Pricing and usage

UniKey uses AI Credits to measure and settle usage across model calls, API requests, agent calls, and future workflow execution.

Credits conversion

$1 = 10,000 AI Credits

The pricing table below uses the same upstream official model price data as the reference platform, expressed as USD per 1M tokens. To convert a table value into UniKey Credits per token:

Credits per token = USD per 1M tokens / 100

Example: GPT-5.2 input is 1.75 USD / 1M tokens, so each input token costs 0.0175 UniKey Credits.

Model pricing

Model	Input ($/1M tokens)	Cache Write ($/1M tokens)	Cache Read ($/1M tokens)	Output ($/1M tokens)	Web Search (Credits/use)
MiniMax M3	0.30	0.30	0.06	1.20	-
MiniMax M2.7	0.30	0.375	0.06	1.20	-
Kimi K2.6	0.95	0.95	0.16	4.00	-
Kimi K2.5	0.59	0.59	0.177	3.00	-
Qwen3.6-27B	0.19	0.19	0.019	2.99	-
GLM-5.2	1.40	1.40	0.28	4.40	-
GLM-5.1	1.40	1.40	0.26	4.40	-
DeepSeek V3.2	0.29	0.29	0.145	0.44	-
DeepSeek V4 Flash	0.28	0.28	0.0056	0.56	-
DeepSeek V4 Pro	0.87	0.87	0.0087	1.74	-
GPT-5.6 Sol	5.00	6.25	0.50	30.00	100
GPT-5.6 Terra	2.50	3.125	0.25	15.00	100
GPT-5.6 Luna	1.00	1.25	0.10	6.00	100
GPT-5.4	2.50	2.50	0.25	15.00	100
GPT-5.5	5.00	5.00	0.50	30.00	100
GPT-5.5 Instant	5.00	5.00	0.50	30.00	100
GPT-5.4 Pro	30.00	30.00	3.00	180.00	-
GPT-5.2	1.75	1.75	0.175	14.00	100
GPT-5.4 Mini	0.75	0.75	0.075	4.50	100
GPT-5 Mini	0.25	0.25	0.025	2.00	100
GPT-5.4 Nano	0.20	0.20	0.02	1.25	100
GPT-5 Nano	0.05	0.05	0.005	0.40	-
Claude Fable 5	10.00	12.50	1.00	50.00	100
Claude Opus 4.8	5.00	6.25	0.50	25.00	100
Claude Opus 4.7	5.00	6.25	0.50	25.00	100
Claude Opus 4.6	5.00	6.25	0.50	25.00	100
Claude Opus 4.5	5.00	6.25	0.50	25.00	100
Claude Sonnet 5	2.00	2.50	0.20	10.00	100
Claude Sonnet 4.6	3.00	3.75	0.30	15.00	100
Claude Sonnet 4.5	3.00	3.75	0.30	15.00	100
Claude Haiku 4.5	1.00	1.25	0.10	5.00	100
Gemini 3.1 Pro	2.00	2.00	0.20	12.00	140
Gemini 3.5 Flash	1.50	1.50	0.15	9.00	140
Gemini 3 Flash	0.50	0.50	0.05	3.00	140

Cache pricing notes

• Cache Write is charged when tokens are written into prompt cache.
• Cache Read is the discounted rate for reusing cached tokens.
• Claude models and GPT-5.6 models apply a 25% premium on cache writes.
• Cache retention time and long-context pricing may vary by upstream provider.

Calculation examples

Claude Sonnet 4.6 with 1,000 cache-write tokens:

1,000 * 3.75 / 100 = 37.5 Credits

GPT-5.2 with 10 input tokens and 50 output tokens:

(10 * 1.75 + 50 * 14.00) / 100 = 7.175 Credits

Usage information

Track these fields for every production request:

• model name;
• endpoint path;
• prompt, completion, cache-write, and cache-read token counts;
• Credits consumed;
• latency and error code;
• request owner, project, or agent ID.

Top up and billing records

UniKey uses a prepaid model. Top up AI Credits before sending production traffic, and review billing records after batch jobs, agent runs, or high-volume deployments.

For agentic systems, enforce application-side request budgets, maximum tool iterations, and stop conditions before calling high-cost models.