gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

Novita vs DeepInfra: LLM API price comparison

Across 45 models both gateways sell, Novita is cheaper on 3, DeepInfra on 34, and 8 are priced identically. Input prices are USD per million tokens, refreshed continually; every model links to its full cross-gateway history.

ModelNovita inDeepInfra in Novita outDeepInfra outCheaper
deepseek-r1-0528$0.70$0.50$2.50$2.15DeepInfra −29% →
deepseek-v3$0.89$0.32$0.89$0.89DeepInfra −64% →
deepseek-v4-flash$0.14$0.09$0.28$0.18DeepInfra −36% →
deepseek-v4-flash-0731$0.44$0.06$1.32$0.18DeepInfra −86% →
deepseek-v4-flash-vision-exp$0.44$0.44$1.32$1.32same
deepseek-v4-pro$1.60$1.30$3.20$2.60DeepInfra −19% →
deepseek-v4-pro-0813$1.32$1.30$3.96$2.60DeepInfra −2% →
deepseek-v4.1-flash$0.30$0.20$1.20$0.60DeepInfra −33% →
gemma-3-12b-it$0.05$0.05$0.10$0.15same
gemma-3-27b-it$0.12$0.08$0.20$0.16DeepInfra −33% →
gemma-4-26b-a4b-it$0.13$0.07$0.40$0.34DeepInfra −46% →
gemma-4-31b-it$0.14$0.15$0.40$0.40Novita −7% →
glm-4.6$0.55$0.50$2.20$2.00DeepInfra −9% →
glm-4.7$0.60$0.40$2.20$1.75DeepInfra −33% →
glm-5.2$1.40$0.75$4.40$2.40DeepInfra −46% →
glm-5.3$1.40$0.90$4.40$4.00DeepInfra −36% →
glm-5.3-flash$0.15$0.15$0.50$0.50same
gpt-oss-120b$0.05$0.04$0.25$0.17DeepInfra −26% →
gpt-oss-20b$0.04$0.03$0.15$0.14DeepInfra −25% →
hy4-preview$0.83$0.83$2.50$2.50same
kimi-k2.6$0.80$0.75$3.40$3.50DeepInfra −6% →
kimi-k3$3.00$2.85$15.00$14.25DeepInfra −5% →
ling-3.0-flash$0.06$0.06$0.18$0.18same
ling-3.0-flash-fin$0.07$0.06$0.22$0.18DeepInfra −20% →
ling-3.0-flash-vl$0.07$0.06$0.22$0.18DeepInfra −20% →
llama-4-scout-17b-16e-instruct$0.18$0.10$0.59$0.30DeepInfra −44% →
mimo-v2.6-flash$0.14$0.14$0.28$0.28same
mimo-v2.6-pro$0.43$0.43$0.87$0.87DeepInfra −1% →
minimax-m3$0.30$0.28$1.20$1.10DeepInfra −7% →
mythomax-l2-13b$0.09$0.40$0.09$0.40Novita −344% →
qwen3-235b-a22b-instruct-2507$0.09$0.09$0.58$0.55same
qwen3-max$2.11$1.20$8.45$6.00DeepInfra −43% →
qwen3-next-80b-a3b-instruct$0.15$0.09$1.50$1.10DeepInfra −40% →
qwen3-vl-235b-a22b-instruct$0.30$0.20$1.50$0.88DeepInfra −33% →
qwen3-vl-30b-a3b-instruct$0.20$0.15$0.70$0.60DeepInfra −25% →
qwen3.5-27b$0.30$0.26$2.40$2.60DeepInfra −13% →
qwen3.5-35b-a3b$0.25$0.14$2.00$1.00DeepInfra −44% →
qwen3.5-397b-a17b$0.60$0.45$3.60$3.00DeepInfra −25% →
qwen3.6-27b$0.60$0.32$3.60$3.20DeepInfra −47% →
qwen3.6-35b-a3b$0.25$0.10$1.49$0.95DeepInfra −60% →
qwen3.7-max$1.25$2.50$3.75$7.50Novita −100% →
qwen3.8-2.4t-a95b$2.00$2.00$6.00$6.00same
qwen3.8-27b$0.42$0.20$3.00$2.50DeepInfra −52% →
qwen3.8-flash$0.15$0.11$0.47$0.38DeepInfra −25% →
qwen3.8-max$2.00$1.65$6.00$4.95DeepInfra −18% →

← All LLM prices