MiniMax M2.5/M2.7 — B200 vs MI325X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on MiniMax M2.5/M2.7. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
B200 posts 10881 tok/s/chip for $0.04 per million tokens at 35 tok/s/user on MiniMax M2.5/M2.7; MI325X posts 2647 tok/s/chip for $0.12. B200 is 161% cheaper per token; B200 delivers 311% more tok/s/chip.
Throughput at 56 tok/s/user on MiniMax M2.5/M2.7: B200 hits 6360 tok/s/chip, MI325X hits 1814. Per-million costs land at $0.08 and $0.17 respectively. B200 is 123% cheaper per token; B200 delivers 251% more tok/s/chip.
B200 / MI325X on MiniMax M2.5/M2.7 at 78 tok/s/user: 3277 / 1009 tok/s/chip, $0.15 / $0.30 per million tokens. B200 is 107% cheaper per token; B200 delivers 225% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:10881.4MI325X:2647.3 | B200:6360.2MI325X:1814.3 | B200:3277.5MI325X:1009.1 |
| Cost ($/M tok) | B200:$0.044MI325X:$0.115 | B200:$0.076MI325X:$0.168 | B200:$0.147MI325X:$0.303 |
| tok/s/MW | B200:6363374MI325X:1566421 | B200:3719408MI325X:1073566 | B200:1916658MI325X:597118 |
| Concurrency | B200:~823MI325X:~18 | B200:~90MI325X:~8 | B200:~32MI325X:~5 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
MiniMax M2.5/2.7 230B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip