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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Amazon Bedrock | 200K | 64K | 0.4 s | — | $1.00 | $5.00 | Read $0.100Write $1.25 | 7 features | Yes | Yes | US EU | Certified |
| 200K | 64K | 0.4 s | 102 tps | $1.00 | $5.00 | Read $0.100Write $1.25 | 7 features | Yes | Yes | Global | Certified | |
| 200K | 64K | 0.4 s | 104 tps | $1.00 | $5.00 | Read $0.100Write $1.25 | 6 features | Yes | Yes | Global | Certified | |
| 200K | 64K | 0.3 s | 98 tps | $1.00 | $5.00 | Read $0.100Write $1.25 | 7 features | Yes | Yes | US EU | Certified |
Uptime
24 hoursRequest success rate per provider.
Amazon Bedrock100.00%Throughput
last hourP50 output tokens per second.
Amazon Bedrock—Latency
last hourP50 time to first token.
Amazon Bedrock0.4 sGetting 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: "anthropic/claude-haiku-4.5",
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. anthropic/claude-haiku-4.5. 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. Claude Haiku 4.5 supports up to 64,000 output tokens. |
reasoning | { effort: 'low' | 'medium' | 'high' } | No | Reasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage. |
tools | Tool[] | No | Function definitions the model can call. Tool calls are returned in choices[].message.tool_calls. |
Supported
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputsInput limits
| Input | Sources | Limits |
|---|---|---|
| Text | — | Prompt and response share the 200K-token context window |
| Image | URL, base64 | Sent as image_url content parts; counts as input tokens |
| URL, base64 | Sent as file content parts; counts as input tokens |
More models by Anthropic
| Model | Context | Input | Output | Cache | Release |
|---|---|---|---|---|---|
| 1M | $0.100 | $0.50 | Read $0.010Write $0.13 | 10/07/2026 | |
| 1M | $0.050 | $0.25 | Read $0.0050Write $0.063 | 10/07/2026 | |
| 1M | $2.00 | $10.00 | Read $0.100Write $2.50 | 09/28/2026 | |
| 1M | $1.00 | $5.00 | Read $0.050Write $1.25 | 09/28/2026 | |
| 1M | $4.00 | $20.00 | Read $0.20Write $5.00 | 09/22/2026 | |
| 1M | $2.00 | $10.00 | Read $0.100Write $2.50 | 09/22/2026 | |
| 1M | $8.00 | $40.00 | Read $0.40Write $10.00 | 09/22/2026 | |
| 1M | $10.00 | $50.00 | Read $0.25Write $12.50 | 08/31/2026 | |
| 1M | $5.00 | $25.00 | Read $0.13Write $6.25 | 08/31/2026 | |
| 1M | $5.00 | $25.00 | Read $0.50Write $6.25 | 07/24/2026 |