Inference Cost per Million Tokens

Hyperscaler cost ↓ Lower is better Source: InferenceX & SemiAnalysis Market July 2026 AI Cloud TCO Model

  • DeepSeek V4 Pro 1.6T

    8K/1K

    B200
    TRTLLM · FP4
    MI355X
    cannot reach @200
    B300
    $1.3929% cheaper than B200
    TRTLLM · FP4
    GB200 NVL72
    $5.922287% more expensive than B200
    Dynamo SGLang · FP4
    GB300 NVL72
    $1.79717% more expensive than B200
    Dynamo TRTLLM · FP4
    View details
  • DeepSeek V4 Pro 1.6T

    Long Context Multi-Turn Realistic Agentic Scenario (AgentX)

    B200
    cannot reach @200
    MI355X
    cannot reach @200
    B300
    cannot reach @200
    GB200 NVL72
    no data for this scenario
    GB300 NVL72
    cannot reach @200
    View details
  • Kimi K3 2.8T

    Long Context Multi-Turn Realistic Agentic Scenario (AgentX)

    B200
    cannot reach @200
    MI355X
    no data for this scenario
    B300
    cannot reach @200
    GB200 NVL72
    cannot reach @200
    GB300 NVL72
    no data for this scenario
    View details
  • MiniMax M3 428B

    8K/1K

    B200
    vLLM · FP4
    MI355X
    $0.15418% more expensive than B200
    ATOM¹ · FP4
    B300
    $0.15620% more expensive than B200
    Dynamo vLLM · FP4
    GB200 NVL72
    cannot reach @200
    GB300 NVL72
    $0.487275% more expensive than B200
    Dynamo vLLM · FP8
    View details
  • MiniMax M3 428B

    Long Context Multi-Turn Realistic Agentic Scenario (AgentX)

    B200
    vLLM · FP4
    MI355X
    no data for this scenario
    B300
    cannot reach @200
    GB200 NVL72
    no data for this scenario
    GB300 NVL72
    no data for this scenario
    View details
  • GLM5.2

    Long Context Multi-Turn Realistic Agentic Scenario (AgentX)

    B200
    SGLang · FP4
    MI355X
    no data for this scenario
    B300
    cannot reach @200
    GB200 NVL72
    no data for this scenario
    GB300 NVL72
    no data for this scenario
    View details
  • Qwen3.5 397B

    8K/1K

    B200
    SGLang · FP4
    MI355X
    $0.332213% more expensive than B200
    ATOM¹ · FP8
    B300
    $0.11912% more expensive than B200
    SGLang · FP4
    GB200 NVL72
    $0.546414% more expensive than B200
    Dynamo SGLang · FP8
    GB300 NVL72
    $0.0988% cheaper than B200
    Dynamo TRTLLM · FP4
    View details
  • Qwen3.5 397B

    Long Context Multi-Turn Realistic Agentic Scenario (AgentX)

    B200
    SGLang · FP8
    MI355X
    no data for this scenario
    B300
    $0.01933% cheaper than B200
    SGLang · FP4
    GB200 NVL72
    no data for this scenario
    GB300 NVL72
    $0.01451% cheaper than B200
    Dynamo SGLang · FP4
    View details

— = no result. ∞ = B200 baseline unavailable.

If a chip does not have FP4 spec decoding available, the next best available configuration is used.