Gemma-4-31B-it-Pearl vs MiniMax M3
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Together
|
by Together
2 providers:
Fireworks $0.300/$1.20
Together $0.300/$1.20
|
|---|---|---|
| Overview | ||
| Status | Current budget Open weights | Current budget Open weights |
| Released | Jan 1, 2026 | Jun 1, 2026 |
| Pricing per million tokens | ||
| Input | $0.280/Mtok | $0.300/Mtok |
| Output | $0.860/Mtok | $1.20/Mtok |
| Blended avg | $0.425/Mtok | $0.525/Mtok |
| Cached input | — | $0.060/Mtok |
| Specifications | ||
| Context window | 128K tokens | 1M tokens |
| Parameters | 31B | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks sources: LMSYS Chatbot Arena (UC Berkeley) / Vellum LLM Leaderboard (Jun 2026), MiniMax model card | ||
| Avg benchmark score | — | 63.1 |
| Perf / dollar | — | 120.2 |
| GPQA Diamond | — | 93 |
| SWE-Bench Verified | — | 45 |
| Terminal-Bench 2.1 | — | 66 |
| MCP Atlas | — | 74.2 |
| BrowseComp | — | 83.5 |
| OSWorld-Verified | — | 70.1 |
| Humanity's Last Exam | — | 22 |
| ARC-AGI 2 | — | 20 |
| AIME 2025 | — | 55 |
| MMMLU | — | 76 |
| BFCL | — | 65 |
| HumanEval | — | 80.5 |
| MATH 500 | — | 70 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | — | 45.4 |
| AA Agentic Index | — | 36.1 |
| AA-Omniscience Index (−100–100) | — | 1.4 |
| GDPval-AA v2 | — | 1389.8 ELO |
| LMSYS Chatbot Arena | 1450.9 ELO | — |
| Providers | ||
| Available from |
Together — $0.280/$0.860/Mtok
|
Fireworks — $0.300/$1.20/Mtok
Together — $0.300/$1.20/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Gemma-4-31B-it-Pearl | MiniMax M3 | Savings |
|---|---|---|---|
| 1M tokens | $0.43 | $0.52 | $0.1 (19%) |
| 10M tokens | $4.25 | $5.25 | $1 (19%) |
| 100M tokens | $42.5 | $52.5 | $10 (19%) |
| 1000M tokens | $425 | $525 | $100 (19%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.425/Mtok blended vs $0.525 — 19% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.060/Mtok — 80% off its list input price, a discount Gemma-4-31B-it-Pearl doesn't offer
- you need the longer context: 1M tokens vs 128K (7.8×)
- provider flexibility: available from 2 providers, so you can price-shop hosts or fail over
The cheaper option here — Gemma-4-31B-it-Pearl costs $0.425/Mtok blended on Together.
Summary
Gemma-4-31B-it-Pearl by Together costs $0.280/Mtok input and $0.860/Mtok output, with a 128K-token context window. It supports text input.
MiniMax M3 by Together costs $0.300/Mtok input and $1.20/Mtok output, with a 1M-token context window. It supports text, image input and is available from 2 providers.
On a blended cost basis, Gemma-4-31B-it-Pearl is 19% cheaper than MiniMax M3.
The two aren't directly comparable on average benchmark score: MiniMax M3 has published per-benchmark results, while Gemma-4-31B-it-Pearl does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.