MiniMax M2.5/M2.7 · Chip comparison

MiniMax M2.5/M2.7 — B300 vs H200

Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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.

Throughput at 43 tok/s/user on MiniMax M2.5/M2.7: B300 hits 10382 tok/s/chip, H200 hits 2816. Per-million costs land at $0.06 and $0.12 respectively. B300 is 99% cheaper per token; B300 delivers 269% more tok/s/chip.

B300 / H200 on MiniMax M2.5/M2.7 at 72 tok/s/user: 4787 / 1855 tok/s/chip, $0.13 / $0.18 per million tokens. B300 is 39% cheaper per token; B300 delivers 158% more tok/s/chip.

Toward the upper edge of the 14–131 tok/s/user interactivity band, at 102 tok/s/user on MiniMax M2.5/M2.7: B300 runs 2425 tok/s/chip at $0.26/M tokens, H200 runs 1011 at $0.34/M. B300 is 29% cheaper per token; B300 delivers 140% 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.)

View performance-per-dollar view →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Throughput (tok/s/chip)
B300:10382.5H200:2816.4
B300:4786.6H200:1855.1
B300:2425.0H200:1011.3
Cost ($/M tok)
B300:$0.060H200:$0.120
B300:$0.131H200:$0.183
B300:$0.259H200:$0.335
tok/s/MW
B300:5464464H200:2055797
B300:2519239H200:1354090
B300:1276295H200:738156
Concurrency
B300:~215H200:~30
B300:~8H200:~12
B300:~16H200:~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