Sumopod
Use Sumopod's OpenAI-compatible multi-model gateway with Anvia.
Sumopod exposes an OpenAI-compatible chat completions endpoint at https://ai.sumopod.com/v1. In Anvia, configure OpenAIClient with that baseUrl, then pass Sumopod model ids to completionModel(...).
Create the Client
import { AgentBuilder } from "@anvia/core";
import { OpenAIClient } from "@anvia/openai";
const client = new OpenAIClient({
baseUrl: "https://ai.sumopod.com/v1",
apiKey: process.env.SUMOPOD_API_KEY,
});
const model = client.completionModel("gpt-4o-mini");
const agent = new AgentBuilder("support", model)
.instructions("Answer support questions clearly.")
.build();
const response = await agent.prompt("Say hello in a creative way").send();
console.log(response.output);baseUrl makes Anvia use the OpenAI-compatible chat completion adapter. The model id is the Sumopod id, not an Anvia-specific alias.
Get the Model List
Sumopod's models API returns the model ids and metadata you can use when choosing a model. Because the client was created with baseUrl, listModels() calls Sumopod's /models endpoint.
const models = await client.listModels();
console.table(
models.data.map((model) => ({
id: model.id,
name: model.name,
contextLength: model.contextLength,
})),
);Use the id field directly with completionModel(...).
Available Models
Sumopod aggregates models from Anthropic, OpenAI, Google, DeepSeek, Alibaba, Z.AI, Moonshot, BytePlus, MiniMax, and Mimo. Sample ids and pricing per 1M tokens:
| Model | Provider | Context | Input | Output |
|---|---|---|---|---|
claude-haiku-4-5 | anthropic | 200,000 | $1.00 | $5.00 |
claude-opus-4-7 | anthropic | 1,000,000 | $5.00 | $25.00 |
claude-opus-4-8 | anthropic | 1,000,000 | $5.00 | $25.00 |
claude-sonnet-4-6 | anthropic | 1,000,000 | $3.00 | $15.00 |
deepseek-v4-flash | deepseek | 1,000,000 | $0.14 | $0.28 |
deepseek-v4-pro | deepseek | 1,000,000 | $0.43 | $0.87 |
gemini/gemini-2.5-flash | gemini | 1,048,576 | $0.30 | $2.50 |
gemini/gemini-2.5-flash-lite | gemini | 1,048,576 | $0.10 | $0.40 |
gemini/gemini-3-flash-preview | gemini | 1,048,576 | $0.50 | $3.00 |
gemini/gemini-3.1-flash-lite | gemini | 1,048,576 | $0.25 | $1.50 |
gemini/gemini-3.1-pro-preview | gemini | 1,048,576 | $2.00 | $12.00 |
gemini/gemini-3.5-flash | gemini | 1,048,576 | $1.50 | $9.00 |
glm-5 | z.ai | 128,000 | $0.60 | $2.00 |
glm-5-turbo | z.ai | 128,000 | $1.20 | $4.00 |
glm-5.1 | z.ai | 200,000 | $1.40 | $4.40 |
glm-5.2 | z.ai | 1,000,000 | $1.40 | $4.40 |
gpt-4.1 | openai | 1,047,576 | $2.00 | $8.00 |
gpt-4.1-mini | openai | 1,047,576 | $0.40 | $1.60 |
gpt-4.1-nano | openai | 1,047,576 | $0.10 | $0.40 |
gpt-5 | openai | 272,000 | $1.25 | $10.00 |
gpt-5-mini | openai | 272,000 | $0.25 | $2.00 |
gpt-5-nano | openai | 272,000 | $0.05 | $0.40 |
gpt-5.4 | openai | 1,050,000 | $2.50 | $15.00 |
gpt-5.4-mini | openai | 272,000 | $0.75 | $4.50 |
gpt-5.4-nano | openai | 272,000 | $0.20 | $1.25 |
kimi-k2.6 | moonshoot | 262,100 | $0.67 | $3.39 |
kimi-k2.7 | moonshoot | 262,100 | $0.95 | $4.00 |
mimo-v2.5 | mimo | 1,100,000 | $0.14 | $0.28 |
mimo-v2.5-pro | mimo | 1,100,000 | $0.43 | $0.87 |
MiniMax-M2.7-highspeed | sumopod | 204,800 | $0.03 | $0.12 |
MiniMax-M3 | minimax | 1,000,000 | $0.30 | $1.20 |
qwen3.6-flash | alibaba | 1,000,000 | $0.25 | $1.50 |
qwen3.6-plus | alibaba | 1,000,000 | $0.50 | $3.00 |
qwen3.7-max | alibaba | 1,000,000 | $1.25 | $3.75 |
qwen3.7-plus | alibaba | 1,000,000 | $0.32 | $1.28 |
seed-2-0-code | byteplus | 256,000 | $0.50 | $3.00 |
seed-2-0-lite | byteplus | 224,000 | $0.25 | $2.00 |
seed-2-0-mini | byteplus | 224,000 | $0.10 | $0.40 |
seed-2-0-pro | byteplus | 256,000 | $0.50 | $3.00 |
text-embedding-3-large | openai | 8,191 | $0.13 | — |
text-embedding-3-small | openai | 8,191 | $0.02 | — |
Prices shown above were captured on June 15, 2026. Discounts, regional pricing, and available models change frequently, so always confirm the latest rates on sumopod.com before quoting or budgeting.
Embedding models such as text-embedding-3-small, text-embedding-3-large, and gemini/gemini-embedding-001 can be retrieved through embeddingModel(...) when the gateway exposes them.
Notes
- Sumopod API keys are passed as bearer tokens in the
Authorizationheader. - Model capabilities still depend on the upstream model. Test the specific model id for tool calling, structured output, streaming, and multimodal support before enabling those features.
- Some models on Sumopod are sold at a discount off the upstream list price. The discount is applied by Sumopod, not by Anvia.
For current Sumopod API details, see the Sumopod documentation.
