MiniMax M2.5/M2.7 · Chip comparison

MiniMax M2.5/M2.7 — B200 vs B300

Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (NVIDIA Blackwell) 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 60 tok/s/user on MiniMax M2.5/M2.7: B200 hits 13123 tok/s/chip, B300 hits 13222. Per-million costs land at $0.04 and $0.05 respectively. B200 is 30% cheaper per token; throughput per chip is essentially tied.

B200 / B300 on MiniMax M2.5/M2.7 at 101 tok/s/user: 6649 / 6697 tok/s/chip, $0.07 / $0.09 per million tokens. B200 is 30% cheaper per token; throughput per chip is essentially tied.

Toward the upper edge of the 19–183 tok/s/user interactivity band, at 143 tok/s/user on MiniMax M2.5/M2.7: B200 runs 3074 tok/s/chip at $0.16/M tokens, B300 runs 2915 at $0.22/M. B200 is 38% cheaper per token; B200 delivers 5% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 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)
B200:13123.3B300:13221.8
B200:6649.1B300:6697.5
B200:3073.5B300:2915.1
Cost ($/M tok)
B200:$0.037B300:$0.047
B200:$0.072B300:$0.094
B200:$0.156B300:$0.215
tok/s/MW
B200:7674471B300:6958818
B200:3888345B300:3524994
B200:1797369B300:1534289
Concurrency
B200:~787B300:~295
B200:~9B300:~9
B200:~11B300:~11

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