The same models as the official APIs, billed by real usage — no subscriptions, no usage windows. Start on free trial credit and run an actual task before you pay.
Have another question? Contact our support team anytime.
Yes — the same models, served through direct connections to the official providers. What makes it cheap is scale: the more traffic we serve, the more repeated context hits the cache, and cached tokens bill at a fraction of the standard rate. That is a cost structure, not a compromise. Run a real task on trial credit and diff the output against the official API yourself.
See the results and the full billing trail, then top up as needed. Credit never expires.
The same models as the official APIs, billed by real usage — no subscriptions, no usage windows. Start on free trial credit and run an actual task before you pay.
Direct provider connections and volume-scale cache hits keep costs low, so prices can stay as low as ~4% of official list.
Prices sync with official pricing in real time; the console shows the actual amount charged.
| Model | Input price | Output price | Cache read | vs. official pricing | Ratio | Status |
|---|---|---|---|---|---|---|
GPT7 models | ||||||
GPT-5.6 SolOpenAI | $0.25 / 1M | $1.50 / 1M | $0.03 / 1M | Save ~95% | 0.35x | Online |
GPT-5.6 TerraOpenAI | $0.10 / 1M | $0.60 / 1M | $0.01 / 1M | Save ~96% | 0.35x | Online |
GPT-5.4OpenAI | $0.13 / 1M | $0.75 / 1M | $0.01 / 1M | Save ~95% | 0.35x | Online |
GPT-5.4 MiniOpenAI | $0.04 / 1M | $0.23 / 1M | $0.00 / 1M | Save ~95% | 0.35x | Online |
GPT-5.5OpenAI | $0.25 / 1M | $1.50 / 1M | $0.03 / 1M | Save ~95% | 0.35x | Online |
GPT Image 2OpenAI | $0.028 / request | — | — | — | 0.35x | Online |
Codex Auto ReviewOpenAI | $0.25 / 1M | $1.50 / 1M | $0.03 / 1M | — | 0.35x | Online |
Claude9 models | ||||||
Claude Fable 5Anthropic | $0.71 / 1M | $3.57 / 1M | $0.07 / 1M | — | 0.5x | Online |
Claude Haiku 4.5Anthropic | $0.07 / 1M | $0.36 / 1M | $0.01 / 1M | — | 0.5x | Online |
Claude Haiku 4.5Anthropic | $0.07 / 1M | $0.36 / 1M | $0.01 / 1M | Save ~93% | 0.5x | Online |
Claude Opus 4.6Anthropic | $0.36 / 1M | $1.79 / 1M | $0.04 / 1M | Save ~93% | 0.5x | Online |
Claude Opus 4.7Anthropic | $0.36 / 1M | $1.79 / 1M | $0.04 / 1M | Save ~93% | 0.5x | Online |
Claude Opus 4.8Anthropic | $0.36 / 1M | $1.79 / 1M | $0.04 / 1M | Save ~93% | 0.5x | Online |
Claude Opus 5Anthropic | $0.36 / 1M | $1.79 / 1M | $0.04 / 1M | — | 0.5x | Online |
Claude Sonnet 4.6Anthropic | $0.21 / 1M | $1.07 / 1M | $0.02 / 1M | Save ~93% | 0.5x | Online |
Claude Sonnet 5Anthropic | $0.14 / 1M | $0.71 / 1M | $0.01 / 1M | — | 0.5x | Online |
Gemini14 models | ||||||
Gemini 2.5 FlashGoogle | $0.01 / 1M | $0.09 / 1M | $0.00 / 1M | Save ~96% | 0.9x | Online |
Gemini 2.5 Flash LiteGoogle | $0.01 / 1M | $0.05 / 1M | $0.00 / 1M | — | 0.9x | Online |
Gemini 3 FlashGoogle | $0.06 / 1M | $0.39 / 1M | $0.01 / 1M | — | 0.9x | Online |
Gemini 3 ProGoogle | $0.26 / 1M | $1.54 / 1M | $0.03 / 1M | — | 0.9x | Online |
Gemini 3 Pro ImageGoogle | $0.26 / 1M | — | — | — | 0.9x | Online |
Gemini 3 Pro PreviewGoogle | $0.07 / 1M | $0.44 / 1M | $0.01 / 1M | Save ~96% | 0.9x | Online |
Gemini 3.1 Flash ImageGoogle | $0.06 / 1M | — | — | — | 0.9x | Online |
Gemini 3.1 Flash Image PreviewGoogle | $0.06 / request | — | — | — | 0.9x | Online |
Gemini 3.1 Flash LiteGoogle | $0.03 / 1M | $0.19 / 1M | $0.00 / 1M | — | 0.9x | Online |
Gemini 3.1 Pro PreviewGoogle | $0.26 / 1M | $1.54 / 1M | $0.03 / 1M | Save ~90% | 0.9x | Online |
Gemini 3.5 FlashGoogle | $0.19 / 1M | $1.16 / 1M | $0.02 / 1M | — | 0.9x | Online |
Gemini 3.6 FlashGoogle | $0.19 / 1M | $0.96 / 1M | $0.02 / 1M | — | 0.9x | Online |
Gemini 3.7 FlashGoogle | $0.10 / 1M | $0.48 / 1M | $0.01 / 1M | — | 0.9x | Online |
Gemini 3.8 FlashGoogle | $0.10 / 1M | $0.48 / 1M | $0.01 / 1M | — | 0.9x | Online |
Grok3 models | ||||||
Grok 4.3xAI | $0.09 / 1M | $0.18 / 1M | $0.01 / 1M | — | 0.5x | Online |
Grok 4.5xAI | $0.14 / 1M | $0.43 / 1M | — | — | 0.5x | Online |
Grok 4.6xAI | $0.14 / 1M | $0.43 / 1M | $0.04 / 1M | — | 0.5x | Online |
DeepSeek3 models | ||||||
DeepSeek V4 FlashDeepSeek | $0.34 / 1M | $1.03 / 1M | $0.01 / 1M | — | 0.8x | Online |
DeepSeek V4 Flash-vision-expDeepSeek | $8.57 / 1M | $8.57 / 1M | — | — | 0.8x | Online |
DeepSeek V4 ProDeepSeek | $0.64 / 1M | $1.93 / 1M | $0.02 / 1M | — | 0.5x | Online |
MiniMax5 models | ||||||
MiniMax M2.5MiniMax | $0.03 / 1M | $0.14 / 1M | $0.00 / 1M | Save ~89% | 0.8x | Online |
MiniMax M2.5 HighSpeedMiniMax | $0.03 / 1M | $0.14 / 1M | $0.01 / 1M | Save ~94% | 0.8x | Online |
MiniMax M2.7MiniMax | $0.03 / 1M | $0.14 / 1M | $0.01 / 1M | Save ~89% | 0.8x | Online |
MiniMax M2.7 HighSpeedMiniMax | $0.03 / 1M | $0.14 / 1M | $0.01 / 1M | Save ~94% | 0.8x | Online |
MiniMax M3MiniMax | $0.03 / 1M | $0.14 / 1M | $0.01 / 1M | Save ~89% | 0.8x | Online |
Unit: USD/1M tokens
Ratio is the multiplier of the billing group serving the model: you pay the model's USD list price × the ratio. The vs-official column already factors in the top-up conversion.
Top up what you need, when you need it. Every $1 of credit spends like $1 on the official APIs, and credit never expires.
Kick the tires on your own codebase
Ship a small project end to end
A full week of heavy agent sessions
Heavy monthly usage and team collaboration
New here? Start on the free trial credit: connect your tool, run a real task, and top up when the results convince you.
Token and request estimates are based on GPT-5.6 Sol's current platform pricing and recent real Codex usage (about 93.5% cache hits); actual mileage varies with model choice and usage pattern.
Top-ups are processed by Stripe with international cards. International invoices are available; Chinese fapiao is not supported.