Gemini 3.5 Flash vs MiniMax M3
API pricing, context window and capabilities for Gemini 3.5 Flash and MiniMax M3, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersGemini 3.5 Flash wins on coding and on intelligence. MiniMax M3 wins on price.
Price
MiniMax M3
Coding
Gemini 3.5 Flash
Intelligence
Gemini 3.5 Flash
Context window
Tied
Key takeaways
who wins on what, from the published numbersGemini 3.5 Flash wins
- More serving providers (3 vs 2)
- Supports audio
- Has web search
MiniMax M3 wins
- Cheaper input ($1.50 vs $0.30 /1M)
- Cheaper output ($9.00 vs $1.20 /1M)
- Higher max output (66K vs 512K)
Cheaper overall
MiniMax M3
$0.30 + $1.20 /1M
Larger context
Tied
More providers
Gemini 3.5 Flash
3 providers
Pricing & specs
cheapest serving route · per 1M tokens| Gemini 3.5 Flash | MiniMax M3 | |
|---|---|---|
| Input $/1M | $1.50 | $0.30 best |
| Output $/1M | $9.00 | $1.20 best |
| Context window | 1M | 1M |
| Max output | 66K | 512K best |
| Serving providers | 3 best | 2 |
| Released | 2026-05-22 | 2026-06-01 |
Benchmarks
Artificial Analysis indices, side by side| Gemini 3.5 Flash | MiniMax M3 | |
|---|---|---|
| Intelligence | 50.2 best | 44.4 |
| Coding | 70.1 best | 58.6 |
| GPQA Diamond | 92% | 93% best |
| Output speed | 188 t/s best | 85 t/s |
| Latency (TTFT) | 18.79s | 5.28s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Gemini 3.5 Flash
via Vertex AI
$17
MiniMax M3
via Fireworks AI
$2.70
Capabilities
feature support, side by side| Feature | Gemini 3.5 Flash | MiniMax M3 |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | ✓ | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | ✓ | — |
Related comparisons
Frequently asked questions
Which is cheaper, Gemini 3.5 Flash or MiniMax M3?
MiniMax M3 is cheaper for input ($1.50 vs $0.30 per 1M tokens). MiniMax M3 is cheaper for output ($9.00 vs $1.20 per 1M tokens).
What is the context window difference between Gemini 3.5 Flash and MiniMax M3?
Both Gemini 3.5 Flash and MiniMax M3 have about a 1M-token context window.
How do Gemini 3.5 Flash and MiniMax M3 compare on benchmarks?
On the tracked Artificial Analysis indices, Gemini 3.5 Flash leads on coding, and Gemini 3.5 Flash leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI