Novita AI API pricing

135 Novita AI models: text, embeddings, rerank, from price book 2026-10-22.

Billing rules Veqen applies

  • Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
  • Rerank models: per query.

Reconcile your bill

Novita AI doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.

Prices come from Novita AI's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.

Text 130 models

ModelInputOutputCached inputBatch inputContextStatus
meta-llama/llama-3.1-8b-instruct$0.02$0.05——16.4K
meta-llama/llama-3.2-1b-instruct$0.02$0.02——131K
paddlepaddle/paddleocr-vl$0.02$0.02——16.4K
deepseek/deepseek-ocr$0.03$0.03——8.2K
deepseek/deepseek-ocr-2$0.03$0.03——8.2K
meta-llama/llama-3.2-3b-instruct$0.03$0.05——32.8K
qwen/qwen3-4b-fp8$0.03$0.03——128K
qwen/qwen3-8b-fp8$0.035$0.138——128K
zai-org/autoglm-phone-9b-multilingual$0.035$0.138——65.5K
meta-llama/llama-3-8b-instruct$0.04$0.04——8.2K
mistralai/mistral-nemo$0.04$0.17——60.3K
openai/gpt-oss-20b$0.04$0.15——131.1K
Sao10K/L3-8B-Stheno-v3.2$0.05$0.05——8.2K
google/gemma-3-12b-it$0.05$0.10——131.1K
nvidia/nemotron-3-nano-30b-a3b$0.05$0.20——262.1K
openai/gpt-oss-120b$0.05$0.25——131.1K
sao10k/l3-8b-lunaris$0.05$0.05——8.2K
deepseek/deepseek-r1-0528-qwen3-8b$0.06$0.09——128K
inclusionai/ling-3.0-flash$0.06$0.18$0.012—262.1K
inclusionai/ling-3.0-flash-fast$0.06$0.18$0.012—262.1K
baichuan/baichuan-m2-32b$0.07$0.07——131.1K
baidu/ernie-4.5-21B-a3b$0.07$0.28——120K
baidu/ernie-4.5-21B-a3b-thinking$0.07$0.28——131.1K
qwen/qwen2.5-7b-instruct$0.07$0.07——32K
qwen/qwen3-coder-30b-a3b-instruct$0.07$0.27——160K
zai-org/glm-4.7-flash$0.07$0.40$0.01—200K
qwen/qwen3-vl-8b-instruct$0.08$0.50——131.1K
gryphe/mythomax-l2-13b$0.09$0.09——4.1K
qwen/qwen3-235b-a22b-instruct-2507$0.09$0.58——131.1K
qwen/qwen3-30b-a3b-fp8$0.09$0.45——41K
qwen/qwen3-32b-fp8$0.10$0.45——41K
xiaomimimo/mimo-v2-flash$0.11$0.33$0.024—262.1K
google/gemma-3-27b-it$0.119$0.20——98.3K
google/gemma-4-26b-a4b-it$0.13$0.40——262.1K
zai-org/glm-4.5-air$0.13$0.85$0.025—131.1K
meta-llama/llama-3.3-70b-instruct$0.135$0.40——12.3K
baidu/ernie-4.5-vl-28b-a3b$0.14$0.56——30K
deepseek/deepseek-v4-flash$0.14$0.28$0.028—1M
google/gemma-4-31b-it$0.14$0.40——262.1K
nousresearch/hermes-2-pro-llama-3-8b$0.14$0.14——8.2K
tencent/hy3$0.14$0.58$0.035—262.1K
deepseek/deepseek-r1-distill-qwen-14b$0.15$0.15——32.8K
qwen/qwen3-next-80b-a3b-instruct$0.15$1.50——131.1K
qwen/qwen3-next-80b-a3b-thinking$0.15$1.50——131.1K
xiaomimimo/mimo-v2.5$0.168$0.336$0.0034—1M
meta-llama/llama-4-scout-17b-16e-instruct$0.18$0.59——131.1K
qwen/qwen3-235b-a22b-fp8$0.20$0.80——41K
qwen/qwen3-coder-next$0.20$1.50——262.1K
qwen/qwen3-vl-30b-a3b-instruct$0.20$0.70——131.1K
qwen/qwen3-vl-30b-a3b-thinking$0.20$1.00——131.1K
skywork/r1v4-lite$0.20$0.60——262.1K
stepfun/step-3.7-flash$0.20$1.15$0.04—262.1K
qwen/qwen3.6-35b-a3b$0.248$1.485——262.1K
qwen/qwen-mt-plus$0.25$0.75——16.4K
qwen/qwen3-omni-30b-a3b-instruct$0.25$0.97——65.5K
qwen/qwen3-omni-30b-a3b-thinking$0.25$0.97——65.5K
qwen/qwen3.5-35b-a3b$0.25$2.00——262.1K
deepseek/deepseek-v3.2$0.269$0.40$0.1345—163.8K
deepseek/deepseek-v3-0324$0.27$1.12$0.135—163.8K
deepseek/deepseek-v3.1$0.27$1.00$0.135—131.1K
deepseek/deepseek-v3.1-terminus$0.27$1.00$0.135—131.1K
deepseek/deepseek-v3.2-exp$0.27$0.41——163.8K
meta-llama/llama-4-maverick-17b-128e-instruct-fp8$0.27$0.85——1M
baidu/cobuddy$0.28$1.13$0.07—131.1K
baidu/ernie-4.5-300b-a47b-paddle$0.28$1.10——123K
deepseek/deepseek-r1-distill-qwen-32b$0.30$0.30——64K
kwaipilot/kat-coder-pro$0.30$1.20$0.06—256K
minimax/minimax-m2$0.30$1.20$0.03—204.8K
minimax/minimax-m2.1$0.30$1.20$0.03—204.8K
minimax/minimax-m2.5$0.30$1.20$0.03—204.8K
minimax/minimax-m2.7$0.30$1.20$0.06—204.8K
minimax/minimax-m3$0.30$1.20$0.06—1M
qwen/qwen3-235b-a22b-thinking-2507$0.30$3.00——131.1K
qwen/qwen3-vl-235b-a22b-instruct$0.30$1.50——131.1K
qwen/qwen3.5-27b$0.30$2.40——262.1K
zai-org/glm-4.6v$0.30$0.90$0.055—131.1K
qwen/qwen-2.5-72b-instruct$0.38$0.40——32K
qwen/qwen3-coder-480b-a35b-instruct$0.38$1.55——262.1K
baidu/ernie-4.5-vl-28b-a3b-thinking$0.39$0.39——131.1K
deepseek/deepseek-v3-turbo$0.40$1.30——64K
qwen/qwen3.5-122b-a10b$0.40$3.20——262.1K
baidu/ernie-4.5-vl-424b-a47b$0.42$1.25——123K
deepseek/deepseek-v4-flash-0731$0.44$1.32$0.028—1M
deepseek/deepseek-v4-flash-vision-exp$0.44$1.32$0.028—1M
mindai/macaron-v1-tall$0.45$2.60$0.08—262.1K
meta-llama/llama-3-70b-instruct$0.51$0.74——8.2K
xiaomimimo/mimo-v2.5-pro$0.522$1.044$0.0043—1M
minimaxai/minimax-m1-80k$0.55$2.20——1M
thudm/glm-4-32b-0414$0.55$1.66——32K
zai-org/glm-4.6$0.55$2.20$0.11—204.8K
moonshotai/kimi-k2-instruct$0.57$2.30——131.1K
minimax/minimax-m2.5-highspeed$0.60$2.40$0.03—204.8K
minimax/minimax-m2.7-highspeed$0.60$2.40$0.06—204.8K
moonshotai/kimi-k2-0905$0.60$2.50——262.1K
moonshotai/kimi-k2-thinking$0.60$2.50$0.15—262.1K
moonshotai/kimi-k2.5$0.60$3.00$0.10—262.1K
qwen/qwen3.5-397b-a17b$0.60$3.60——262.1K
qwen/qwen3.6-27b$0.60$3.60——262.1K
zai-org/glm-4.5$0.60$2.20$0.11—131.1K
zai-org/glm-4.5v$0.60$1.80$0.11—65.5K
zai-org/glm-4.7$0.60$2.20$0.11—204.8K
zai-org/glm-4.7-h$0.60$2.20$0.11—204.8K
microsoft/wizardlm-2-8x22b$0.62$0.62——65.5K
deepseek/deepseek-prover-v2-671b$0.70$2.50——160K
deepseek/deepseek-r1-0528$0.70$2.50$0.35—163.8K
deepseek/deepseek-r1-turbo$0.70$2.50——64K
deepseek/deepseek-r1-distill-llama-70b$0.80$0.80——8.2K
moonshotai/kimi-k2.6$0.80$3.40$0.16—262.1K
qwen/qwen2.5-vl-72b-instruct$0.80$0.80——32.8K
deepseek/deepseek-v3/community$0.89$0.89——64K
deepseek/deepseek_v3$0.89$0.89——64K
moonshotai/kimi-k2.7-code$0.95$4.00$0.19—262.1K
qwen/qwen3-vl-235b-a22b-thinking$0.98$3.95——131.1K
zai-org/glm-5$1.00$3.20$0.20—202.8K
zai-org/glm-5-turbo$1.20$4.00$0.24—202.8K
zai-org/glm-5v-turbo$1.20$4.00$0.24—204.8K
qwen/qwen3.7-max$1.25$3.75$0.25—1M
deepseek/deepseek-v4-pro-0813$1.32$3.96$0.132—1M
zai-org/glm-5.1$1.38$4.40$0.26—204.8K
zai-org/glm-5.2$1.40$4.40$0.26—1M
zai-org/glm-5.3$1.40$4.40$0.26—1M
sao10k/l3-70b-euryale-v2.1$1.48$1.48——8.2K
sao10k/l31-70b-euryale-v2.2$1.48$1.48——8.2K
mindai/macaron-v1-venti$1.50$4.50$0.30—1M
deepseek/deepseek-v4-pro$1.60$3.20$0.135—1M
qwen/qwen3.8-max$2.00$6.00$0.25—1M
qwen/qwen3-max$2.11$8.45——262.1K
moonshotai/kimi-k3$3.00$15.00$0.30—1M
deepseek/deepseek-r1$4.00$4.00——64K
deepseek/deepseek-r1/community$4.00$4.00——64K

Embeddings 3 models

ModelPriceStatus
baai/bge-m3$0.01 per 1M tokens
qwen/qwen3-embedding-0.6b$0.07 per 1M tokens
qwen/qwen3-embedding-8b$0.07 per 1M tokens

Rerank 2 models

ModelPriceStatus
baai/bge-reranker-v2-m3$0.01 in · $0.01 out per 1M
qwen/qwen3-reranker-8b$0.05 in · $0.05 out per 1M