Back to providers
Provider · active

chutes

Listed in the BitRouter provider registry — rendered straight from the source YAML so what you see here is exactly what the proxy reads when it routes.

providers/chutes.yaml
01 — Overview
Models
7
Protocols
openai
Cheapest input
$0.09
/ 1M tokens
Routing weight
1
higher = preferred
02 — Rate limits & routing
Limits
  • scope: *
    rpm 30
Protocol mapping
  • *openai
03 — Model listingsSheet 03 / 07

The exact set of models chutes serves through BitRouter, with prices straight from the registry. Click any row to view the model in the catalog.

Model IDUpstream slugInputCache readOutput
xiaomi/mimo-v2-flashXiaomiMiMo/MiMo-V2-Flash-TEE$0.09$0.04$0.29
minimax/minimax-m2.5MiniMaxAI/MiniMax-M2.5-TEE$0.15$0.07$1.20
deepseek/deepseek-v3.2deepseek-ai/DeepSeek-V3.2-TEE$0.28$0.14$0.42
moonshotai/kimi-k2.5moonshotai/Kimi-K2.5-TEE$0.44$0.22$2.00
moonshotai/kimi-k2.6moonshotai/Kimi-K2.6-TEE$0.95$0.47$4.00
z-ai/glm-5zai-org/GLM-5-TEE$0.95$0.47$2.55
z-ai/glm-5.1zai-org/GLM-5.1-TEE$1.05$0.53$3.50

Cheapest output: $0.29 / 1M tokens. Prices in USD per million tokens.