Operational Checked 1d ago

Mode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMs

com.modevc/chart-ai-inference-cost-comparison

Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..

Latest observation

Status overview

Current statusOperationalNetwork, MCP handshake, and supported capability checks succeeded.

Latency294 msEnd-to-end protocol check

Protocol2026-07-28Modern flow

Tools discovered3Safe tools/list discovery only

Reliability

Auth-required and unknown checks are excluded.

Last 24 hours—Collecting comparable data

Last 7 days100%1 comparable checks · 294 ms average

Last 30 days100%2 comparable checks · 283 ms average

OperationalDegradedDownExcludedNewest on the left

Transparent checks

Network reachability

HTTPS endpoint and response timing.

Passed

MCP handshake

Modern discovery or legacy initialization.

Passed

Tools/list

Capability discovery without invoking any tool.

Passed

Events

No incidents recorded

An incident opens only after consecutive confirmed failures.

Keep exploring