Models
Every model the platform serves, with live per-1M-token pricing.
Every model speaks both wire formats — OpenAI (chat/completions + responses) and Anthropic (messages) — so any coding harness works.
43 of 43 models
mimo-v2.5- Input / 1M
- $0.14$0.049save $0.091
- Output / 1M
- $0.28$0.098save $0.182
- Context
- 1M
- Max out
- 131K
glm-5.3-flash- Input / 1M
- $0.15$0.0525save $0.0975
- Output / 1M
- $0.50$0.175save $0.325
- Context
- 1M
- Max out
- 131K
qwen3.8-omni-flash- Input / 1M
- $0.15$0.0525save $0.0975
- Output / 1M
- $0.47$0.1645save $0.3055
- Context
- 1M
- Max out
- 131K
gpt-5.6-luna- Input / 1M
- $0.20$0.07save $0.13
- Output / 1M
- $1.20$0.42save $0.78
- Context
- 1.05M
- Max out
- 128K
gpt-6-luna- Input / 1M
- $0.20$0.07save $0.13
- Output / 1M
- $0.75$0.2625save $0.4875
- Context
- 1.05M
- Max out
- 128K
qwen3.8-27b- Input / 1M
- $0.20$0.07save $0.13
- Output / 1M
- $0.80$0.28save $0.52
- Context
- 1M
- Max out
- 131K
qwen3.8-flash- Input / 1M
- $0.15$0.0825save $0.0675
- Output / 1M
- $0.47$0.2585save $0.2115
- Context
- 1M
- Max out
- 131K
deepseek-v4-flash- Input / 1M
- $0.30$0.105save $0.195
- Output / 1M
- $1.20$0.42save $0.78
- Context
- 1M
- Max out
- 393K
deepseek-v4-flash-0731- Input / 1M
- $0.30$0.105save $0.195
- Output / 1M
- $1.20$0.42save $0.78
- Context
- 1M
- Max out
- 393K
deepseek-v4.1-flash- Input / 1M
- $0.30$0.105save $0.195
- Output / 1M
- $1.20$0.42save $0.78
- Context
- 1M
- Max out
- 128K
minimax-m3- Input / 1M
- $0.30$0.105save $0.195
- Output / 1M
- $1.20$0.42save $0.78
- Context
- 1M
- Max out
- 131K
glm-5.3-flashx- Input / 1M
- $0.37$0.1295save $0.2405
- Output / 1M
- $1.25$0.4375save $0.8125
- Context
- 1.05M
- Max out
- 131K
gemini-2.5-flash-imageGenerate with POST /v1/images/generations.
- Input / 1M
- $0.30$0.15save $0.15
- Output / 1M
- $2.50$1.25save $1.25
- Context
- 32.8K
- Max out
- 8.2K
mimo-v2.5-pro- Input / 1M
- $0.435$0.15225save $0.28275
- Output / 1M
- $0.87$0.3045save $0.5655
- Context
- 1M
- Max out
- 131K
deepseek-v4.1-flash-fast- Input / 1M
- $0.32$0.224save $0.096
- Output / 1M
- $1.16$0.812save $0.348
- Context
- 1M
- Max out
- 393K
qwen3.7-plus- Input / 1M
- $0.96$0.336save $0.624
- Output / 1M
- $3.84$1.344save $2.496
- Context
- 1M
- Max out
- 65.5K
deepseek-v4-pro- Input / 1M
- $1.32$0.462save $0.858
- Output / 1M
- $3.96$1.386save $2.574
- Context
- 1M
- Max out
- 393K
deepseek-v4-pro-0813- Input / 1M
- $1.32$0.462save $0.858
- Output / 1M
- $3.96$1.386save $2.574
- Context
- 1M
- Max out
- 393K
glm-5.2- Input / 1M
- $1.40$0.49save $0.91
- Output / 1M
- $4.40$1.54save $2.86
- Context
- 1M
- Max out
- 131K
glm-5.3- Input / 1M
- $1.40$0.49save $0.91
- Output / 1M
- $4.40$1.54save $2.86
- Context
- 1M
- Max out
- 131K
qwen3.7-max- Input / 1M
- $1.475$0.51625save $0.95875
- Output / 1M
- $4.425$1.54875save $2.87625
- Context
- 1M
- Max out
- 65.5K
gemini-3.8-flash- Input / 1M
- $1.50$0.525save $0.975
- Output / 1M
- $7.50$2.625save $4.875
- Context
- 1.05M
- Max out
- 65.5K
claude-sonnet-5-5- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $10$3.50save $6.50
- Context
- 1M
- Max out
- 128K
gpt-5.6-terra- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $12$4.20save $7.80
- Context
- 1.05M
- Max out
- 128K
grok-4.6- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $6$2.10save $3.90
- Context
- 500K
- Max out
- 128K
kimi-k3.1-pro- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $10$3.50save $6.50
- Context
- 1.05M
- Max out
- 1.05M
qwen3.8-max- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $6$2.10save $3.90
- Context
- 1M
- Max out
- 65.5K
qwen3.8-max-0902- Input / 1M
- $2$0.70save $1.30
- Output / 1M
- $6$2.10save $3.90
- Context
- 1M
- Max out
- 131K
kimi-k3- Input / 1M
- $3$1.05save $1.95
- Output / 1M
- $15$5.25save $9.75
- Context
- 1.05M
- Max out
- 131K
kimi-k3-256k- Input / 1M
- $3$1.05save $1.95
- Output / 1M
- $15$5.25save $9.75
- Context
- 262K
- Max out
- 131K
claude-opus-5-5- Input / 1M
- $4$1.40save $2.60
- Output / 1M
- $20$7save $13
- Context
- 1M
- Max out
- 128K
gemini-3.1-pro- Input / 1M
- $4$1.40save $2.60
- Output / 1M
- $18$6.30save $11.70
- Context
- 1.05M
- Max out
- 65.5K
gemini-4-argon- Input / 1M
- $4$1.40save $2.60
- Output / 1M
- $20$7save $13
- Context
- 1.05M
- Max out
- 1.05M
gpt-6.1-sol- Input / 1M
- $4$1.40save $2.60
- Output / 1M
- $15$5.25save $9.75
- Context
- 1.05M
- Max out
- 128K
grok-4.7- Input / 1M
- $4$1.40save $2.60
- Output / 1M
- $12$4.20save $7.80
- Context
- 500K
- Max out
- 500K
claude-opus-4.6- Input / 1M
- $5$1.75save $3.25
- Output / 1M
- $25$8.75save $16.25
- Context
- 1M
- Max out
- 128K
claude-opus-4-7- Input / 1M
- $5$1.75save $3.25
- Output / 1M
- $25$8.75save $16.25
- Context
- 1M
- Max out
- 128K
claude-opus-4-8- Input / 1M
- $5$1.75save $3.25
- Output / 1M
- $25$8.75save $16.25
- Context
- 1M
- Max out
- 128K
gpt-5.6-sol- Input / 1M
- $5$1.75save $3.25
- Output / 1M
- $30$10.50save $19.50
- Context
- 1.05M
- Max out
- 128K
claude-fable-5- Input / 1M
- $10$3.50save $6.50
- Output / 1M
- $50$17.50save $32.50
- Context
- 1.05M
- Max out
- 131K
claude-fable-5-1- Input / 1M
- $10$3.50save $6.50
- Output / 1M
- $50$17.50save $32.50
- Context
- 1.05M
- Max out
- 131K
gpt-6-astra- Input / 1M
- $10$3.50save $6.50
- Output / 1M
- $50$17.50save $32.50
- Context
- 1.05M
- Max out
- 128K
- GPT Image 2OpenAI
gpt-image-2Generate with POST /v1/images/generations.
- Input / 1M
- $5
- Output / 1M
- $8
- Context
- 400K
- Max out
- 400K
Price per 1M tokens.
Promo prices apply to pay-as-you-go usage paid from your balance; plans use the official price.