Скорость вывода
23162.3 tok/s
24159.9 tok/s
25MiniMax M2.5157.1 tok/s
27155.3 tok/s
MiniMax M2.5 is available through 150 API providers on LMSpeed. Compare API pricing from $0.0007 to $535.71 per million input tokens across providers. Free API access is offered by 7 providers. Context window: 204,800. In speed benchmarks, the fastest provider reaches 105 tok/s.
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
Также известна как
Compare MiniMax M2.5 API pricing across 143 providers. Input prices range from $0.0007 to $535.71 per million input. MMKG offers the lowest rate at $0.0007/M. 7 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
星见雅 API100% | 李/minimaxai/minimax-m2.5 | — | Бесплатно | Бесплатно | 104.5 t/s | 0.91 s-83% |
| 英伟达/minimaxai/minimax-m2.5 | — | Бесплатно | Бесплатно | — | — | |
Spaceship92.2% | MiniMax-M2.5 | — | $75.00 | $75.00 | 68.7 t/s | 12.05 s |
素墨API100% | minimax-m2.5 | — | $0.010-97% | $0.010-99% | 18.6 t/s | 19.89 s |
| minimax-m2.5-free | — | $0.010-97% | $0.010-99% | — | — | |
| minimaxai/minimax-m2.5 | — | $0.010-97% | $0.010-99% | — | — | |
V-API100% | MiniMax-M2.5 | — | $0.020-93% | $0.020-98% | — | — |
Thorbase100% | minimax/minimax-m2.5 | — | $0.142-52% | $1.09-9% | — | — |
老张API100% | MiniMax-M2.5 | — | $0.288-4% | $1.15-4% | — | — |
柏拉图AI100% | MiniMax-M2.5 | — | $0.288-4% | $1.15-4% | — | — |
PackyAPI100% | minimax-m2.5 | — | $0.300 | $1.20 | — | — |
MapleLeaf API100% | minimax-m2.5 | — | $0.290-3% | $1.15-4% | — | — |
天絮 API100% | MiniMaxAI/MiniMax-M2.5 | — | $2.14 | $8.57 | — | — |
| Pro/MiniMaxAI/MiniMax-M2.5 | — | $2.14 | $8.71 | — | — | |
| minimax/minimax-m2.5:free | — | $535.71 | $535.71 | — | — | |
6345ywz API99.8% | MiniMaxAI/MiniMax-M2.5 | — | $0.041-86% | $0.164-86% | — | — |
| Pro/MiniMaxAI/MiniMax-M2.5 | — | $0.041-86% | $0.167-86% | — | — | |
| minimaxai/minimax-m2.5 | — | $0.137-54% | $0.137-89% | — | — | |
VSLLM99.7% | MiniMax-M2.5 | — | $7.30 | $18.25 | — | — |
ChooseC API99.7% | MiniMax-M2.5 | — | $2.10 | $8.40 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
星见雅 API 李/minimaxai/minimax-m2.5 | 104.54 tok/s | 0.91s | 5 |
minimax-m2.5 | 103.52 tok/s | 8.67s | 5 |
MiniMax-M2.5 | 85.29 tok/s | 17.74s | 5 |
minimaxai/minimax-m2.5 | 78.81 tok/s | 3.19s | 45 |
Pro/MiniMaxAI/MiniMax-M2.5 | 71.37 tok/s | 9.63s | 25 |
MiniMax-M2.5 | 68.71 tok/s | 12.05s | 5 |
MiniMax-M2.5 | 68.56 tok/s | 8.37s | 5 |
MiniMax-M2.5 | 67.81 tok/s | 7.80s | 20 |
minimax/minimax-m2.5:free | 67.24 tok/s | 13.81s | 3 |
MiniMax-M2.5-VIP | 66.21 tok/s | 6.00s | 5 |
minimax-m2.5 | 65.47 tok/s | 6.56s | 5 |
minimax-m2.5-free | 64.12 tok/s | 7.72s | 5 |
minimaxai/minimax-m2.5 | 60.04 tok/s | 11.13s | 15 |
MiniMaxAI/MiniMax-M2.5 | 54.74 tok/s | 7.54s | 5 |
MiniMax/MiniMax-M2.5 | 52.75 tok/s | 7.49s | 5 |
MiniMax-M2.5 | 52.60 tok/s | 5.95s | 30 |
MiniMax-M2.5 | 49.91 tok/s | 3.73s | 5 |
ollama/minimax-m2.5 | 49.60 tok/s | 11.48s | 5 |
kilo/minimax-m2.5 | 49.09 tok/s | 9.38s | 5 |
MiniMax-M2.5 | 42.92 tok/s | 2.19s | 5 |
Показано 1–20 из 29 провайдеров
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
