B2BB2B LLM

Cene modelov

Trenutno omogočeni modeli in cene v USD

Compare official provider pricing with potential Model Gate gateway savings.The crossed-out amount is the official public provider price. The highlighted amount illustrates up to 2× lower gateway pricing. Final corporate terms depend on the model, traffic profile, jurisdiction and committed volume.

BUSINESS MODEL CATALOG

Official prices and potential gateway savings

Prices are shown in USD per one million tokens. Gateway examples are calculated at 50% of the official public price to illustrate savings of up to 2×; they are not a binding offer.

Request corporate pricing
Official provider pricePotential Model Gate price
ModelInputOutputCache readCache writeReasoning
Claude Opus 5
claude-opus-5
$5$2.5up to 2× less$25$12.5up to 2× less$0.5$0.25up to 2× less$6.25$3.125up to 2× less$25$12.5up to 2× less
Claude Sonnet 5
claude-sonnet-5
$2$1up to 2× less$10$5up to 2× less$0.2$0.1up to 2× less$2.5$1.25up to 2× less$2$1up to 2× less
DeepSeek V4 Flash
deepseek-v4-flash
$0.14$0.07up to 2× less$0.28$0.14up to 2× less$0.0028$0.0014up to 2× less$0.14$0.07up to 2× less$0.28$0.14up to 2× less
DeepSeek V4 Pro
deepseek-v4-pro
$0.435$0.2175up to 2× less$0.87$0.435up to 2× less$0.0036$0.0018up to 2× less$0.435$0.2175up to 2× less$0.87$0.435up to 2× less
GLM 5.2
glm-5.2
$1.4$0.7up to 2× less$4.4$2.2up to 2× less$0.26$0.13up to 2× less$1.4$0.7up to 2× less$4.4$2.2up to 2× less
GPT 5.4 Mini
gpt-5.4-mini
$0.75$0.375up to 2× less$4.5$2.25up to 2× less$0.075$0.0375up to 2× less$0$0up to 2× less$4.5$2.25up to 2× less
GPT 5.6 Luna
gpt-5.6-luna
$0.2$0.1up to 2× less$0.4$0.2up to 2× less$0.2$0.1up to 2× less$0.25$0.125up to 2× less$0.2$0.1up to 2× less
GPT 5.6 Sol
gpt-5.6-sol
$5$2.5up to 2× less$30$15up to 2× less$0.5$0.25up to 2× less$6.25$3.125up to 2× less$30$15up to 2× less
GPT 5.6 Terra
gpt-5.6-terra
$2$1up to 2× less$12$6up to 2× less$0.2$0.1up to 2× less$2.5$1.25up to 2× less$12$6up to 2× less
Kimi K2.7 Code
kimi-k2.7-code
$1.9$0.95up to 2× less$8$4up to 2× less$0.38$0.19up to 2× less$1.9$0.95up to 2× less$8$4up to 2× less
Kimi K3
kimi-k3
$3$1.5up to 2× less$15$7.5up to 2× less$0.3$0.15up to 2× less$3$1.5up to 2× less$15$7.5up to 2× less
MiMo V2.5
mimo-v2.5
$0.15$0.075up to 2× less$0.3$0.15up to 2× less$0.04$0.02up to 2× less$0.15$0.075up to 2× less$0.3$0.15up to 2× less
MiMo V2.5 Pro
mimo-v2.5-pro
$0.45$0.225up to 2× less$0.9$0.45up to 2× less$0.04$0.02up to 2× less$0.45$0.225up to 2× less$0.9$0.45up to 2× less
MiniMax M3
minimax-m3
$0.45$0.225up to 2× less$1.8$0.9up to 2× less$0.09$0.045up to 2× less$0.45$0.225up to 2× less$1.8$0.9up to 2× less
Qwen3.7 Max
qwen3.7-max
$2.5$1.25up to 2× less$7.5$3.75up to 2× less$2.5$1.25up to 2× less$2.5$1.25up to 2× less$7.5$3.75up to 2× less
Qwen3.7 Plus
qwen3.7-plus
$1.2$0.6up to 2× less$4.8$2.4up to 2× less$1.2$0.6up to 2× less$1.2$0.6up to 2× less$4.8$2.4up to 2× less
Claude Opus 4.6
claude-opus-4-6
$5$2.5up to 2× less$25$12.5up to 2× less$0.5$0.25up to 2× less$6.25$3.125up to 2× less$25$12.5up to 2× less
Claude Opus 4.7
claude-opus-4-7
$5$2.5up to 2× less$25$12.5up to 2× less$0.5$0.25up to 2× less$6.25$3.125up to 2× less$25$12.5up to 2× less
Claude Opus 4.8
claude-opus-4-8
$5$2.5up to 2× less$25$12.5up to 2× less$0.5$0.25up to 2× less$6.25$3.125up to 2× less$25$12.5up to 2× less
Claude Sonnet 4.6
claude-sonnet-4-6
$3$1.5up to 2× less$15$7.5up to 2× less$0.3$0.15up to 2× less$3.75$1.875up to 2× less$15$7.5up to 2× less
GPT 5.4
gpt-5.4
$2.5$1.25up to 2× less$15$7.5up to 2× less$0.25$0.125up to 2× less$3.75$1.875up to 2× less$15$7.5up to 2× less
GPT 5.5
gpt-5.5
$5$2.5up to 2× less$30$15up to 2× less$0.5$0.25up to 2× less$6$3up to 2× less$30$15up to 2× less
Input-token caching and routing

Prompt/input-token caching may work through Model Gate, but cache affinity cannot be guaranteed because requests can be routed between eligible upstream routes. When guaranteed provider-side cache continuity is important, use a direct provider API account or key.

DIRECT PROVIDER ACCESS

Need to work without our gateway?

We can fund eligible official provider accounts or issue direct official API keys with a dedicated balance. Service fees start from 15% and depend on jurisdiction, provider, payment route and volume.

Discuss direct access