Providers
Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.
| Provider | Context | Max output | Latency | Throughput | Input | Output | Cache | Capabilities | ZDR | No training | Regions | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 262K | 33K | 0.4 s | 138 tps | $0.090 | $1.10 | Read —Write — | 3 features | No | Yes | Global | Certified | |
| 262K | 262K | — | — | $0.15 | $1.20 | Read —Write — | 3 features | Yes | Yes | Global | Certified |
Uptime
24 hoursRequest success rate per provider.
Throughput
last hourP50 output tokens per second.
Latency
last hourP50 time to first token.
Getting started
Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.inferencebureau.com/v1",
apiKey: process.env.IB_API_KEY,
});
const res = await client.chat.completions.create({
model: "alibaba/qwen3-next-80b-a3b-instruct",
messages: [{ role: "user", content: "Why is the sky blue?" }],
});
console.log(res.choices[0].message.content);Top-level parameters
Standard Chat Completions parameters work as documented. These have model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. alibaba/qwen3-next-80b-a3b-instruct. Must be allowed by your team's Directives. |
max_tokens | number | No | Hard cap on generated tokens, and the basis for the balance reserved per request. Qwen3 Next 80B A3B Instruct supports up to 262,114 output tokens. |
tools | Tool[] | No | Function definitions the model can call. Tool calls are returned in choices[].message.tool_calls. |
Supported
max_tokenstemperaturestoptoolstool_choiceresponse_formatstructured_outputsInput limits
| Input | Sources | Limits |
|---|---|---|
| Text | — | Prompt and response share the 262K-token context window |
More models by alibaba
| Model | Context | Input | Output | Cache | Release |
|---|---|---|---|---|---|
| 1M | $4.00 | $12.00 | Read $0.50Write $5.00 | 09/23/2026 | |
| 1M | $0.15 | $0.47 | Read $0.016Write — | 09/17/2026 | |
| 991K | $2.00 | $6.00 | Read $0.25Write $2.50 | 09/01/2026 | |
| 991K | $0.15 | $0.47 | Read $0.016Write $0.20 | 08/26/2026 | |
| 262K | $0.060 | $2.30 | Read $0.059Write — | 08/14/2026 | |
| 262K | $2.00 | $6.00 | Read $0.25Write — | 08/02/2026 | |
| 262K | $2.00 | $6.00 | Read $0.25Write — | 08/02/2026 | |
| 991K | $0.030 | $0.13 | Read $0.0060Write $0.038 | 07/28/2026 | |
| 1M | $0.40 | $1.60 | Read $0.080Write $0.50 | 06/02/2026 | |
| 991K | $2.50 | $7.50 | Read $0.50Write $3.13 | 05/21/2026 |