---
title: "Blaze: One API for Open-Weight Model Inference"
description: "Blaze is a model inference API from E2E Networks: one OpenAI-compatible endpoint for open-weight text, voice, OCR, multi-modal and diffusion models."
url: "https://www.e2enetworks.com/blaze"
canonical: "https://www.e2enetworks.com/blaze"
provider: "E2E Networks Limited"
type: "Service"
keywords: ["blaze", "model inference api", "openai compatible api", "open-weight models", "llm inference india", "model routing", "token factory", "e2e networks blaze"]
region: "India"
generated: "2026-09-17"
---

# Blaze: One API for Open-Weight Model Inference

> A model inference API from E2E Networks. One OpenAI-compatible endpoint for the open-weight text, voice, OCR, multi-modal and diffusion models in the Blaze catalogue, with model routing via the x-model: auto header. Runs in Indian data centres and is billed in INR.

Canonical page: https://www.e2enetworks.com/blaze

## What is Blaze?

Blaze is a model inference API from E2E Networks.

It provides a single API for the open-weight models in the Blaze catalogue — text, voice, OCR, multi-modal and diffusion. An application sends a request and receives a model response. Capacity, availability, serving, optimisation and endpoint operations are provided by the platform. Blaze runs on E2E Networks infrastructure located in Indian data centres and is billed in INR.

## What do you stop operating when inference moves to an API?

The same workload can be served by infrastructure you run or by an API you call. These are the pieces of work that move.

| Concern | Running inference yourself | Running inference through Blaze |
| --- | --- | --- |
| GPU capacity | Source, qualify and provision GPU capacity | Send a request to the API and receive a response |
| Contracts & utilisation | Reserve or lease capacity, and manage contracts and utilisation | Capacity and availability are operated by the platform |
| Serving stack | Build the serving stack — serving, batching, quantisation, kernels, scaling | Serving and optimisation are provided in the platform |
| Tuning | Tune latency, throughput and cost on an ongoing basis | Models can be switched without changing your own infrastructure |
| Endpoint operations | Operate autoscaling, failure handling, upgrades and capacity planning | Endpoint operations are handled by the platform |
| Analytics | Build your own token-level analytics and monitoring | Token-level usage, performance and cost analytics are provided |

## What you get from the platform

- **One API** — A single API for the models in the Blaze catalogue — text, voice, OCR, multi-modal and diffusion — reached through an OpenAI-compatible endpoint.
- **Model routing** — Requests are placed across model endpoints by the platform’s routing layer rather than being pinned to a static endpoint per model.
- **Runtime features for agentic workloads** — Session persistence, hierarchical context memory and long-context handling are provided in the runtime, so an agent framework does not have to implement them itself.
- **Token analytics** — Token-level usage, performance and cost data are available through the platform, rather than something you instrument and store yourself.
- **Location and billing** — Blaze runs on E2E Networks infrastructure located in Indian data centres and is billed in INR.
- **Custom inference stack** — Model configurations are benchmarked and tuned across the GPU architectures in the fleet, with KV offload and context transfer across variants in the same model family.

## Which models are available on Blaze?

The catalogue covers text, voice, OCR, multi-modal and diffusion models — among them Gemma 4B, Qwen 3.5-9B, Qwen3.8 Flash and Qwen3.8 Max, DeepSeek V4 Flash, Kimi K3 from Moonshot AI, GLM 5.3, IBM Granite 4.2 8B and Tencent’s Hy-MT2 translation models, alongside the sovereign Indic models Sarvam 30B and Sarvam 100B.

| Model | API alias | Creator | Capabilities | Context | Max output |
| --- | --- | --- | --- | --- | --- |
| Granite 4.2 8B | ibm-granite/granite-4.2-8b | IBM | Tools, JSON, Reasoning | 131,072 | 117,964 |
| Qwen3.8 Flash | qwen/qwen3.8-flash | Qwen | Vision, Tools, JSON, Reasoning | 1,000,000 | 131,072 |
| GLM 5.3 Flash | z-ai/glm-5.3-flash | Z.ai | Vision, Tools, JSON, Reasoning | 1,310,720 | 131,072 |
| GLM 5.3 Flash (batch) | z-ai/glm-5.3-flash:batch | Z.ai | Vision, Tools, JSON, Reasoning | 1,048,575 | 943,717 |
| DeepSeek V4 Flash Vision Exp | deepseek/deepseek-v4-flash-vision-exp | DeepSeek | Vision, Tools, Reasoning | 1,048,576 | 384,000 |
| Hy-MT2-1.8B | tencent/hy-mt2-1.8b | Tencent | Text only | 8,192 | 4,096 |

A sample of the Blaze catalogue, as listed in the console. Context and maximum output are in tokens.

## How do you call Blaze without pinning a model?

Call the same OpenAI-compatible endpoint you would use for a single model, and set the x-model: auto header — either as a default header on the client or per request. The routing layer then places each request across model endpoints instead of you naming one up front.

## Example request — Python

```python
from openai import OpenAI

client = OpenAI(
    api_key="BLAZE_API_KEY",
    base_url="https://blaze.e2enetworks.net/v1",
    default_headers={
        "x-model": "auto",
    },
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Extract the payment terms from this clause."}],
)
print(response.choices[0].message.content)
```

## Example request — Node

```node
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.BLAZE_API_KEY,
  baseURL: "https://blaze.e2enetworks.net/v1",
  defaultHeaders: {
    "x-model": "auto",
  },
});

const response = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Extract the payment terms from this clause." }],
});
console.log(response.choices[0].message.content);
```

## Example request — cURL

```bash
curl https://blaze.e2enetworks.net/v1/chat/completions \
  -H "Authorization: Bearer $BLAZE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-model: auto" \
  -d '{
        "model": "auto",
        "messages": [
          { "role": "user", "content": "Extract the payment terms from this clause." }
        ]
      }'
```

## Request headers and endpoint

- **x-model: auto** — Blaze selects a model for each request instead of you naming one. Send it as a default header on the client, or per request.
- **Base URL** — — the OpenAI-compatible path, so existing clients need a base URL and a key, not a rewrite.

## What is inside the inference stack?

Experience the bleeding-edge inference research. Blaze is a custom inference stack with optimised kernels, the latest decoding techniques and advanced caching baked in.

## Frequently asked questions

### What is Blaze?

Blaze is a model inference API from E2E Networks. It provides a single API for the open-weight models in the Blaze catalogue, covering text, voice, OCR, multi-modal and diffusion models. An application sends a request and receives a model response. Capacity, serving and endpoint operations are provided by the platform.

### Which models are available on Blaze?

The Blaze catalogue covers text, voice, OCR, multi-modal and diffusion models, including Gemma 4B, Qwen 3.5-9B, Qwen3.8 Flash and Qwen3.8 Max, DeepSeek V4 Flash, Kimi K3 from Moonshot AI, GLM 5.3, IBM Granite 4.2 8B, Tencent Hy-MT2 translation models, and the sovereign Indic models Sarvam 30B and Sarvam 100B. The current list is shown in the Model APIs section of the Blaze console.

### Is the Blaze API OpenAI-compatible?

Yes. Blaze exposes an OpenAI-compatible endpoint, so an existing OpenAI client can be pointed at the Blaze base URL. In Python, this means setting base_url on the OpenAI client and supplying a Blaze API key; the rest of the chat completions call is unchanged.

### How does model routing work on Blaze?

Requests are placed across model endpoints by the Blaze routing layer rather than being pinned to a static endpoint per model. A caller can name a model, or send the header x-model: auto and have the platform select a model for each request. Models can be switched without changes to the caller’s own infrastructure.

### What does Blaze provide for agentic workloads?

Session persistence, hierarchical context memory and long-context handling are provided in the Blaze runtime, so an agent framework does not have to implement them itself. Several models in the catalogue also expose tool calling, JSON output and reasoning, and context windows above one million tokens.

### Where does Blaze run, and in what currency is it billed?

Blaze runs on E2E Networks infrastructure located in Indian data centres and is billed in INR.

### What do I not have to operate if I use Blaze?

Running inference yourself means sourcing and provisioning GPU capacity, managing capacity contracts and utilisation, building a serving stack covering batching, quantisation, kernels and scaling, tuning latency, throughput and cost, and operating autoscaling, failure handling and upgrades. On Blaze these are operated by the platform and reached through the API.

### How is token usage measured and reported on Blaze?

Token-level usage, performance and cost data are available through the platform in the Analytics section of the Blaze console, rather than being something the caller instruments and stores itself.

### What is inside the Blaze inference stack?

Blaze uses a custom inference stack. Model configurations are benchmarked and tuned across the GPU architectures in the fleet, requests are placed by the platform’s orchestration layer, and KV offload and context transfer are supported across variants within the same model family, including FP8 and BF16.

## Related pages

- [Inference endpoints: deploy a model on dedicated capacity](https://www.e2enetworks.com/inference-endpoints)
- [TIR: build, fine-tune and deploy models](https://www.e2enetworks.com/tir)
- [GPU cloud](https://www.e2enetworks.com/gpu-cloud)
- [All products](https://www.e2enetworks.com/compute-products)
- [Talk to sales](https://www.e2enetworks.com/contact-sales)

---

This Markdown is generated from the same data that renders https://www.e2enetworks.com/blaze. Provider: E2E Networks Limited (NSE: E2E), India. Site index for AI agents: https://www.e2enetworks.com/llms.txt