Noryva — Model APIs for coding, images and video

Models & pricing

GLM-5.3

Zhipu / Z.ai

Planned

Input: $1.40
Output: $4.40

USD · per 1M tokensDetails

Cached input: $0.26 per 1M tokens. Standard pay-as-you-go API prices; Coding Plan subscriptions are separate.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Z.ai · international ↗

Noryva price

Sign in for pricing

GLM-5.2

Zhipu / Z.ai

Planned

Input: $1.40
Output: $4.40

USD · per 1M tokensDetails

Cached input: $0.26 per 1M tokens. Standard pay-as-you-go API prices; Coding Plan subscriptions are separate.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Z.ai · international ↗

Noryva price

Sign in for pricing

Kimi K3

Moonshot AI

Planned

Input: $3.00
Output: $15.00

USD · per 1M tokensDetails

Cached input: $0.30 per 1M tokens. International API rate card in USD.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Kimi · international ↗

Noryva price

Sign in for pricing

Qwen3.8 Max

Alibaba Cloud

Planned

Input: $2.00
Output: $6.00

USD · per 1M tokensDetails

Singapore / International deployment, up to 1M input tokens per request. Standard input excludes caching discounts. Other deployment regions have different rates.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

Qwen3.8 Flash

Alibaba Cloud

Planned

Input: $0.15
Output: $0.47

USD · per 1M tokensDetails

Singapore / International deployment, up to 1M input tokens per request. Standard input excludes caching discounts. Other deployment regions have different rates.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

Qwen3.8 2.4T-A95B

Alibaba Cloud

Planned

Input: $2.00
Output: $6.00

USD · per 1M tokensDetails

Singapore / International deployment, up to 1M input tokens per request. API model: qwen3.8-2.4t-a95b.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

Qwen3.8 27B

Alibaba Cloud

Planned

Input: $0.50
Output: $3.00

USD · per 1M tokensDetails

Singapore / International deployment, up to 1M input tokens per request. API model: qwen3.8-27b.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

DeepSeek V4 Pro

DeepSeek

Planned

Input: $0.66–1.32
Output: $1.98–3.96

USD · per 1M tokensDetails

Cached input: $0.022–0.044 per 1M tokens. Ranges show off-peak to peak pricing. Peak: Monday–Friday, 01:00–04:00 and 06:00–10:00 UTC; all other hours are off-peak. Uncached input shown above.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

DeepSeek · direct API ↗

Noryva price

Sign in for pricing

DeepSeek V4 Flash

DeepSeek

Planned

Input: $0.22–0.44
Output: $0.66–1.32

USD · per 1M tokensDetails

Cached input: $0.007–0.014 per 1M tokens. Ranges show off-peak to peak pricing. Peak: Monday–Friday, 01:00–04:00 and 06:00–10:00 UTC; all other hours are off-peak. Uncached input shown above.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

DeepSeek · direct API ↗

Noryva price

Sign in for pricing

Hy4 preview

Tencent Hunyuan

Planned

Input: CNY 6.00
Output: CNY 18.00

per 1M tokensDetails

Cached input: CNY 0.30 per 1M tokens. Guangzhou online inference rate card. Preview model; prices are in Chinese yuan and have not been converted to USD.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Tencent Cloud · Guangzhou ↗

Noryva price

Sign in for pricing

Seedance 2.5

ByteDance

Planned

No video input: CNY 70
With video input: CNY 42

per 1M video tokensDetails

480p / 720p online inference. 1080p list rates: CNY 77 / 46 per 1M video tokens (without / with video input). A 28% discount applies to 1080p until 17 Sep 2026, 14:00 UTC+8. Video input affects billable usage and minimum charges; these are not per-second prices.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Volcengine · China ↗

Noryva price

Sign in for pricing

Seedance 2.0

ByteDance

Planned

No video input: CNY 46
With video input: CNY 28

per 1M video tokensDetails

480p / 720p online inference. 1080p: CNY 51 / 31 per 1M video tokens; 4K: CNY 26 / 16 (without / with video input). Different resolutions consume different token quantities; a lower token rate does not imply a cheaper video. Video-input minimum charges apply.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Volcengine · China ↗

Noryva price

Sign in for pricing

Wan 3.0

Alibaba Cloud

Planned

480p: $0.05
720p: $0.10
1080p: $0.20

USD · per billable second · list priceDetails

Singapore / International deployment. Billable seconds include input video plus successfully generated output. Standard list prices shown; the official page currently advertises a temporary 30% discount. Check the source for its current terms.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

Wan 3.0 Prime

Alibaba Cloud

Planned

480p: $0.068
720p: $0.14
1080p: $0.28

USD · per billable secondDetails

Singapore / International deployment. Billable seconds include input video plus successfully generated output.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Alibaba Cloud · Singapore / International ↗

Noryva price

Sign in for pricing

Kling 3.0

Kuaishou / Kling

Version to confirm

720p: $0.084
1080p: $0.112
4K: $0.42

USD · per second · no native audioDetails

Reference configuration: Kling 3.0 without native audio. Audio and motion-control modes have different rates. The planned Noryva integration version is not yet confirmed. Developer API pricing is separate from consumer memberships.

Reference checked 05 Sep 2026. Planned for Noryva; availability unconfirmed.

Kling · global developer API ↗

Noryva price

Sign in for pricing

Coding and creative workflows.

Only show active models in the picker.

lib/models.js

AssistantComplete

Filter the list before creating the options.

models.jsJavaScript

const options = models
  .filter(({ active }) => active)
  .map(({ id }) => ({ label: id, value: id }));

Inactive models are excluded.

Ask a follow-up…

Coding assistants & agents

Image & video workflows

Cloud supply
at negotiated rates.

AWS
Google Cloud
Microsoft Azure
Volcengine
Tencent Cloud
Alibaba Cloud

Supply details

Our cloud supply partners include AWS, Google Cloud, Microsoft Azure, Volcengine, Tencent Cloud and Alibaba Cloud. Model availability, processing regions and retention terms depend on the selected service and route.

OpenAI-compatible text APIs.

curl "$NORYVA_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $NORYVA_API_KEY" \
  -H "Content-Type: application/json" \
  --data @- <<JSON
{
    "model": "$NORYVA_MODEL",
    "messages": [{"role": "user", "content": "Write a Python function to deduplicate a list."}],
    "stream": true
}
JSON

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["NORYVA_BASE_URL"],
    api_key=os.environ["NORYVA_API_KEY"],
)

stream = client.chat.completions.create(
    model=os.environ["NORYVA_MODEL"],
    messages=[{"role": "user", "content": "Write a Python function to deduplicate a list."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: process.env.NORYVA_BASE_URL,
  apiKey: process.env.NORYVA_API_KEY,
});

const stream = await client.chat.completions.create({
  model: process.env.NORYVA_MODEL,
  messages: [{ role: "user", content: "Write a Python function to deduplicate a list." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Connection settings

Set NORYVA_BASE_URL to your console's API base URL, including /v1 without a trailing slash; NORYVA_API_KEY to your key; and NORYVA_MODEL to a supported text model ID.

Python and JavaScript use the OpenAI SDK. Image and video models have separate parameters and may use asynchronous tasks.

One account for your model APIs.

Models & pricing

GLM-5.3

GLM-5.2

Kimi K3

Qwen3.8 Max

Qwen3.8 Flash

Qwen3.8 2.4T-A95B

Qwen3.8 27B

DeepSeek V4 Pro

DeepSeek V4 Flash

Hy4 preview

Seedance 2.5

Seedance 2.0

Wan 3.0

Wan 3.0 Prime

Kling 3.0

Coding and creative workflows.

Coding assistants & agents

Image & video workflows

Cloud supply
at negotiated rates.

OpenAI-compatible text APIs.

Start with an API key.

Noryva: Powerful models. Create more. Spend less.

One account for your model APIs.

Models & pricing

Coding & text

GLM-5.3

GLM-5.2

Kimi K3

Qwen3.8 Max

Qwen3.8 Flash

Qwen3.8 2.4T-A95B

Qwen3.8 27B

DeepSeek V4 Pro

DeepSeek V4 Flash

Hy4 preview

Video generation

Seedance 2.5

Seedance 2.0

Wan 3.0

Wan 3.0 Prime

Kling 3.0

Coding and creative workflows.

Coding assistants & agents

Image & video workflows

Cloud supplyat negotiated rates.

OpenAI-compatible text APIs.

Start with an API key.

Cloud supply
at negotiated rates.