← All models

gemini-3-pro-preview

gmi · chat model

gemini-3-pro-preview is listed here as a chat model from gmi. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.

Input
$2.0000 / 1M tokens
Output
$12.0000 / 1M tokens
Cached input
N/A
Context
65.5K

Quick read

Best for

Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.

Things to verify

Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.

Pricing

Item Price
Input
$2.0000 / 1M tokens
Output
$12.0000 / 1M tokens
Embedding
$2.0000 / 1M tokens

Token limits

Context window
65.5K
Max input tokens
1.0M
Max output tokens
65.5K
Max tokens
65.5K

Capabilities

Capability Supported
Vision
Function calling
Parallel function calling
Tool choice
Prompt caching
Reasoning
Response schema
System messages
Audio input
Audio output
Web search
PDF input
Video input

Benchmarks

Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer

Benchmark Score Metric Scope Checked Source
Humanity's Last Exam 37.5% (no tools) accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
ARC-AGI-2 31.1% accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
GPQA Diamond 91.9% accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
Terminal-Bench 2.0 56.9% accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
SWE-bench Verified 76.2% (single attempt) accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
LiveCodeBench Pro 2439 Elo Elo Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
MMMU-Pro 81.0% accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
MRCR v2 77.0% (128k average) accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
MRCR v2 26.3% (1M pointwise) accuracy Base model: Gemini 3 Pro (Gemini 3 Pro Thinking (High)) 2026-05-31 Link
SWE-bench Verified 69.60% % resolved Base model: Gemini 3 Pro (Gemini 3 Pro) 2026-05-31 Link
LMArena Text Arena (English) 1489±5 Arena Elo Base model: Gemini 3 Pro (gemini-3-pro) 2026-05-31 Link
MMLU-Pro 89.8% accuracy Base model: Gemini 3 Pro Preview (Gemini 3 Pro Preview (high)) 2026-05-31 Link
MMLU-Pro 89.5% accuracy Base model: Gemini 3 Pro Preview (Gemini 3 Pro Preview (low)) 2026-05-31 Link

Sources

Source links
Pricing data LiteLLM model cost map
Synced at 2026-05-28

Similar models

This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.

Comparing from
Model Cost Input shape Features Context Why it is close
gemini-3-pro-preview
gmi
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
Output: unknown
VisionFunction calling
65.5K
Current model
Reference row

Overall blends cost, modality overlap, capabilities, and context.

Model Cost Input shape Features Context Why it is close
claude-sonnet-4.5
gmi
In $3.0000 / 1M tokens
Out $15.0000 / 1M tokens
Output: unknown
VisionFunction calling
32.0K
Same provider
Overall 47%
claude-sonnet-4
gmi
In $3.0000 / 1M tokens
Out $15.0000 / 1M tokens
Output: unknown
VisionFunction calling
32.0K
Same provider
Overall 47%
google.gemini-2.5-pro
oci
In $1.2500 / 1M tokens
Out $10.0000 / 1M tokens
Output: unknown
VisionFunction calling
65.5K
Partial I/O overlap
Overall 46%
gpt-4o
gmi
In $2.5000 / 1M tokens
Out $10.0000 / 1M tokens
Output: unknown
VisionFunction calling
16.4K
Same provider
Overall 45%
gemini-3-flash-preview
gmi
In $0.5000 / 1M tokens
Out $3.0000 / 1M tokens
Output: unknown
VisionFunction calling
65.5K
Same provider
Overall 45%
gemini-2.5-pro
vercel_ai_gateway
In $2.5000 / 1M tokens
Out $10.0000 / 1M tokens
audioimage
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 44%
claude-opus-4.5
gmi
In $5.0000 / 1M tokens
Out $25.0000 / 1M tokens
Output: unknown
VisionFunction calling
32.0K
Same provider
Overall 41%
gemini-3-pro-preview
vertex_ai-language-models
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
audioimage
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 40%
gemini-3-pro-preview
Vertex AI
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
pdf
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 40%
gemini-3.1-pro-preview
vertex_ai-language-models
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
audioimage
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 39%
gemini-3.1-pro-preview-customtools
vertex_ai-language-models
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
audioimage
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 39%
gemini-3.1-pro-preview
Vertex AI
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
pdfurl
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 39%
gemini-3.1-pro-preview-customtools
Vertex AI
In $2.0000 / 1M tokens
Out $12.0000 / 1M tokens
pdfurl
Output: text
VisionFunction calling
65.5K
Partial I/O overlap
Overall 39%
gpt-5.2
gmi
In $1.7500 / 1M tokens
Out $14.0000 / 1M tokens
Output: unknown
Function calling
32.0K
Same provider
Overall 37%
meta.llama3-2-90b-instruct-v1:0
Bedrock
In $2.0000 / 1M tokens
Out $2.0000 / 1M tokens
imagetext
Output: text
VisionFunction calling
4.1K
Partial I/O overlap
Overall 37%
meta.llama-3.2-90b-vision-instruct
oci
In $2.0000 / 1M tokens
Out $2.0000 / 1M tokens
Output: unknown
VisionFunction calling
4.0K
Partial I/O overlap
Overall 37%
meta.llama-3.2-11b-vision-instruct
oci
In $2.0000 / 1M tokens
Out $2.0000 / 1M tokens
Output: unknown
VisionFunction calling
4.0K
Partial I/O overlap
Overall 37%
claude-opus-4
gmi
In $15.0000 / 1M tokens
Out $75.0000 / 1M tokens
Output: unknown
VisionFunction calling
32.0K
Same provider
Overall 35%
gpt-4o-mini
gmi
In $0.1500 / 1M tokens
Out $0.6000 / 1M tokens
Output: unknown
VisionFunction calling
16.4K
Same provider
Overall 30%