Pricing
Simple, per-token pricing
Prices are in USD per 1 million tokens and update live. You're billed only for what each request uses — input, output and cached tokens — from a prepaid balance.
No subscription
Top up any amount from $5. Unused balance never expires.
Cache-aware
Re-used prompt tokens are billed at the cheaper cached rate automatically.
Full transparency
Every request shows its tokens and exact cost in your dashboard.
Monthly cost estimator
Coding agents typically re-use 50–80% of their prompt from cache. Adjust to your workload — the last column updates live.
| Model | Context | Input /1M | Output /1M | Cached /1M | Est. / month |
|---|---|---|---|---|---|
| Claude Fable 5 claude-fable-5 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| Claude Opus 4.6 claude-opus-4-6 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| Claude Opus 4.7 claude-opus-4-7 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| Claude Opus 4.8 claude-opus-4-8 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| Claude Opus 5 claude-opus-5 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| Claude Opus 5.5 claude-opus-5-5 | 1M | $1.6 | $1.6 | $0.16 | $17.92 |
| Claude Sonnet 5 claude-sonnet-5trial | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| DeepSeek V4 Flash deepseek-v4-flash-0731 | 1M | $0.06 | $0.06 | $0.0053 | $0.66 |
| DeepSeek V4 Pro deepseek-v4-pro-0813 | 1M | $0.5 | $0.5 | $0.1 | $6.20 |
| DeepSeek V4 Pro Uncensored deepseek-v4-pro-uncensored | 1M | $0.5 | $0.5 | $0.1 | $6.20 |
| DeepSeek V4.1 Flash deepseek-v4.1-flashtrial | 1M | $0.04 | $0.04 | $0.01 | $0.52 |
| GLM-5.2 glm-5.2 | 1M | $0.6 | $0.6 | $0.1 | $7.20 |
| GLM-5.3 glm-5.3 | 1M | $0.6 | $0.6 | $0.1 | $7.20 |
| GLM-5.3 Flash glm-5.3-flashtrial | 1M | $0.1 | $0.1 | $0.0089 | $1.11 |
| GLM-5.3 Flash Abliterated glm-5.3-flash-abliterated | 1M | $0.4 | $0.4 | $0.1 | $5.20 |
| GLM-5.3 Flash Uncensored glm-5.3-flash-uncensored | 1M | $0.1 | $0.1 | $0.0089 | $1.11 |
| GLM-5.3 Uncensored glm-5.3-uncensored | 1M | $0.6 | $0.6 | $0.1 | $7.20 |
| GPT-5.5 gpt-5.5 | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| GPT-5.6 Luna gpt-5.6-luna | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| GPT-5.6 Sol gpt-5.6-sol | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| GPT-5.6 Terra gpt-5.6-terra | 1M | $0.9 | $0.9 | $0.08 | $9.96 |
| GPT-6 Astra gpt-6-astra | 1.05M | $0.9 | $0.9 | $0.08 | $9.96 |
| GPT-6 Luna gpt-6-lunatrial | 1.05M | $0.1 | $0.1 | $0.02 | $1.24 |
| GPT-6 Sol gpt-6-sol | 1.05M | $0.4 | $0.4 | $0.08 | $4.96 |
| GPT-6.1 Sol gpt-6.1-sol | 1.05M | $0.2 | $0.2 | $0.04 | $2.48 |
| Grok 4.5 grok-4.5 | 200K | $0.2 | $0.2 | $0.04 | $2.48 |
| Grok 4.6 grok-4.6 | 500K | $0.2 | $0.2 | $0.04 | $2.48 |
| Grok 4.7 grok-4.7 | 500K | $0.2 | $0.2 | $0.04 | $2.48 |
| Kimi K3 kimi-k3 | 1M | $0.3 | $0.3 | $0.06 | $3.72 |
| MiMo V2.6 Flash mimo-v2.6-flash | 600K | $0.06 | $0.06 | $0.004 | $0.65 |
| MiMo V2.6 Pro mimo-v2.6-pro | 600K | $0.2 | $0.2 | $0.006 | $2.07 |
Estimates assume the cache hit rate applies to input tokens. Actual cost depends on your prompts; see per-request costs in the dashboard.