Novita AI API models & prices

Novita AI Verified 29 days ago · 2026-10-15 API platform

1 plan

Novita AI provides multi-model inference APIs billed in USD by model and usage. Dedicated Endpoints, Agent Sandbox and GPU resources have separate resource-based billing.

Found a data issue? Report it·Reports go through manual verification and never change published prices directly.·Claim this product

All plans · 1

API models and prices · 71

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

GLM 5.3 Flash

Official model ID: zai-org/glm-5.3-flash

Input / output: text, image, video → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.15
OutputUSD 0.5
Cached readUSD 0.03

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiMo V2.6 Flash

Official model ID: xiaomimimo/mimo-v2.6-flash

Input / output: text, image, video, audio → text

Model developer: Xiaomi · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.14
OutputUSD 0.28
Cached readUSD 0.0028

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiMo V2.6 Pro

Official model ID: xiaomimimo/mimo-v2.6-pro

Input / output: text, image, video, audio → text

Model developer: Xiaomi · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.435
OutputUSD 0.87
Cached readUSD 0.0036

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Hy4 Preview

Official model ID: tencent/hy4-preview

Input / output: text → text

Model developer: Tencent · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.834
OutputUSD 2.501
Cached readUSD 0.042

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 64,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek V4.1 Flash

Official model ID: deepseek/deepseek-v4.1-flash

Input / output: text, image → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 1.2
Cached readUSD 0.006

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 393,216 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 5.3

Official model ID: zai-org/glm-5.3

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.4
OutputUSD 4.4
Cached readUSD 0.26

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek V4 Pro 0813

Official model ID: deepseek/deepseek-v4-pro-0813

Input / output: text → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.32
OutputUSD 3.96
Cached readUSD 0.044

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 393,216 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K3

Official model ID: moonshotai/kimi-k3

Input / output: text, image, video → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 3
OutputUSD 15
Cached readUSD 0.3

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 1,048,576 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Hy3

Official model ID: tencent/hy3

Input / output: text → text

Model developer: Tencent · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.14
OutputUSD 0.58
Cached readUSD 0.035

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 5.2

Official model ID: zai-org/glm-5.2

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.4
OutputUSD 4.4
Cached readUSD 0.26

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2.7 Code

Official model ID: moonshotai/kimi-k2.7-code

Input / output: text, image, video → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.95
OutputUSD 4
Cached readUSD 0.19

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.8 Flash

Official model ID: qwen/qwen3.8-flash

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.15
OutputUSD 0.47
Cached readUSD 0.016

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek V4 Flash 0731

Official model ID: deepseek/deepseek-v4-flash-0731

Input / output: text → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.44
OutputUSD 1.32
Cached readUSD 0.028

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 393,216 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Macaron V1 Venti

Official model ID: mindai/macaron-v1-venti

Input / output: text → text

Model developer: Mind Lab · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.825
OutputUSD 2.475
Cached readUSD 0.165

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiniMax M3

Official model ID: minimax/minimax-m3

Input / output: text, image, video → text

Model developer: MiniMax · Service provider: Novita AI · Market: com

Model family: — · Model catalog only; see service-channel quotes

MiniMax M3 uses input-length tiers: 1–524,288 tokens costs $0.30/$1.20/$0.06 for input/output/cache read; 524,288–1,000,000 costs $0.60/$2.40/$0.12 per million tokens. Tier boundaries follow the official model page; no flat rate is assigned.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek V4 Pro

Official model ID: deepseek/deepseek-v4-pro

Input / output: text → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.6
OutputUSD 3.2
Cached readUSD 0.135

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 393,216 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Apodex 1.1 Mini

Official model ID: apodex/apodex-1.1-mini

Input / output: text → text

Model developer: Apodex · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0
OutputUSD 0
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately. The current pricing page marks this model Free; this does not imply platform-wide or permanent free access.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Step 5 Preview

Official model ID: stepfun/step-5-preview

Input / output: text, image, video → text

Model developer: StepFun · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1
OutputUSD 2.7
Cached readUSD 0.1

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 64,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Ling 3.1 Flash

Official model ID: inclusionai/ling-3.1-flash

Input / output: text → text

Model developer: inclusionAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 0.9
Cached readUSD 0.06
Capabilities, license and channel status
Developer
InclusionAI
Model type
Language model
Input
Text
Output
Text
Tool calls
Confirmed
Structured output
Unverified
Official model ID
inclusionai/ling-3.1-flash
Version
Unverified
Release date
Unverified
License
Unverified
Total parameters
Unverified
Active parameters
Unverified
Open weights
Unverified
Reasoning
Confirmed
Code generation
Unverified
Agent
Unverified
Status
Current catalog
Metadata checked
2026-10-15T06:57:32.742Z

Model sources: Source 1 · Source 2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.8 27B

Official model ID: qwen/qwen3.8-27b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.42
OutputUSD 3
Cached readUSD 0.085

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Ling 3.0 Flash Fin

Official model ID: inclusionai/ling-3.0-flash-fin

Input / output: text → text

Model developer: inclusionAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.075
OutputUSD 0.22
Cached readUSD 0.015
Capabilities, license and channel status
Developer
InclusionAI
Model type
Language model
Input
Text
Output
Text
Tool calls
Confirmed
Structured output
Unverified
Official model ID
inclusionai/ling-3.0-flash-fin
Version
Unverified
Release date
Unverified
License
Unverified
Total parameters
Unverified
Active parameters
Unverified
Open weights
Unverified
Reasoning
Confirmed
Code generation
Unverified
Agent
Unverified
Status
Current catalog
Metadata checked
2026-10-15T06:57:32.742Z

Model sources: Source 1 · Source 2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.8 2.4T A95B

Official model ID: qwen/qwen3.8-2.4t-a95b

Input / output: text → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 2
OutputUSD 6
Cached readUSD 0.25

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.8 Max

Official model ID: qwen/qwen3.8-max

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 2
OutputUSD 6
Cached readUSD 0.25

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Ling 3.0 Flash

Official model ID: inclusionai/ling-3.0-flash

Input / output: text → text

Model developer: inclusionAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.06
OutputUSD 0.18
Cached readUSD 0.012
Capabilities, license and channel status
Developer
InclusionAI
Model type
Language model
Input
Text
Output
Text
Tool calls
Confirmed
Structured output
Unverified
Official model ID
inclusionai/ling-3.0-flash
Version
Unverified
Release date
Unverified
License
Unverified
Total parameters
Unverified
Active parameters
Unverified
Open weights
Unverified
Reasoning
Confirmed
Code generation
Unverified
Agent
Unverified
Status
Current catalog
Metadata checked
2026-10-15T06:57:32.742Z

Model sources: Source 1 · Source 2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Macaron V1 Tall

Official model ID: mindai/macaron-v1-tall

Input / output: text → text

Model developer: Mind Lab · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.2475
OutputUSD 1.43
Cached readUSD 0.044

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Step 3.7 Flash

Official model ID: stepfun/step-3.7-flash

Input / output: text, image, video → text

Model developer: StepFun · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.2
OutputUSD 1.15
Cached readUSD 0.04

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 256,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

NVIDIA Nemotron 3 Nano 30B A3B

Official model ID: nvidia/nemotron-3-nano-30b-a3b

Input / output: text → text

Model developer: NVIDIA · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.05
OutputUSD 0.2
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

CoBuddy

Official model ID: baidu/cobuddy

Input / output: text → text

Model developer: Baidu · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.28
OutputUSD 1.13
Cached readUSD 0.07

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.7 Max

Official model ID: qwen/qwen3.7-max

Input / output: text → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.25
OutputUSD 3.75
Cached readUSD 0.25

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.6 27B

Official model ID: qwen/qwen3.6-27b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 3.6
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2.6

Official model ID: moonshotai/kimi-k2.6

Input / output: text, image, video → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.8
OutputUSD 3.4
Cached readUSD 0.16

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 5.1

Official model ID: zai-org/glm-5.1

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1.38
OutputUSD 4.4
Cached readUSD 0.26

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 204,800 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Gemma 4 26B A4B

Official model ID: google/gemma-4-26b-a4b-it

Input / output: text, image → text

Model developer: Google · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.13
OutputUSD 0.4
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Gemma 4 31B

Official model ID: google/gemma-4-31b-it

Input / output: text, image → text

Model developer: Google · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.14
OutputUSD 0.4
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiniMax M2.7

Official model ID: minimax/minimax-m2.7

Input / output: text → text

Model developer: MiniMax · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 1.2
Cached readUSD 0.06

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 204,800 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.5 27B

Official model ID: qwen/qwen3.5-27b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 2.4
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.5 122B A10B

Official model ID: qwen/qwen3.5-122b-a10b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.4
OutputUSD 3.2
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.5 35B A3B

Official model ID: qwen/qwen3.5-35b-a3b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.25
OutputUSD 2
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.5 397B A17B

Official model ID: qwen/qwen3.5-397b-a17b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 3.6
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiniMax M2.5

Official model ID: minimax/minimax-m2.5

Input / output: text → text

Model developer: MiniMax · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 1.2
Cached readUSD 0.03

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 204,800 tokens

Maximum output: 131,100 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 5

Official model ID: zai-org/glm-5

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 1
OutputUSD 3.2
Cached readUSD 0.2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 202,800 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek OCR 2

Official model ID: deepseek/deepseek-ocr-2

Input / output: text, image → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.03
OutputUSD 0.03
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 8,192 tokens

Maximum output: 8,192 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2.5

Official model ID: moonshotai/kimi-k2.5

Input / output: text, image, video → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 3
Cached readUSD 0.1

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 262,144 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.7 Flash

Official model ID: zai-org/glm-4.7-flash

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.07
OutputUSD 0.4
Cached readUSD 0.01

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 200,000 tokens

Maximum output: 128,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.7

Official model ID: zai-org/glm-4.7

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 2.2
Cached readUSD 0.11

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 204,800 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

AutoGLM Phone 9B Multilingual

Official model ID: zai-org/autoglm-phone-9b-multilingual

Input / output: text, image → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.035
OutputUSD 0.138
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 65,536 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2 Thinking

Official model ID: moonshotai/kimi-k2-thinking

Input / output: text → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 2.5
Cached readUSD 0.15

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 98,304 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.6V

Official model ID: zai-org/glm-4.6v

Input / output: text, video, image → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.3
OutputUSD 0.9
Cached readUSD 0.055

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.6

Official model ID: zai-org/glm-4.6

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.55
OutputUSD 2.2
Cached readUSD 0.11

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 204,800 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3.6 35B A3B

Official model ID: qwen/qwen3.6-35b-a3b

Input / output: text, image, video → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.248
OutputUSD 1.485
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 65,536 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2 Instruct 0905

Official model ID: moonshotai/kimi-k2-0905

Input / output: text → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 2.5
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 98,304 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

OpenAI GPT OSS 120B

Official model ID: openai/gpt-oss-120b

Input / output: text, image → text

Model developer: OpenAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.05
OutputUSD 0.25
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Kimi K2 Instruct

Official model ID: moonshotai/kimi-k2-instruct

Input / output: text → text

Model developer: Moonshot AI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.57
OutputUSD 2.3
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 98,304 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Llama 3.1 8B Instruct

Official model ID: meta-llama/llama-3.1-8b-instruct

Input / output: text → text

Model developer: Meta · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.02
OutputUSD 0.05
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 16,384 tokens

Maximum output: 16,384 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.5V

Official model ID: zai-org/glm-4.5v

Input / output: text, video, image → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.6
OutputUSD 1.8
Cached readUSD 0.11

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 65,536 tokens

Maximum output: 16,384 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Llama 3.3 70B Instruct

Official model ID: meta-llama/llama-3.3-70b-instruct

Input / output: text → text

Model developer: Meta · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.135
OutputUSD 0.4
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 12,288 tokens

Maximum output: 12,288 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

MiniMax M1

Official model ID: minimaxai/minimax-m1-80k

Input / output: text → text

Model developer: MiniMax · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.55
OutputUSD 2.2
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,000,000 tokens

Maximum output: 40,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek R1 0528

Official model ID: deepseek/deepseek-r1-0528

Input / output: text → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.7
OutputUSD 2.5
Cached readUSD 0.35

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 163,840 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

WizardLM 2 8x22B

Official model ID: microsoft/wizardlm-2-8x22b

Input / output: text → text

Model developer: Microsoft · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.62
OutputUSD 0.62
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 65,535 tokens

Maximum output: 8,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Llama 4 Maverick Instruct

Official model ID: meta-llama/llama-4-maverick-17b-128e-instruct-fp8

Input / output: text, image → text

Model developer: Meta · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.27
OutputUSD 0.85
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 1,048,576 tokens

Maximum output: 8,192 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Llama 4 Scout Instruct

Official model ID: meta-llama/llama-4-scout-17b-16e-instruct

Input / output: text, image → text

Model developer: Meta · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.18
OutputUSD 0.59
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Gemma 3 27B

Official model ID: google/gemma-3-27b-it

Input / output: text, image → text

Model developer: Google · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.119
OutputUSD 0.2
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 98,304 tokens

Maximum output: 16,384 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

DeepSeek R1 Turbo

Official model ID: deepseek/deepseek-r1-turbo

Input / output: text → text

Model developer: DeepSeek · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.7
OutputUSD 2.5
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 64,000 tokens

Maximum output: 16,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Llama 3 8B Stheno V3.2

Official model ID: Sao10K/L3-8B-Stheno-v3.2

Input / output: text → text

Model developer: Sao10K · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.05
OutputUSD 0.05
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 8,192 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Ling 3.0 Flash VL

Official model ID: inclusionai/ling-3.0-flash-vl

Input / output: text, image, video → text

Model developer: inclusionAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.075
OutputUSD 0.22
Cached readUSD 0.015
Capabilities, license and channel status
Developer
InclusionAI
Model type
Language model
Input
Text / Image / Video
Output
Text
Tool calls
Confirmed
Structured output
Unverified
Official model ID
inclusionai/ling-3.0-flash-vl
Version
Unverified
Release date
Unverified
License
Unverified
Total parameters
Unverified
Active parameters
Unverified
Open weights
Unverified
Reasoning
Confirmed
Code generation
Unverified
Agent
Unverified
Status
Current catalog
Metadata checked
2026-10-15T06:57:32.742Z

Model sources: Source 1 · Source 2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Ling 3.0 Flash Sante

Official model ID: inclusionai/ling-3.0-flash-sante

Input / output: text → text

Model developer: inclusionAI · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.075
OutputUSD 0.22
Cached readUSD 0.015
Capabilities, license and channel status
Developer
InclusionAI
Model type
Language model
Input
Text
Output
Text
Tool calls
Confirmed
Structured output
Unverified
Official model ID
inclusionai/ling-3.0-flash-sante
Version
Unverified
Release date
Unverified
License
Unverified
Total parameters
Unverified
Active parameters
Unverified
Open weights
Unverified
Reasoning
Confirmed
Code generation
Unverified
Agent
Unverified
Status
Current catalog
Metadata checked
2026-10-15T06:57:32.742Z

Model sources: Source 1 · Source 2

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 262,144 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

GLM 4.5 Air

Official model ID: zai-org/glm-4.5-air

Input / output: text → text

Model developer: Z.ai · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.13
OutputUSD 0.85
Cached readUSD 0.025

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 98,304 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3 VL 30B A3B Instruct

Official model ID: qwen/qwen3-vl-30b-a3b-instruct

Input / output: text, video, image → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.2
OutputUSD 0.7
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 131,072 tokens

Maximum output: 32,768 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen3 Omni 30B A3B Thinking

Official model ID: qwen/qwen3-omni-30b-a3b-thinking

Input / output: text, audio, video, image → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Model catalog only; see service-channel quotes

Qwen3 Omni has modality-specific input and output pricing. The pricing page labels it Omnimodal; no single token rate or free usage is implied. See the official model page.

Documented API context: 65,536 tokens

Maximum output: 16,384 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Qwen MT Plus

Official model ID: qwen/qwen-mt-plus

Input / output: text → text

Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.25
OutputUSD 0.75
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 16,384 tokens

Maximum output: 8,192 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

ERNIE 4.5 21B A3B

Official model ID: baidu/ernie-4.5-21B-a3b

Input / output: text → text

Model developer: Baidu · Service provider: Novita AI · Market: com

Model family: — · Currency: USD

Rates per million tokens
Price dimensionCurrent rate
InputUSD 0.07
OutputUSD 0.28
Cached readUnverified

Novita AI inference rates in USD per million tokens. Unpublished cache write and storage charges remain unknown. The model developer and inference provider are recorded separately.

Documented API context: 120,000 tokens

Maximum output: 8,000 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Need a recommendation?

The AI advisor considers your budget, tools, usage and purchase conditions to suggest primary and backup options.

Open AI advisor →