pricing

Four intelligent tiers · pay per use

The Qwen3 routing brain auto-selects the best model by task capability. Pay only for what you use — cache hits cost even less.

Mesh Free
$0
daily free quota

✓ Daily free calls / tokens
✓ Node compute + free API fallback
✓ Intelligent routing (Qwen3 decides)
✓ Run a node for unlimited free use
recommended
Mesh Pro
$0.30/M in
$0.60/M out

✓ Daily workhorse (80% of requests)
✓ Intelligent routing by capability
✓ Cache hit $0.005/M
✓ Session stickiness + context compression
Mesh Max
$0.90/M in
$2.00/M out

✓ Single flagship model (V4-Pro, etc.)
✓ Hard problems / complex tasks
✓ Cache hit $0.005/M
✓ Picks the strongest flagship by capability
Mesh Research
$3.00/M in
$8.00/M out

✓ Deep research (MoA multi-model)
✓ Major questions / decisions
✓ Autonomous agent-loop iteration
✓ Cross-validation + synthesis report
Detailed price table (per 1M tokens)
model input $ output $ cache hit notes
mesh-free $0 $0 daily free quota
mesh-pro $0.30 $0.60 $0.005 intelligent routing workhorse
mesh-max $0.90 $2.00 $0.005 single flagship model
mesh-research $3.00 $8.00 deep research MoA
Top-up methods
🇨🇳 China · WeChat Pay
WeChat QR-code payment
Zero fees
Instant credit
🌍 Global · USDT (TRC-20)
USDT-TRC20 transfer
5% fee
Auto-credited
Contribute compute, earn credits
node tier device credit multiplier models
Tier 0Phone×0.30.5-2B
Tier 1Light PC×1Qwen3-8B
Tier 2Mid-range GPU×3Qwen3-14B
Tier 3Powerful GPU / large-memory personal rig×10GLM-5 / 32B / V4-Pro (DGX Spark, M5 Ultra)
Tier 4Compute center (enterprise)×30H100/A100 running GLM-5.2 / V4-Pro

Credits are spendable on mesh-pro/max/research within the platform. Credits are not withdrawable for cash — platform use only.

Get started free →

500 free credits on sign-up, no credit card required