Skip to content
InfratoApp
InfratoApp / LLM prices / Novita AI

Novita AI API pricing

Novita AI has 65 models with a token price on record: input $0.02 to $3.00 and output $0.03 to $15.00 per million tokens at the standard tier. Each rate links to the page it was read from, most recently on 2026-10-22.

Novita AI sells models made by others, so these are what it charges, not the makers' own prices.

Price a workload on these models →Every seller →Novita AI’s own pricing page →

65
models with a price
42
publish a cached rate
○
batch listings
no batch tier on record
2026-10-22
most recent read

Every model Novita AI prices

Novita AI token prices per million tokens, by model and tier, each with the page it was read from
ModelTierInput $/MOutput $/MCached $/MContextRead from
baidu/cobuddyStandard$0.28$1.13$0.07○2026-10-22
baidu/ernie-4.5-21b-a3bStandard$0.07$0.28○○2026-10-22
deepseek/deepseek-ocr-2Standard$0.03$0.03○○2026-10-22
deepseek/deepseek-r1-0528Standard$0.70$2.50$0.35164K2026-10-22
deepseek/deepseek-r1-turboStandard$0.70$2.50○○2026-10-22
deepseek/deepseek-v4-flash-0731Standard$0.44$1.32$0.0281M2026-10-22
deepseek/deepseek-v4-proStandard$1.60$3.20$0.1351M2026-10-22
deepseek/deepseek-v4-pro-0813Standard$1.32$3.96$0.0441M2026-10-22
deepseek/deepseek-v4.1-flashStandard$0.30$1.20$0.0061M2026-10-22
deepseek/deepseek-v4.1-flash-1017Standard$0.30$1.20$0.0061M2026-10-22
google/gemma-3-27bStandard$0.119$0.20○○2026-10-22
google/gemma-4-26b-a4bStandard$0.13$0.40○○2026-10-22
google/gemma-4-31bStandard$0.14$0.40○○2026-10-22
inclusionai/ling-3.0-flashStandard$0.06$0.18$0.012262K2026-10-22
inclusionai/ling-3.0-flash-finStandard$0.075$0.22$0.015262K2026-10-22
inclusionai/ling-3.0-flash-vlStandard$0.075$0.22$0.015131K2026-10-22
inclusionai/ling-3.1-flashStandard$0.30$0.90$0.06262K2026-10-22
meta-llama/llama-3.1-8b-instructStandard$0.02$0.05○131K2026-10-22
meta-llama/llama-3.3-70b-instructStandard$0.135$0.40○131K2026-10-22
meta/llama-4-maverick-instructStandard$0.27$0.85○○2026-10-22
meta/llama-4-scout-instructStandard$0.18$0.59○○2026-10-22
microsoft/wizardlm-2-8x22bStandard$0.62$0.62○66K2026-10-22
minimax/minimax-m1Standard$0.55$2.20○1M2026-10-22
minimax/minimax-m2.5Standard$0.30$1.20$0.03205K2026-10-22
minimax/minimax-m2.7Standard$0.30$1.20$0.06205K2026-10-22
moonshotai/kimi-k2-thinkingStandard$0.60$2.50$0.15262K2026-10-22
moonshotai/kimi-k2.5Standard$0.60$3.00$0.10262K2026-10-22
moonshotai/kimi-k2.6Standard$0.80$3.40$0.16262K2026-10-22
moonshotai/kimi-k2.7-codeStandard$0.95$4.00$0.19262K2026-10-22
moonshotai/kimi-k3Standard$3.00$15.00$0.301M2026-10-22
nvidia/nemotron-3-nano-30b-a3bStandard$0.05$0.20○262K2026-10-22
openai/gpt-oss-120bStandard$0.05$0.25○131K2026-10-22
qwen/qwen3-vl-30b-a3b-instructStandard$0.20$0.70○262K2026-10-22
qwen/qwen3.5-122b-a10bStandard$0.40$3.20○262K2026-10-22
qwen/qwen3.5-27bStandard$0.30$2.40○262K2026-10-22
qwen/qwen3.5-35b-a3bStandard$0.25$2.00○262K2026-10-22
qwen/qwen3.5-397b-a17bStandard$0.60$3.60○262K2026-10-22
qwen/qwen3.6-27bStandard$0.60$3.60○262K2026-10-22
qwen/qwen3.6-35b-a3bStandard$0.248$1.485○262K2026-10-22
qwen/qwen3.7-maxStandard$1.25$3.75$0.251M2026-10-22
qwen/qwen3.8-2.4t-a95bStandard$2.00$6.00$0.251M2026-10-22
qwen/qwen3.8-27bStandard$0.42$3.00$0.0851M2026-10-22
qwen/qwen3.8-flashStandard$0.15$0.47$0.0161M2026-10-22
qwen/qwen3.8-maxStandard$2.00$6.00$0.25○2026-10-22
sao10k/llama-3-8b-stheno-v3.2Standard$0.05$0.05○○2026-10-22
stepfun/step-3.7-flashStandard$0.20$1.15$0.04262K2026-10-22
stepfun/step-5-previewStandard$1.00$2.70$0.101M2026-10-22
tencent/hy3Standard$0.14$0.58$0.035262K2026-10-22
tencent/hy4-previewStandard$0.834$2.501$0.0421M2026-10-22
xiaomi/mimo-v2.5Standard$0.168$0.336$0.00341.1M2026-10-22
xiaomi/mimo-v2.5-proStandard$0.522$1.044$0.00431.1M2026-10-22
xiaomi/mimo-v2.6-flashStandard$0.14$0.28$0.00281.1M2026-10-22
xiaomi/mimo-v2.6-proStandard$0.435$0.87$0.00361.1M2026-10-22
z-ai/autoglm-phone-9b-multilingualStandard$0.035$0.138○○2026-10-22
z-ai/glm-4.5-airStandard$0.13$0.85$0.025131K2026-10-22
z-ai/glm-4.5vStandard$0.60$1.80$0.1166K2026-10-22
z-ai/glm-4.6Standard$0.55$2.20$0.11205K2026-10-22
z-ai/glm-4.6vStandard$0.30$0.90$0.055131K2026-10-22
z-ai/glm-4.7Standard$0.60$2.20$0.11205K2026-10-22
z-ai/glm-4.7-flashStandard$0.07$0.40$0.01200K2026-10-22
z-ai/glm-5Standard$1.00$3.20$0.20205K2026-10-22
z-ai/glm-5.1Standard$1.38$4.40$0.26205K2026-10-22
z-ai/glm-5.2Standard$1.40$4.40$0.261M2026-10-22
z-ai/glm-5.3Standard$1.40$4.40$0.261M2026-10-22
z-ai/glm-5.3-flashStandard$0.15$0.50$0.031M2026-10-22

○ means no answer on record, not zero. Rates older than 21 days are hidden rather than shown stale. Input and output are priced separately, so a figure built from input alone is a different, smaller number.

Other sellers

OpenRouter 385Together AI 20Anthropic 19Baseten 16Fireworks AI 13OpenAI 13Mistral AI 10FriendliAI 7Google DeepMind 7SambaNova 6Moonshot AI 4AI21 Labs 2DeepSeek 2Cerebras Inference 1xAI 1

Frequently asked

How much does the Novita AI API cost per million tokens?
It depends on the model. At the standard tier, input is $0.02 to $3.00 and output is $0.03 to $15.00 per million tokens across 65 models on record. Input and output are priced separately, and every model's rates are in the table above with the page each was read from.
Does Novita AI price cached input or a batch tier?
42 models carry a cached input rate on record. No batch tier is on record. A missing rate means no answer on record, not that none exists.
Where do these Novita AI prices come from?
Each row links to the page it was read from and shows the date it was read. A price older than 21 days is hidden rather than shown stale, and a rate we have not read is left blank rather than estimated.

How these prices are read

Every rate here links to the page it was read from and carries the date it was read. Nothing is averaged or estimated, and a rate we have not read is shown as missing instead of guessed. How any figure is gathered, and what is refused, is on methodology.