> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bytespike.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Opus 4.6

> Refined 4-series Opus — 200K context with tighter long-form output and reduced hallucination on multi-document synthesis.

**Vendor:** Anthropic
**Model ID:** `claude-opus-4-6`
**Capability:** 200K context · tool use · vision · prompt caching · streaming · extended thinking
**Pricing:** per-token, Opus tier ([live rate](https://bytespike.ai/pricing#text))

Opus 4.6 is the refinement step on 4.5 — tighter
long-form prose and a measurable drop in hallucinations when summarising
across many documents within its 200K context. It's the right Opus for
multi-document workflows that 4.5 was nearly good enough at: legal review,
scientific literature synthesis, codebase audit reports.
[Opus 4.8](/models/claude-opus-4-8) is the current flagship; 4.6 is kept
available for teams who've validated against this specific version.

## Request

```bash theme={null}
curl https://llm.bytespike.ai/v1/messages \
  -H "x-api-key: $BYTESPIKE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-4-6",
    "max_tokens": 16384,
    "messages": [
      {"role": "user", "content": "Synthesize the methodology sections of these 14 papers."}
    ]
  }'
```

### Body parameters

| Field         | Type            | Required | Default           | Notes                                             |
| ------------- | --------------- | -------- | ----------------- | ------------------------------------------------- |
| `model`       | string          | yes      | —                 | `claude-opus-4-6`                                 |
| `messages`    | array           | yes      | —                 | Conversation history. Up to 200K tokens of input. |
| `max_tokens`  | integer         | yes      | —                 | Hard cap. Max for this model: 32768.              |
| `system`      | string \| array | no       | —                 | Array form supports `cache_control`.              |
| `temperature` | number          | no       | 1.0               | Range 0.0–1.0.                                    |
| `top_p`       | number          | no       | 1.0               | Nucleus sampling.                                 |
| `tools`       | array           | no       | —                 | Supported.                                        |
| `tool_choice` | object          | no       | `{"type":"auto"}` | `auto` / `any` / `tool` (named).                  |
| `thinking`    | object          | no       | —                 | Extended-thinking budget.                         |
| `stream`      | boolean         | no       | false             | SSE streaming.                                    |

## Response

```json theme={null}
{
  "id": "msg_opus_…",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-6",
  "content": [
    {"type": "text", "text": "Across the 14 papers, three methodological themes emerge..."}
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 187430,
    "output_tokens": 4218
  }
}
```

## Code examples

<CodeGroup>
  ```bash cURL theme={null}
  curl https://llm.bytespike.ai/v1/messages \
    -H "x-api-key: $BYTESPIKE_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "content-type: application/json" \
    -d '{
      "model": "claude-opus-4-6",
      "max_tokens": 16384,
      "messages": [{"role": "user", "content": "Synthesize the methodology sections of these papers."}]
    }'
  ```

  ```python Python theme={null}
  import anthropic

  client = anthropic.Anthropic(
      base_url="https://llm.bytespike.ai/v1",
      api_key="$BYTESPIKE_API_KEY",
  )

  message = client.messages.create(
      model="claude-opus-4-6",
      max_tokens=16384,
      messages=[
          {"role": "user", "content": "Synthesize the methodology sections of these papers."}
      ],
  )

  print(message.content[0].text)
  ```

  ```javascript Node theme={null}
  import Anthropic from "@anthropic-ai/sdk"

  const client = new Anthropic({
    baseURL: "https://llm.bytespike.ai/v1",
    apiKey: process.env.BYTESPIKE_API_KEY,
  })

  const message = await client.messages.create({
    model: "claude-opus-4-6",
    max_tokens: 16384,
    messages: [
      {
        role: "user",
        content: "Synthesize the methodology sections of these papers.",
      },
    ],
  })

  console.log(message.content[0].text)
  ```
</CodeGroup>

## Cache control

```json theme={null}
{
  "model": "claude-opus-4-6",
  "system": [
    {
      "type": "text",
      "text": "<the corpus you keep referring to>",
      "cache_control": {"type": "ephemeral"}
    }
  ],
  "messages": [...]
}
```

Cache rate at the discounted tier visible in the
[pricing table](https://bytespike.ai/pricing#text).

## Errors

| Code | Trigger                   | Billed?                  |
| ---- | ------------------------- | ------------------------ |
| 400  | Body validation failed    | No                       |
| 401  | Missing / revoked key     | No                       |
| 402  | Wallet exhausted          | No                       |
| 413  | Input exceeds 200K tokens | No                       |
| 429  | Rate-limited              | No                       |
| 5xx  | Upstream provider issue   | No (auto-retry envelope) |

## When to use

* Multi-document synthesis where 4.5 was almost-but-not-quite reliable.
* Long-form summarisation that needs tight, non-repetitive prose.
* For the current flagship Opus, see [Opus 4.8](/models/claude-opus-4-8).
* For mid-tier cost / latency, see [Sonnet 4.6](/api-reference/text/claude-sonnet-4-6).

## Limits

| Limit                      | Value        |
| -------------------------- | ------------ |
| Context window             | 200K tokens  |
| Max output                 | 32768 tokens |
| Supports tool use          | Yes          |
| Supports vision            | Yes          |
| Supports streaming         | Yes          |
| Supports prompt caching    | Yes          |
| Supports extended thinking | Yes          |