Models

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.

Latest models

New models are added here as providers release them. Prices are in USD per 1M tokens, and models are listed alphabetically within each tier.

🚀 Frontier

Model	Best for	Context	Max output	Input	Cached	Output	API Protocol
claude-fable-5-1	Coding	1M	128K	$10.00	$0.50	$50.00	Messages, Chat Completions
gpt-6-astra	Coding	1.05M	128K	$10.00	$1.00	$50.00	Responses, Chat Completions

🛠️ Workhorse

Model	Best for	Context	Max output	Input	Cached	Output	API Protocol
claude-opus-5-5	Coding	1M	128K	$4.00	$0.20	$20.00	Messages, Chat Completions
claude-opus-5	Coding	1M	128K	$5.00	$0.50	$25.00	Messages, Chat Completions
claude-sonnet-5-5	Coding	1M	128K	$2.00	$0.20	$10.00	Messages, Chat Completions
claude-sonnet-5	Coding	1M	128K	$2.00	$0.20	$10.00	Messages, Chat Completions
gemini-4-argon	Coding	1.05M	1.05M	$4.00	$0.20	$20.00	Chat Completions
gpt-6.1-sol	Coding	1.05M	128K	$2.00	$0.20	$10.00	Responses, Chat Completions
gpt-6-sol	Coding	1.05M	128K	$2.00	$0.20	$10.00	Responses, Chat Completions
kimi-k3	Coding	1M	128K	$3.00	$0.30	$15.00	Chat Completions

⚡ Fast

Model	Best for	Context	Max output	Input	Cached	Output	API Protocol
claude-haiku-5-5	Coding	1M	128K	$0.10	$0.01	$0.50	Messages, Chat Completions
deepseek-v4.1-flash	Coding	1M	384K	$0.31	$0.01	$1.23	Chat Completions
deepseek-v4-pro	Coding	1M	384K	$1.74	$0.14	$3.48	Chat Completions
gemini-3.8-flash	Coding	1M	128K	$0.75	$0.15	$3.75	Chat Completions
glm-5.3	Coding	1M	128K	$1.20	$0.30	$4.20	Chat Completions
glm-5.3-flash	Coding	1M	384K	$0.15	$0.04	$0.50	Chat Completions
gpt-6-luna	General-purpose	1.05M	128K	$0.10	$0.01	$0.50	Responses, Chat Completions
gpt-6.1-terraNew	General-purpose	1.05M	128K	$1.10	$0.055	$5.50	Responses, Chat Completions
kimi-k2.8-preview	Coding	1M	—	$1.00	$0.26	$4.15	Chat Completions
minimax-m3	Coding	512K	128K	$1.20	$0.24	$2.40	Chat Completions
viv-fast	General-purpose	1M	256K	$0.13	$0.05	$0.40	Responses, Chat Completions

Prices are USD per 1M tokens at the base rate. Models with a long-context surcharge list it on their own page.

Image, decision & other models

These models are priced per image or per decision call, so they sit outside the price tiers.

Legacy models

Models from earlier generations remain available unless a retirement is announced. Prices are USD per 1M tokens, and each row points to the model to move to.

Scheduled retirements on November 11, 2026

The following models will be retired from Vivgrid on November 11, 2026 and will no longer be available after retirement. Migrate your integrations to the replacements listed in the table above before that date.

• deepseek-v3.2
• gemini-3.1-flash-lite-preview
• gemini-3.1-pro-preview
• gpt-5-mini
• gpt-5.1-codex
• gpt-5.1-codex-max
• gpt-5.2-codex
• gpt-5.3-codex
• gpt-5.4
• gpt-5.4-mini
• gpt-5.4-nano
• gpt-5.5

API Surfaces

Most models are offered on more than one surface. The API Protocol column above shows which wire protocols each model speaks; they are the same endpoints listed below, and each model's page shows which surfaces it is catalogued on.

Every surface sits behind the same API key and the same https://api.vivgrid.com/v1 base URL. Each model's page lists the surfaces it is catalogued on, with a copy-pasteable request for each — see gpt-6-sol or claude-opus-5-5 for an example.

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.

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 and model states across multiple data zones, ensuring each region delivers optimized, low-latency performance.

The table covers the latest models. Legacy models keep the acceleration mode listed on their own pages.

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-4-argon), 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.