Compare

FLUX.2 [Pro] Preview vs Gemini 3.1 Pro

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
FLUX.2 [Pro] Preview
black-forest-labs/flux-2-pro-preview
Gemini 3.1 Pro
google/gemini-3.1-pro
Provider
Black Forest Labs
Google
Family
FLUX
Gemini 3
Modality
image
text
Context window
1,000,000 tok
Max output
65,536 tok
Released
2026-05-27
2026-05-22
License
Open-weight
Proprietary
Input price
$2.00 /1M
Output price
$12.00 /1M
Cache read
$0.200 /1M
Per image
$0.0000 /img
Tools
yes
Streaming
yes
Vision
yes
JSON mode
yes
Reasoning
yes
Prompt caching
yes
Batch API
Try it
Open in playground →
Open in playground →
FLUX.2 [Pro] Preview
black-forest-labs/flux-2-pro-preview
Full spec →

FLUX.2 [pro] Preview is Black Forest Labs' recommended default for production image generation and editing — tracks the latest [pro] weights with strong multi-reference support.

Strengths
  • Text-to-image generation
  • Creative control
Use cases
Marketing assetsProduct mockupsConcept art
Gemini 3.1 Pro
google/gemini-3.1-pro
Full spec →

Google's most intelligent Gemini model with improved reasoning, a medium thinking level, and a 1M token context window.

Strengths
  • 2M-token context
  • Native video + audio input
  • Cheapest long-context reasoning
Use cases
Video understandingVery long-document RAGCodebase-scale reasoning

Benchmarks

FLUX.2 [Pro] Preview
Gemini 3.1 Pro
Long-Context
94.2
MMLU
89.6

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Gemini 3.1 Pro vs Claude Opus 4.7
google/gemini-3.1-pro · anthropic/claude-opus-4.7
GPT-5.4 vs Gemini 3.1 Pro
openai/gpt-5.4 · google/gemini-3.1-pro
Claude Sonnet 4.6 vs Gemini 3.1 Pro
anthropic/claude-sonnet-4.6 · google/gemini-3.1-pro
Gemini 3.1 Pro vs Kimi-K2.6
google/gemini-3.1-pro · moonshot/kimi-k2.6
Claude Opus 4.8 vs Gemini 3.1 Pro
anthropic/claude-opus-4.8 · google/gemini-3.1-pro
Claude Opus 4.8 vs FLUX.2 [Pro] Preview
anthropic/claude-opus-4.8 · black-forest-labs/flux-2-pro-preview
Claude Sonnet 4.6 vs FLUX.2 [Pro] Preview
anthropic/claude-sonnet-4.6 · black-forest-labs/flux-2-pro-preview
Grok 4.20 Multi-Agent vs Gemini 3.1 Pro
xai/grok-4.20-multi-agent-0309 · google/gemini-3.1-pro
Grok 4.20 Multi-Agent vs FLUX.2 [Pro] Preview
xai/grok-4.20-multi-agent-0309 · black-forest-labs/flux-2-pro-preview
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# FLUX.2 [Pro] Preview
client.chat.completions.create(
    model="black-forest-labs/flux-2-pro-preview",
    messages=[{"role":"user","content":"hello"}],
)

# Gemini 3.1 Pro
client.chat.completions.create(
    model="google/gemini-3.1-pro",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →