Model pricing
All models are billed per token — genuine models, no substitution or degradation, transparent pricing. No subscription, no minimum, no long-context surcharge, no dynamic pricing. Settlement currency USDT / USDC. The “est. effective w/ cache” figures are estimates at an 80% input-cache hit rate, not discounts.
57Models
10providers
High availability
🎁 New users save ~8% on your first top-up — applied automatically
👑 Top up $100+ in total to become VIP and keep ~8% off long-term · all automatic, no promo code
livePrices sync with upstream in real time · unit: per million tokens ($/M)First-party · native precision · no quantization
| Model / provider | Type | Input /M | Output /M |
|---|---|---|---|
| OpenAI | |||
gpt-5.4 | per-token | $3.00 est. effective w/ cache ≈ $0.84 | $18.00 |
gpt-5.4-mini | per-token | $0.90 est. effective w/ cache ≈ $0.25 | $5.40 |
gpt-5.5 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $36.00 |
gpt-5.6-luna | per-token | $0.24 est. effective w/ cache ≈ $0.0670 | $1.44 |
gpt-5.6-sol | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $36.00 |
gpt-5.6-terra | per-token | $2.40 est. effective w/ cache ≈ $0.67 | $14.40 |
gpt-6-astra | per-token | $12.00 est. effective w/ cache ≈ $3.36 | $60.00 |
gpt-image-2 | per-token | $6.00 | $36.00 |
| Anthropic | |||
claude-fable-5 | per-token | $12.00 est. effective w/ cache ≈ $3.36 | $60.00 |
claude-fable-5-1 | per-token | $12.00 est. effective w/ cache ≈ $3.36 | $60.00 |
claude-haiku-4-5-20251001 | per-token | $1.20 est. effective w/ cache ≈ $0.34 | $6.00 |
claude-opus-4-5-20251101 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $29.99 |
claude-opus-4-6 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $30.00 |
claude-opus-4-7 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $30.00 |
claude-opus-4-8 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $30.00 |
claude-opus-5 | per-token | $6.00 est. effective w/ cache ≈ $1.68 | $30.00 |
claude-opus-5-5 | per-token | $4.80 est. effective w/ cache ≈ $1.15 | $24.00 |
claude-sonnet-4-5-20250929 | per-token | $3.59 est. effective w/ cache ≈ $1.00 | $17.95 |
claude-sonnet-4-6 | per-token | $3.60 est. effective w/ cache ≈ $1.01 | $18.00 |
claude-sonnet-5 | per-token | $2.40 est. effective w/ cache ≈ $0.67 | $12.00 |
claude-sonnet-5-5 | per-token | $2.40 est. effective w/ cache ≈ $0.67 | $12.00 |
| DeepSeek | |||
deepseek-v4-flash | per-token | $0.17 est. effective w/ cache ≈ $0.0430 | $1.44 |
deepseek-v4-pro | per-token | $1.58 est. effective w/ cache ≈ $0.36 | $4.75 |
deepseek-v4.1-flash | per-token | $0.17 est. effective w/ cache ≈ $0.0430 | $1.44 |
| ByteDance | |||
doubao-seedance-2.0 | Video | $8.04 ≈ $0.40/clip | $8.04 |
doubao-seedance-2.0-fast | Video | $6.48 ≈ $0.33/clip | $6.48 |
doubao-seedance-2.0-mini | Video | $4.32 ≈ $0.22/clip | $4.32 |
| Google Gemini | |||
gemini-2.5-flash | per-token | $0.36 est. effective w/ cache ≈ $0.14 | $3.00 |
gemini-2.5-flash-image | Per request | $0.048 | — |
gemini-2.5-flash-lite | per-token | $0.12 est. effective w/ cache ≈ $0.0270 | $0.48 |
gemini-2.5-pro | per-token | $1.50 est. effective w/ cache ≈ $0.42 | $12.00 |
gemini-3-flash-preview | per-token | $0.60 est. effective w/ cache ≈ $0.17 | $3.60 |
gemini-3-pro-image-preview | Per request | $0.240 | — |
gemini-3.1-flash-image | per-token | $0.60 | $72.00 |
gemini-3.1-flash-image-preview | Per request | $0.180 | — |
gemini-3.1-flash-lite-preview | per-token | $0.30 est. effective w/ cache ≈ $0.0840 | $1.80 |
gemini-3.1-pro-preview | per-token | $2.40 est. effective w/ cache ≈ $0.67 | $14.40 |
gemini-3.5-flash | per-token | $1.80 est. effective w/ cache ≈ $0.50 | $10.80 |
gemini-3.5-flash-lite | per-token | $0.36 est. effective w/ cache ≈ $0.10 | $3.00 |
gemini-3.6-flash | per-token | $1.80 est. effective w/ cache ≈ $0.50 | $9.00 |
gemini-3.7-flash | per-token | $1.80 est. effective w/ cache ≈ $0.50 | $9.00 |
gemini-3.8-flash | per-token | $1.80 est. effective w/ cache ≈ $0.50 | $9.00 |
| Zhipu GLM | |||
GLM-5-Turbo | per-token | $1.44 est. effective w/ cache ≈ $0.52 | $4.80 |
GLM-5.2 | per-token | $1.68 | $5.28 |
glm-5.3 | per-token | $1.44 est. effective w/ cache ≈ $0.58 | $5.02 |
glm-5.3-flash | per-token | $0.14 est. effective w/ cache ≈ $0.0620 | $0.50 |
GLM-5V-Turbo | per-token | $1.44 est. effective w/ cache ≈ $0.52 | $4.80 |
| Moonshot Kimi | |||
kimi/kimi-k3 | per-token | $3.60 est. effective w/ cache ≈ $1.01 | $18.00 |
| MiniMax | |||
MiniMax/MiniMax-M3 | per-token | $0.36 est. effective w/ cache ≈ $0.19 | $1.44 |
| Alibaba Qwen | |||
qwen3-235b-a22b | per-token | $0.34 | $1.38 |
qwen3-235b-a22b-instruct-2507 | per-token | $0.07 | $0.49 |
qwen3-235b-a22b-thinking-2507 | per-token | $0.24 | $0.72 |
qwen3-coder-480b-a35b-instruct | per-token | $0.36 | $1.56 |
qwen3.8-flash | per-token | $0.15 est. effective w/ cache ≈ $0.0490 | $0.49 |
qwen3.8-max | per-token | $2.15 est. effective w/ cache ≈ $0.65 | $6.44 |
qwen3.8-max-0902 | per-token | $2.15 est. effective w/ cache ≈ $0.65 | $6.44 |
| Xiaomi MiMo | |||
?xiaomi/mimo-v2.5-pro | per-token | $0.52 est. effective w/ cache ≈ $0.11 | $1.04 |
