# Models
> Source: https://vivgrid.com/docs/models
All AI models supported by Vivgrid — including GPT-5, Claude Opus/Sonnet, Gemini, and DeepSeek variants for coding, text, speech, and multimodal workloads.
Vivgrid provides access to a range of powerful AI models for building enterprise-grade AI agents. We select models based on their performance, cost-effectiveness, and suitability for various tasks. Pricing is transparent and, for most models, matches the rates of the original providers.
## Supported Models
### Coding Models
- [`viv-fast`](/docs/models/viv-fast)
- [`jev-latest`](/docs/models/jev-latest)
- [`gpt-6-astra`](/docs/models/gpt-6-astra)
- [`claude-fable-5-1`](/docs/models/claude-fable-5-1)
- [`deepseek-v4.1-flash`](/docs/models/deepseek-v4.1-flash)
- [`gemini-3.8-flash`](/docs/models/gemini-3.8-flash)
- [`kimi-k2.8-preview`](/docs/models/kimi-k2.8-preview)
- [`claude-fable-5`](/docs/models/claude-fable-5)
- [`deepseek-v4-pro-0813`](/docs/models/deepseek-v4-pro-0813)
- [`glm-5.3-flash`](/docs/models/glm-5.3-flash)
- [`deepseek-v4-flash-vision-exp`](/docs/models/deepseek-v4-flash-vision-exp)
- [`deepseek-v4-flash (0731)`](/docs/models/deepseek-v4-flash)
- [`gemini-3.7-flash`](/docs/models/gemini-3.7-flash)
- [`glm-5.3`](/docs/models/glm-5.3)
- [`gemini-3.6-flash`](/docs/models/gemini-3.6-flash)
- [`claude-opus-5`](/docs/models/claude-opus-5)
- [`kimi-k3`](/docs/models/kimi-k3)
- [`gpt-5.6-sol`](/docs/models/gpt-5.6-sol)
- [`gpt-5.6-terra`](/docs/models/gpt-5.6-terra)
- [`claude-opus-4.8`](/docs/models/claude-opus-4-8)
- [`claude-sonnet-5`](/docs/models/claude-sonnet-5)
- [`gpt-5.5`](/docs/models/gpt-5.5)
- [`glm-5.2`](/docs/models/glm-5.2)
- [`claude-opus-4.7`](/docs/models/claude-opus-4-7)
- [`claude-opus-4.6`](/docs/models/claude-opus-4-6)
- [`claude-sonnet-4.6`](/docs/models/claude-sonnet-4-6)
- [`claude-haiku-4.5`](/docs/models/claude-haiku-4-5)
- [`gemini-3.1-pro-preview`](/docs/models/gemini-3.1-pro-preview)
- [`gpt-5.4`](/docs/models/gpt-5.4)
- [`gpt-5.3-codex`](/docs/models/gpt-5.3-codex)
- [`gpt-5.2-codex`](/docs/models/gpt-5.2-codex)
- [`gpt-5.1-codex-max`](/docs/models/gpt-5.1-codex-max)
- [`gpt-5.1-codex`](/docs/models/gpt-5.1-codex)
- [`glm-5.1`](/docs/models/glm-5.1)
- [`kimi-k2.6`](/docs/models/kimi-k2.6)
- [`minimax-m2.7`](/docs/models/minimax-m2.7)
- [`minimax-m3`](/docs/models/minimax-m3)
### Agent Models
- [`viv-fast`](/docs/models/viv-fast)
- [`gpt-6-astra`](/docs/models/gpt-6-astra)
- [`claude-fable-5-1`](/docs/models/claude-fable-5-1)
- [`deepseek-v4.1-flash`](/docs/models/deepseek-v4.1-flash)
- [`gemini-3.8-flash`](/docs/models/gemini-3.8-flash)
- [`kimi-k2.8-preview`](/docs/models/kimi-k2.8-preview)
- [`claude-fable-5`](/docs/models/claude-fable-5)
- [`deepseek-v4-pro-0813`](/docs/models/deepseek-v4-pro-0813)
- [`deepseek-v4-flash-vision-exp`](/docs/models/deepseek-v4-flash-vision-exp)
- [`deepseek-v4-flash (0731)`](/docs/models/deepseek-v4-flash)
- [`gemini-3.7-flash`](/docs/models/gemini-3.7-flash)
- [`gemini-3.6-flash`](/docs/models/gemini-3.6-flash)
- [`claude-opus-5`](/docs/models/claude-opus-5)
- [`kimi-k3`](/docs/models/kimi-k3)
- [`gpt-5.6-sol`](/docs/models/gpt-5.6-sol)
- [`gpt-5.6-terra`](/docs/models/gpt-5.6-terra)
- [`gpt-5.6-luna`](/docs/models/gpt-5.6-luna)
- [`gemini-3.5-flash`](/docs/models/gemini-3.5-flash)
- [`gpt-5.5`](/docs/models/gpt-5.5)
- [`deepseek-v4-pro`](/docs/models/deepseek-v4-pro)
- [`gpt-5.4`](/docs/models/gpt-5.4)
- [`gpt-5.4-mini`](/docs/models/gpt-5.4-mini)
- [`gpt-5.4-nano`](/docs/models/gpt-5.4-nano)
- [`gemini-3.1-pro-preview`](/docs/models/gemini-3.1-pro-preview)
- [`gemini-3.1-flash-lite-preview`](/docs/models/gemini-3.1-flash-lite-preview)
- [`gpt-5.2`](/docs/models/gpt-5.2)
- [`gpt-5.1`](/docs/models/gpt-5.1)
- [`gpt-5`](/docs/models/gpt-5)
- [`gpt-5-mini`](/docs/models/gpt-5-mini)
- [`gemini-3-pro-preview`](/docs/models/gemini-3-pro-preview)
- [`gemini-3-flash-preview`](/docs/models/gemini-3-flash-preview)
- [`glm-5.1`](/docs/models/glm-5.1)
- [`kimi-k2.6`](/docs/models/kimi-k2.6)
- [`minimax-m3`](/docs/models/minimax-m3)
### Image Models
- [`gpt-image-2.5-flare`](/docs/models/gpt-image-2.5-flare)
- [`gpt-image-2.5-sunburst`](/docs/models/gpt-image-2.5-sunburst)
- [`gemini-3-pro-image`](/docs/models/gemini-3-pro-image)
- [`gemini-3.1-flash-image`](/docs/models/gemini-3.1-flash-image)
### Decision Models
- [`jev-latest`](/docs/models/jev-latest)
## How to Set Models for your Agent Project
You don't need to specify a `model-name` in your API calls. The model for your agent is managed on the backend, so switching models won't require any code changes.
To change the model for your agent, go to the **Agent Settings** page in the Vivgrid Console.
## Pricing
Pricing is calculated in USD per 1 million tokens. The table below details the cost for input, cached, and output tokens for each model.
Image generation models bill generated images as output tokens at their own rate; the gpt-image-2.5 models also price image inputs separately from text. See [gemini-3-pro-image](/docs/models/gemini-3-pro-image) and [gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image) for the per-image token conversion at each resolution.
| Model | Input Token | Cached Token | Output Token |
| --------------------- | ----------- | ------------ | ------------ |
| **[viv-fast](/docs/models/viv-fast)** | \$0.13 | \$0.05 | \$0.40 |
| **[jev-latest](/docs/models/jev-latest)** | \$0.084 | - | \$0.00 |
| **[gpt-image-2.5-flare](/docs/models/gpt-image-2.5-flare)** | \$8.00 (text)
\$8.00 (image) | \$1.25 (text)
\$3.00 (image) | \$0.00 (text)
\$33.00 (image) |
| **[gpt-image-2.5-sunburst](/docs/models/gpt-image-2.5-sunburst)** | \$8.00 (text)
\$8.00 (image) | \$1.25 (text)
\$3.00 (image) | \$0.00 (text)
\$33.00 (image) |
| **[gpt-6-astra](/docs/models/gpt-6-astra)** | \$10.00 (\<= 272k tokens)
\$20.00 (> 272k tokens) | \$1.00 (\<= 272k tokens)
\$2.00 (> 272k tokens) | \$50.00 (\<= 272k tokens)
\$75.00 (> 272k tokens) |
| **[claude-fable-5-1](/docs/models/claude-fable-5-1)** | \$10.00 | \$0.50 | \$50.00 |
| **[gemini-3.8-flash](/docs/models/gemini-3.8-flash)** | \$0.75 | \$0.15 | \$3.75 |
| **[kimi-k2.8-preview](/docs/models/kimi-k2.8-preview)** | \$1.00 | \$0.26 | \$4.15 |
| **[deepseek-v4.1-flash](/docs/models/deepseek-v4.1-flash)** | \$0.31 | \$0.01 | \$1.23 |
| **[claude-fable-5](/docs/models/claude-fable-5)** | \$10.00 | \$1.25 | \$50.00 |
| **[glm-5.3-flash](/docs/models/glm-5.3-flash)** | \$0.15 | \$0.04 | \$0.50 |
| **[deepseek-v4-pro-0813](/docs/models/deepseek-v4-pro-0813)** | \$1.35 | \$0.05 | \$3.00 |
| **[deepseek-v4-flash-vision-exp](/docs/models/deepseek-v4-flash-vision-exp)** | \$0.44 | \$0.044 | \$1.32 |
| **[deepseek-v4-flash (0731)](/docs/models/deepseek-v4-flash)** | \$0.44 | \$0.044 | \$1.32 |
| **[gemini-3.7-flash](/docs/models/gemini-3.7-flash)** | \$0.75 | \$0.075 | \$3.75 |
| **[glm-5.3](/docs/models/glm-5.3)** | \$1.20 | \$0.30 | \$4.20 |
| **[gemini-3.6-flash](/docs/models/gemini-3.6-flash)** | \$0.75 | \$0.075 | \$3.75 |
| **[gemini-3-pro-image](/docs/models/gemini-3-pro-image)** | \$2.00 | \$0.20 | \$12.00 (text)
\$120.00 (image) |
| **[gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image)** | \$0.50 | \$0.05 | \$3.00 (text)
\$60.00 (image) |
| **[claude-opus-5](/docs/models/claude-opus-5)** | \$5.00 | \$0.50 | \$25.00 |
| **[kimi-k3](/docs/models/kimi-k3)** | \$3.00 | \$0.30 | \$15.00 |
| **[gpt-5.6-sol](/docs/models/gpt-5.6-sol)** | \$5.00 (\<= 272k tokens)
\$10.00 (> 272k tokens) | \$0.50 (\<= 272k tokens)
\$1.00 (> 272k tokens) | \$30.00 (\<= 272k tokens)
\$45.00 (> 272k tokens) |
| **[gpt-5.6-terra](/docs/models/gpt-5.6-terra)** | \$2.50 (\<= 272k tokens)
\$5.00 (> 272k tokens) | \$0.25 (\<= 272k tokens)
\$0.50 (> 272k tokens) | \$15.00 (\<= 272k tokens)
\$22.50 (> 272k tokens) |
| **[gpt-5.6-luna](/docs/models/gpt-5.6-luna)** | \$1.00 (\<= 272k tokens)
\$2.00 (> 272k tokens) | \$0.10 (\<= 272k tokens)
\$0.20 (> 272k tokens) | \$6.00 (\<= 272k tokens)
\$9.00 (> 272k tokens) |
| **[claude-sonnet-5](/docs/models/claude-sonnet-5)** | \$2.00 | \$0.20 | \$10.00 |
| **[claude-opus-4.8](/docs/models/claude-opus-4-8)** | \$5.00 | \$0.50 | \$25.00 |
| **[glm-5.2](/docs/models/glm-5.2)** | \$1.20 | \$0.30 | \$4.20 |
| **[minimax-m3](/docs/models/minimax-m3)** | \$0.32 (\<= 512k tokens)
\$0.67 (> 512k tokens) | \$0.07 (\<= 512k tokens)
\$0.13 (> 512k tokens) | \$1.28 (\<= 512k tokens)
\$2.55 (> 512k tokens) |
| **[gemini-3.5-flash](/docs/models/gemini-3.5-flash)** | \$1.50 | \$0.15 | \$9.00 |
| **[kimi-k2.6](/docs/models/kimi-k2.6)** | \$1.00 | \$0.20 | \$4.10 |
| **[glm-5.1](/docs/models/glm-5.1)** | \$0.91 (\<= 32k tokens)
\$1.22 (> 32k tokens) | \$0.20 (\<= 32k tokens)
\$0.31 (> 32k tokens) | \$3.64 (\<= 32k tokens)
\$4.25 (> 32k tokens) |
| **[minimax-m2.7](/docs/models/minimax-m2.7)** | \$0.32 | \$0.07 | \$1.28 |
| **[deepseek-v4-pro](/docs/models/deepseek-v4-pro)** | \$1.80 | \$0.30 | \$3.50 |
| **[gpt-5.5](/docs/models/gpt-5.5)** | \$5.00 (\<= 272k tokens)
\$10.00 (> 272k tokens) | \$0.50 (\<= 272k tokens)
\$1.00 (> 272k tokens) | \$30.00 (\<= 272k tokens)
\$45.00 (> 272k tokens) |
| **[gpt-5.4](/docs/models/gpt-5.4)** | \$2.50 (\<= 272k tokens)
\$5.00 (> 272k tokens) | \$0.25 (\<= 272k tokens)
\$0.50 (> 272k tokens) | \$15.00 (\<= 272k tokens)
\$22.50 (> 272k tokens) |
| **[gpt-5.4-mini](/docs/models/gpt-5.4-mini)** | \$0.75 | \$0.075 | \$4.50 |
| **[gpt-5.4-nano](/docs/models/gpt-5.4-nano)** | \$0.20 | \$0.02 | \$1.25 |
| **[gemini-3.1-flash-lite-preview](/docs/models/gemini-3.1-flash-lite-preview)** | \$0.25 | \$0.025 | \$1.50 |
| **[gemini-3.1-pro-preview](/docs/models/gemini-3.1-pro-preview)** | \$2.00 (\<= 200k tokens)
\$4.00 (> 200k tokens) | \$0.20 (\<= 200k tokens)
\$0.40 (> 200k tokens) | \$12.00 (\<= 200k tokens)
\$18.00 (> 200k tokens) |
| **[claude-opus-4.7](/docs/models/claude-opus-4-7)** | \$5.00 | \$0.50 | \$25.00 |
| **[claude-opus-4.6](/docs/models/claude-opus-4-6)** | \$5.00 | \$0.50 | \$25.00 |
| **[claude-sonnet-4.6](/docs/models/claude-sonnet-4-6)** | \$3.00 | \$0.30 | \$15.00 |
| **[claude-haiku-4.5](/docs/models/claude-haiku-4-5)** | \$1.00 | \$0.10 | \$5.00 |
| **[gpt-5.3-codex](/docs/models/gpt-5.3-codex)** | \$1.75 | \$0.18 | \$14.00 |
| **[gpt-5.2-codex](/docs/models/gpt-5.2-codex)** | \$1.75 | \$0.18 | \$14.00 |
| **[gpt-5.1-codex-max](/docs/models/gpt-5.1-codex-max)** | \$1.25 | \$0.13 | \$10.00 |
| **[gpt-5.1-codex](/docs/models/gpt-5.1-codex)** | \$1.25 | \$0.13 | \$10.00 |
| **[gpt-5.2](/docs/models/gpt-5.2)** | \$1.75 | \$0.18 | \$14.00 |
| **[gpt-5.1](/docs/models/gpt-5.1)** | \$1.25 | \$0.125 | \$10.00 |
| **[gpt-5](/docs/models/gpt-5)** | \$1.25 | \$0.125 | \$10.00 |
| **[gpt-5-mini](/docs/models/gpt-5-mini)** | \$0.25 | \$0.03 | \$2.00 |
| **[gpt-5.1](/docs/models/gpt-5.1)** | \$1.25 | \$0.125 | \$10.00 |
| **[gemini-3-pro-preview](/docs/models/gemini-3-pro-preview)** | \$2.00 | \$0.40 | \$12.00 |
| **[gemini-3-flash-preview](/docs/models/gemini-3-flash-preview)** | \$0.50 | \$0.05 | \$3.00 |
| **[gemini-2.5-pro](/docs/models/gemini-2.5-pro)** | \$1.25 (\<= 200k tokens)
\$2.50 (> 200k tokens) | \$0.125 (\<= 200k tokens)
\$0.25 (> 200k tokens) | \$10.00 (\<= 200k tokens)
\$15.00 (> 200k tokens) |
| **[gemini-2.5-flash](/docs/models/gemini-2.5-flash)** | \$0.30 | \$0.03 | \$2.50 |
| **[deepseek-v3.2](/docs/models/deepseek-v3.2)** | \$0.30 | \$0.06 | \$0.45 |
| **kimi-k2.5** | \$1.25 | \$0.125 | \$10.00 |
| **glm-5** | \$1.00 | \$0.10 | \$3.20 |
| **[gpt-4.1](/docs/models/gpt-4.1)** | \$2.00 | \$0.50 | \$8.00 |
| **[gpt-4o](/docs/models/gpt-4o)** | \$2.50 | \$1.25 | \$10.00 |
| **[deepseek-r1](/docs/models/deepseek-r1-0528)** | \$1.35 | - | \$5.40 |
| **[deepseek-v3.1](/docs/models/deepseek-v3.1)** | \$1.14 | - | \$4.56 |
## Capabilities
| Model | Context Window | Max Output Tokens | Tool Call |
| --------------------- | -------------- | ----------------- | --------- |
| **[viv-fast](/docs/models/viv-fast)** | 1,000,000 | 256,000 | Yes |
| **[jev-latest](/docs/models/jev-latest)** | 64,000 | — | No |
| **[gpt-6-astra](/docs/models/gpt-6-astra)** | 1,050,000 | 128,000 | Yes |
| **[claude-fable-5-1](/docs/models/claude-fable-5-1)** | 1,000,000 | 128,000 | Yes |
| **[gemini-3.8-flash](/docs/models/gemini-3.8-flash)** | 1,000,000 | 128,000 | Yes |
| **[kimi-k2.8-preview](/docs/models/kimi-k2.8-preview)** | 1,000,000 | — | Yes |
| **[deepseek-v4.1-flash](/docs/models/deepseek-v4.1-flash)** | 1,000,000 | 384,000 | Yes |
| **[gpt-image-2.5-flare](/docs/models/gpt-image-2.5-flare)** | — | — | No |
| **[gpt-image-2.5-sunburst](/docs/models/gpt-image-2.5-sunburst)** | — | — | No |
| **[claude-fable-5](/docs/models/claude-fable-5)** | 1,000,000 | 128,000 | Yes |
| **[glm-5.3-flash](/docs/models/glm-5.3-flash)** | 1,000,000 | 384,000 | Yes |
| **[deepseek-v4-pro-0813](/docs/models/deepseek-v4-pro-0813)** | 1,000,000 | 384,000 | Yes |
| **[deepseek-v4-flash-vision-exp](/docs/models/deepseek-v4-flash-vision-exp)** | 1,000,000 | 384,000 | Yes |
| **[deepseek-v4-flash (0731)](/docs/models/deepseek-v4-flash)** | 1,000,000 | 384,000 | Yes |
| **[gemini-3.7-flash](/docs/models/gemini-3.7-flash)** | 1,000,000 | 64,000 | Yes |
| **[glm-5.3](/docs/models/glm-5.3)** | 1,000,000 | 128,000 | Yes |
| **[gemini-3.6-flash](/docs/models/gemini-3.6-flash)** | 1,000,000 | 64,000 | Yes |
| **[gemini-3-pro-image](/docs/models/gemini-3-pro-image)** | 65,536 | 32,768 | No |
| **[gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image)** | 131,072 | 32,768 | No |
| **[claude-opus-5](/docs/models/claude-opus-5)** | 1,000,000 | 128,000 | Yes |
| **[kimi-k3](/docs/models/kimi-k3)** | 1,000,000 | 128,000 | Yes |
| **[gpt-5.6-sol](/docs/models/gpt-5.6-sol)** | 1,050,000 | 128,000 | Yes |
| **[gpt-5.6-terra](/docs/models/gpt-5.6-terra)** | 1,050,000 | 128,000 | Yes |
| **[gpt-5.6-luna](/docs/models/gpt-5.6-luna)** | 1,050,000 | 128,000 | Yes |
| **[claude-sonnet-5](/docs/models/claude-sonnet-5)** | 1,000,000 | 128,000 | Yes |
| **[claude-opus-4.8](/docs/models/claude-opus-4-8)** | 1,000,000 | 128,000 | Yes |
| **[glm-5.2](/docs/models/glm-5.2)** | 1,000,000 | 128,000 | Yes |
| **[minimax-m3](/docs/models/minimax-m3)** | 512,000 | 128,000 | Yes |
| **[gemini-3.5-flash](/docs/models/gemini-3.5-flash)** | 1,000,000 | 65,536 | Yes |
| **[kimi-k2.6](/docs/models/kimi-k2.6)** | 256,000 | 256,000 | Yes |
| **[glm-5.1](/docs/models/glm-5.1)** | 200,000 | 128,000 | Yes |
| **[minimax-m2.7](/docs/models/minimax-m2.7)** | 204,800 | 131,072 | Yes |
| **[deepseek-v4-pro](/docs/models/deepseek-v4-pro)** | 1,000,000 | 384,000 | Yes |
| **[gpt-5.5](/docs/models/gpt-5.5)** | 1,050,000 | 128,000 | Yes |
| **[gpt-5.4](/docs/models/gpt-5.4)** | 1,050,000 | 128,000 | Yes |
| **[gpt-5.4-mini](/docs/models/gpt-5.4-mini)** | 400,000 | 128,000 | Yes |
| **[gpt-5.4-nano](/docs/models/gpt-5.4-nano)** | 400,000 | 128,000 | Yes |
| **[gemini-3.1-flash-lite-preview](/docs/models/gemini-3.1-flash-lite-preview)** | 1,048,576 | 65,536 | Yes |
| **[gemini-3.1-pro-preview](/docs/models/gemini-3.1-pro-preview)** | 1,048,576 | 65,536 | Yes |
| **[claude-opus-4.7](/docs/models/claude-opus-4-7)** | 1,000,000 | 128,000 | Yes |
| **[claude-opus-4.6](/docs/models/claude-opus-4-6)** | 200,000 | 128,000 | Yes |
| **[claude-sonnet-4.6](/docs/models/claude-sonnet-4-6)** | 200,000 | 128,000 | Yes |
| **[gpt-5.3-codex](/docs/models/gpt-5.3-codex)** | 400,000 | 128,000 | Yes |
| **[gpt-5.2-codex](/docs/models/gpt-5.2-codex)** | 400,000 | 128,000 | Yes |
| **[gpt-5.1-codex-max](/docs/models/gpt-5.1-codex-max)** | 400,000 | 128,000 | Yes |
| **[gpt-5.1-codex](/docs/models/gpt-5.1-codex)** | 400,000 | 128,000 | Yes |
| **[gpt-5.2](/docs/models/gpt-5.2)** | 400,000 | 128,000 | Yes |
| **[gpt-5.1](/docs/models/gpt-5.1)** | 400,000 | 128,000 | Yes |
| **[gpt-5](/docs/models/gpt-5)** | 400,000 | 128,000 | Yes |
| **[gpt-5-mini](/docs/models/gpt-5-mini)** | 272,000 | 128,000 | Yes |
| **[deepseek-v3.2](/docs/models/deepseek-v3.2)** | 128,000 | 128,000 | Yes |
| **[gemini-3-pro-preview](/docs/models/gemini-3-pro-preview)** | 1,000,000 | 64,000 | Yes |
| **[gemini-3-flash-preview](/docs/models/gemini-3-flash-preview)** | 1,000,000 | 64,000 | Yes |
## Service Regions & Geo-Distributed Acceleration
Vivgrid intelligently accelerates model inference by **automatically routing API requests to the nearest available compute region**, minimizing latency and maximizing throughput — all while maintaining **data-residency compliance** for enterprise workloads.
Unlike conventional _Global_ deployments on public clouds (which rely on single centralized endpoints), **Vivgrid’s geo-distributed architecture** continuously synchronizes [**AI Skills**](/docs/managed-skills) and model states across multiple data zones, ensuring each region delivers **optimized, low-latency performance**.
| Model | Acceleration Mode | Accelerated Regions |
| :------------- | :---------------- | :------------------ |
| **[viv-fast](/docs/models/viv-fast)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[jev-latest](/docs/models/jev-latest)** | 🌐 Global (Centralized) | **AMER** |
| **[gpt-6-astra](/docs/models/gpt-6-astra)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[claude-fable-5-1](/docs/models/claude-fable-5-1)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gpt-image-2.5-flare](/docs/models/gpt-image-2.5-flare)** | 🌐 Global (Centralized) | **EMEA** |
| **[gpt-image-2.5-sunburst](/docs/models/gpt-image-2.5-sunburst)** | 🌐 Global (Centralized) | **EMEA** |
| **[gemini-3.8-flash](/docs/models/gemini-3.8-flash)** | 🌐 Global (Centralized) | — |
| **[kimi-k2.8-preview](/docs/models/kimi-k2.8-preview)** | 🌐 Global (Centralized) | **APAC** |
| **[deepseek-v4.1-flash](/docs/models/deepseek-v4.1-flash)** | 🌐 Global (Centralized) | **APAC** |
| **[claude-fable-5](/docs/models/claude-fable-5)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[glm-5.3-flash](/docs/models/glm-5.3-flash)** | 🌐 Global (Centralized) | **APAC** |
| **[deepseek-v4-pro-0813](/docs/models/deepseek-v4-pro-0813)** | 🌐 Global (Centralized) | **APAC** |
| **[deepseek-v4-flash-vision-exp](/docs/models/deepseek-v4-flash-vision-exp)** | 🌐 Global (Centralized) | **APAC** |
| **[deepseek-v4-flash (0731)](/docs/models/deepseek-v4-flash)** | 🌐 Global (Centralized) | **APAC** |
| **[gemini-3.7-flash](/docs/models/gemini-3.7-flash)** | 🌐 Global (Centralized) | — |
| **[glm-5.3](/docs/models/glm-5.3)** | 🌐 Global (Centralized) | **APAC** |
| **[gemini-3.6-flash](/docs/models/gemini-3.6-flash)** | 🌐 Global (Centralized) | — |
| **[gemini-3-pro-image](/docs/models/gemini-3-pro-image)** | 🌐 Global (Centralized) | — |
| **[gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image)** | 🌐 Global (Centralized) | — |
| **[claude-opus-5](/docs/models/claude-opus-5)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[kimi-k3](/docs/models/kimi-k3)** | 🌐 Global (Centralized) | **APAC** |
| **[gpt-5.6-sol](/docs/models/gpt-5.6-sol)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.6-terra](/docs/models/gpt-5.6-terra)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.6-luna](/docs/models/gpt-5.6-luna)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[claude-sonnet-5](/docs/models/claude-sonnet-5)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[claude-opus-4.8](/docs/models/claude-opus-4-8)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[glm-5.2](/docs/models/glm-5.2)** | 🌐 Global (Centralized) | **APAC** |
| **[minimax-m3](/docs/models/minimax-m3)** | 🌐 Global (Centralized) | **APAC** |
| **[gemini-3.5-flash](/docs/models/gemini-3.5-flash)** | 🌐 Global (Centralized) | - |
| **[kimi-k2.6](/docs/models/kimi-k2.6)** | 🌐 Global (Centralized) | **APAC** |
| **[glm-5.1](/docs/models/glm-5.1)** | 🌐 Global (Centralized) | **APAC** |
| **[minimax-m2.7](/docs/models/minimax-m2.7)** | 🌐 Global (Centralized) | **APAC** |
| **[deepseek-v4-pro](/docs/models/deepseek-v4-pro)** | 🌐 Global (Centralized) | **APAC** |
| **[gpt-5.5](/docs/models/gpt-5.5)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.4](/docs/models/gpt-5.4)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gpt-5.4-mini](/docs/models/gpt-5.4-mini)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gpt-5.4-nano](/docs/models/gpt-5.4-nano)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gemini-3.1-flash-lite-preview](/docs/models/gemini-3.1-flash-lite-preview)** | 🌐 Global (Centralized) | - |
| **[gemini-3.1-pro-preview](/docs/models/gemini-3.1-pro-preview)** | 🌐 Global (Centralized) | — |
| **[claude-opus-4.7](/docs/models/claude-opus-4-7)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[claude-opus-4.6](/docs/models/claude-opus-4-6)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[claude-sonnet-4.6](/docs/models/claude-sonnet-4-6)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **claude-opus-4.5** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.3-codex](/docs/models/gpt-5.3-codex)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.2-codex](/docs/models/gpt-5.2-codex)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.1-codex-max](/docs/models/gpt-5.1-codex-max)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.1-codex](/docs/models/gpt-5.1-codex)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gpt-5.2](/docs/models/gpt-5.2)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5.1](/docs/models/gpt-5.1)** | ⚡ Geo-Distributed | **AMER**, **EMEA** |
| **[gpt-5](/docs/models/gpt-5)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gpt-5-mini](/docs/models/gpt-5-mini)** | ⚡ Geo-Distributed | **AMER**, **EMEA**, **APAC** |
| **[gemini-2.5-pro](/docs/models/gemini-2.5-pro)** | 🌐 Global (Centralized) | — |
| **[gemini-2.5-flash](/docs/models/gemini-2.5-flash)** | 🌐 Global (Centralized) | — |
### Key Highlights
- **Dynamic Routing** — Vivgrid automatically detects the user’s region and routes requests to the **nearest accelerated node**, minimizing cross-continent latency.
- **Tool Synchronization** — AI tools and context caches are replicated across all accelerated regions for consistent behavior.
- **Adaptive Caching** — Frequently accessed prompts and embeddings are regionally cached to reduce cold-start delays.
- **Seamless Fallback** — Traffic automatically re-routes to neighboring accelerated zones during high load or outages.
### Notes on Global Models
For **Global-only** models (e.g., `gemini-3.1-pro-preview`), the model host remains centralized under the provider’s _Global Standard endpoint_, limiting VivGrid’s ability to perform regional acceleration.\
In contrast, **Geo-Distributed** models (e.g., `gpt-5.6-sol`,`claude-opus-5`) leverage Vivgrid’s orchestration layer — delivering **sub-50 ms latency worldwide** through intelligent regional acceleration.
---
Comparing Vivgrid with other platforms? See [Vivgrid vs. Alternatives](/compare).