Provider
WandB
36 Models · 36 Prices · Cheapest on 7 · Uptime — · updated 2026-09-19 01:15 UTC
Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).
About
WandB is an AI inference provider that serves 13 machine-learning models through official and openrouter platforms, facilitating the deployment and use of these models in various applications.
AI-generated summary from public information — is this yours? Claim & edit
Models served
| Model | $ in /1M | $ out /1M | Cheapest | Router / Source | Evidence |
|---|---|---|---|---|---|
| gpt-oss-20b | $0.030 | $0.130 | — | Pricebook (LiteLLM) ↗ | Official list |
| granite-4.1-8b | $0.050 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Mellum2-12B-A2.5B-Instruct | $0.050 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| gpt-oss-120b | $0.030 | $0.170 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-14B-Instruct | $0.050 | $0.220 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-235B-A22B-Instruct-2507 | $0.100 | $0.100 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-235B-A22B-Thinking-2507 | $0.100 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | $0.070 | $0.200 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| granite-4.2-8b | $0.100 | $0.150 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-30B-A3B-Instruct-2507 | $0.100 | $0.300 | — | Pricebook (LiteLLM) ↗ | Official list |
| gemma-4-31B-it | $0.100 | $0.340 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V4-Flash-0731 | $0.130 | $0.280 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V4-Flash | $0.140 | $0.280 | — | Pricebook (LiteLLM) ↗ | Official list |
| Llama-3.1-8B-Instruct | $0.220 | $0.220 | — | Pricebook (LiteLLM) ↗ | Official list |
| GLM-5.3-Flash | $0.150 | $0.500 | — | Pricebook (LiteLLM) ↗ | Official list |
| Llama-4-Scout-17B-16E-Instruct | $0.170 | $0.660 | — | Pricebook (LiteLLM) ↗ | Official list |
| MiniMax-M3 | $0.230 | $0.960 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.6-35B-A3B | $0.250 | $1.25 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.5-35B-A3B | $0.250 | $1.25 | — | Pricebook (LiteLLM) ↗ | Official list |
| MiniMax-M2.5 | $0.300 | $1.20 | — | Pricebook (LiteLLM) ↗ | Official list |
| Llama-3.3-70B-Instruct | $0.710 | $0.710 | — | Pricebook (LiteLLM) ↗ | Official list |
| Llama-3.1-70B-Instruct | $0.800 | $0.800 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V3.1 | $0.550 | $1.65 | — | Pricebook (LiteLLM) ↗ | Official list |
| NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.500 | $2.15 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.8-27B | $0.400 | $3.00 | — | Pricebook (LiteLLM) ↗ | Official list |
| Kimi-K2-Instruct | $0.600 | $2.50 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-Coder-480B-A35B-Instruct | $1.00 | $1.50 | — | Pricebook (LiteLLM) ↗ | Official list |
| GLM-5.2 | $0.760 | $2.42 | — | Pricebook (LiteLLM) ↗ | Official list |
| Kimi-K2.5 | $0.600 | $3.00 | — | Pricebook (LiteLLM) ↗ | Official list |
| Kimi-K2.6 | $0.650 | $3.41 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.6-27B | $0.600 | $3.60 | — | Pricebook (LiteLLM) ↗ | Official list |
| Kimi-K2.7-Code | $0.710 | $3.50 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V4-Pro | $1.15 | $2.55 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V3-0324 | $1.14 | $2.75 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-V4-Pro-0813 | $1.31 | $3.96 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-R1-0528 | $1.35 | $5.40 | — | Pricebook (LiteLLM) ↗ | Official list |