tokens, <=200K or >200K prompt tier
CAPABILITY CONTRACT
Published model behavior.
text + image + video + audio + PDF
Input modalities come from the cited official model documentation.
text
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Official paid API.
Tiered Global list rates for ≤128K input/request: $2.00 input · $12.00 output per MTok. Above 128K up to 256K and other regions have different rates.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
REGIONAL TIERED PRICING
Published list rates depend on request input length and region.
Global · Global Standard API · 1–200,000 input tokens/request
$2.00 input · $12.00 output per 1 million tokens
Global · Global Standard API · 200,001+ input tokens/request (within model limits)
$4.00 input · $18.00 output per 1 million tokens
Official list prices verified 2026-10-12; no historical effective-start date is claimed. Promotion prices are excluded. Official pricing evidence ↗
CAVEATS
What the source record does not assume.
01
Official API ID gemini-3.1-pro-preview; preview availability may change.
02
Standard tiered input/output token prices per million: $2/$12 for prompts <=200K, $4/$18 above 200K; caching and grounding are additional.
03
Fixed token calculator disabled because the rate depends on prompt length.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
Gemini 3.1 Pro Preview: what changed.
No post-baseline factual changes recorded for Gemini 3.1 Pro Preview since 2026-10-12.
VERIFIED BASELINE2026-10-12Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
Gemini 3.1 Pro Preview verified history.
Gemini 3.1 Pro Preview
Baseline verified: 1,048,576 context · 65,536 max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 77b0ad167e15…
COMPARE GEMINI 3.1 PRO PREVIEW