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.
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.
Model family: — · Model catalog only; see service-channel quotes
Platform directory entry. Prices and context depend on the selected model; no platform-wide token rate or context limit is assigned.
Requires a Novita AI account and API key.
Official source · Last verified: 2026-10-15T06:57:32.742Z
Official model ID: zai-org/glm-5.3-flash
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.15 |
| Output | USD 0.5 |
| Cached read | USD 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 Unpublished cache write and storage charges remain unknown.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
Input / output modalities: text, image, video → text
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
Official model ID: xiaomimimo/mimo-v2.6-flash
Model developer: Xiaomi · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.14 |
| Output | USD 0.28 |
| Cached read | USD 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 Unpublished cache write and storage charges remain unknown.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
Input / output modalities: text, image, video, audio → text
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
Official model ID: xiaomimimo/mimo-v2.6-pro
Model developer: Xiaomi · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.435 |
| Output | USD 0.87 |
| Cached read | USD 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 Unpublished cache write and storage charges remain unknown.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
Input / output modalities: text, image, video, audio → text
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
Official model ID: tencent/hy4-preview
Model developer: Tencent · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.834 |
| Output | USD 2.501 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: deepseek/deepseek-v4.1-flash
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 1.2 |
| Cached read | USD 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
Input / output modalities: text, image → text
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
Official model ID: zai-org/glm-5.3
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.4 |
| Output | USD 4.4 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: deepseek/deepseek-v4-pro-0813
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.32 |
| Output | USD 3.96 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: moonshotai/kimi-k3
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 3 |
| Output | USD 15 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: tencent/hy3
Model developer: Tencent · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.14 |
| Output | USD 0.58 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-5.2
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.4 |
| Output | USD 4.4 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: moonshotai/kimi-k2.7-code
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.95 |
| Output | USD 4 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: qwen/qwen3.8-flash
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.15 |
| Output | USD 0.47 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: deepseek/deepseek-v4-flash-0731
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.44 |
| Output | USD 1.32 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: mindai/macaron-v1-venti
Model developer: Mind Lab · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.825 |
| Output | USD 2.475 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: minimax/minimax-m3
Model developer: MiniMax · Service provider: Self-hosted · 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.
Model context: 1,000,000 tokens
Maximum output: 131,072 tokens
Input / output modalities: text, image, video → text
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
Official model ID: deepseek/deepseek-v4-pro
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.6 |
| Output | USD 3.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: apodex/apodex-1.1-mini
Model developer: Apodex · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0 |
| Output | USD 0 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: stepfun/step-5-preview
Model developer: StepFun · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1 |
| Output | USD 2.7 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: inclusionai/ling-3.1-flash
Model developer: inclusionAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 0.9 |
| Cached read | USD 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: 262,144 tokens
Maximum output: 262,144 tokens
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.8-27b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.42 |
| Output | USD 3 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: inclusionai/ling-3.0-flash-fin
Model developer: inclusionAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.075 |
| Output | USD 0.22 |
| Cached read | USD 0.015 |
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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.8-2.4t-a95b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 2 |
| Output | USD 6 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.8-max
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 2 |
| Output | USD 6 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: inclusionai/ling-3.0-flash
Model developer: inclusionAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.06 |
| Output | USD 0.18 |
| Cached read | USD 0.012 |
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
Input / output modalities: text → text
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
Official model ID: mindai/macaron-v1-tall
Model developer: Mind Lab · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.2475 |
| Output | USD 1.43 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: stepfun/step-3.7-flash
Model developer: StepFun · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.2 |
| Output | USD 1.15 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: nvidia/nemotron-3-nano-30b-a3b
Model developer: NVIDIA · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.05 |
| Output | USD 0.2 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: baidu/cobuddy
Model developer: Baidu · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.28 |
| Output | USD 1.13 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.7-max
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.25 |
| Output | USD 3.75 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.6-27b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 3.6 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: moonshotai/kimi-k2.6
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.8 |
| Output | USD 3.4 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: zai-org/glm-5.1
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1.38 |
| Output | USD 4.4 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: google/gemma-4-26b-a4b-it
Model developer: Google · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.13 |
| Output | USD 0.4 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: google/gemma-4-31b-it
Model developer: Google · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.14 |
| Output | USD 0.4 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: minimax/minimax-m2.7
Model developer: MiniMax · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 1.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.5-27b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 2.4 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: qwen/qwen3.5-122b-a10b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.4 |
| Output | USD 3.2 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: qwen/qwen3.5-35b-a3b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.25 |
| Output | USD 2 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: qwen/qwen3.5-397b-a17b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 3.6 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: minimax/minimax-m2.5
Model developer: MiniMax · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 1.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-5
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 1 |
| Output | USD 3.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: deepseek/deepseek-ocr-2
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.03 |
| Output | USD 0.03 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: moonshotai/kimi-k2.5
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 3 |
| Cached read | USD 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
Input / output modalities: text, image, video → text
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
Official model ID: zai-org/glm-4.7-flash
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.07 |
| Output | USD 0.4 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-4.7
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 2.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: zai-org/autoglm-phone-9b-multilingual
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.035 |
| Output | USD 0.138 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: moonshotai/kimi-k2-thinking
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 2.5 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-4.6v
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.3 |
| Output | USD 0.9 |
| Cached read | USD 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
Input / output modalities: text, video, image → text
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
Official model ID: zai-org/glm-4.6
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.55 |
| Output | USD 2.2 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3.6-35b-a3b
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.248 |
| Output | USD 1.485 |
| Cached read | Unverified |
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
Input / output modalities: text, image, video → text
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
Official model ID: moonshotai/kimi-k2-0905
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 2.5 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: openai/gpt-oss-120b
Model developer: OpenAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.05 |
| Output | USD 0.25 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: moonshotai/kimi-k2-instruct
Model developer: Moonshot AI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.57 |
| Output | USD 2.3 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: meta-llama/llama-3.1-8b-instruct
Model developer: Meta · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.02 |
| Output | USD 0.05 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-4.5v
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.6 |
| Output | USD 1.8 |
| Cached read | USD 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
Input / output modalities: text, video, image → text
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
Official model ID: meta-llama/llama-3.3-70b-instruct
Model developer: Meta · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.135 |
| Output | USD 0.4 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: minimaxai/minimax-m1-80k
Model developer: MiniMax · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.55 |
| Output | USD 2.2 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: deepseek/deepseek-r1-0528
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.7 |
| Output | USD 2.5 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: microsoft/wizardlm-2-8x22b
Model developer: Microsoft · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.62 |
| Output | USD 0.62 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Model developer: Meta · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.27 |
| Output | USD 0.85 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: meta-llama/llama-4-scout-17b-16e-instruct
Model developer: Meta · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.18 |
| Output | USD 0.59 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: google/gemma-3-27b-it
Model developer: Google · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.119 |
| Output | USD 0.2 |
| Cached read | Unverified |
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
Input / output modalities: text, image → text
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
Official model ID: deepseek/deepseek-r1-turbo
Model developer: DeepSeek · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.7 |
| Output | USD 2.5 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: Sao10K/L3-8B-Stheno-v3.2
Model developer: Sao10K · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.05 |
| Output | USD 0.05 |
| Cached read | Unverified |
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: 32,000 tokens
Input / output modalities: text → text
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
Official model ID: inclusionai/ling-3.0-flash-vl
Model developer: inclusionAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.075 |
| Output | USD 0.22 |
| Cached read | USD 0.015 |
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
Input / output modalities: text, image, video → text
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
Official model ID: inclusionai/ling-3.0-flash-sante
Model developer: inclusionAI · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.075 |
| Output | USD 0.22 |
| Cached read | USD 0.015 |
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
Input / output modalities: text → text
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
Official model ID: zai-org/glm-4.5-air
Model developer: Z.ai · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.13 |
| Output | USD 0.85 |
| Cached read | USD 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
Input / output modalities: text → text
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
Official model ID: qwen/qwen3-vl-30b-a3b-instruct
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.2 |
| Output | USD 0.7 |
| Cached read | Unverified |
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
Input / output modalities: text, video, image → text
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
Official model ID: qwen/qwen3-omni-30b-a3b-thinking
Model developer: Alibaba (Qwen) · Service provider: Self-hosted · 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.
Model context: 65,536 tokens
Maximum output: 16,384 tokens
Input / output modalities: text, audio, video, image → text
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
Official model ID: qwen/qwen-mt-plus
Model developer: Alibaba (Qwen) · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.25 |
| Output | USD 0.75 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
Official model ID: baidu/ernie-4.5-21B-a3b
Model developer: Baidu · Service provider: Novita AI · Market: com
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.07 |
| Output | USD 0.28 |
| Cached read | Unverified |
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
Input / output modalities: text → text
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
The AI advisor considers your budget, tools, usage and purchase conditions to suggest primary and backup options.
Open AI advisor →