Strands harness runs on the latest models across Amazon Bedrock, Anthropic, OpenAI, and Google, and uses Amazon Bedrock by default. Pass `model` to pick another; pass `effort` to change how hard the agent reasons. Both are single arguments that work the same across every provider.

## Point Strands harness at a model

You pick a model by passing `model`, which accepts three forms: a `provider/name` string, a bare Bedrock model id, or a ready-made Strands `Model` instance. The `provider/` prefix has aliases for `bedrock`, `bedrock-mantle`, `anthropic`, `openai`, `google`, `ollama`, and `litellm`. A string with no provider prefix is treated as a bare Amazon Bedrock id.

(( tab "Strands harness" ))
(( tab "Python" ))
```python
from strands_harness import create_harness

agent = create_harness(model="openai/gpt-5.6-sol")
```
(( /tab "Python" ))

(( tab "TypeScript" ))
```typescript
import { createHarness } from '@strands-agents/harness'

const agent = await createHarness({ model: 'openai/gpt-5.6-sol' })
```
(( /tab "TypeScript" ))
(( /tab "Strands harness" ))

(( tab "SDK" ))
(( tab "Python" ))
```python
from strands import Agent

agent = Agent(model="global.anthropic.claude-sonnet-5")
```
(( /tab "Python" ))

(( tab "TypeScript" ))
```typescript
import { Agent } from '@strands-agents/sdk'

const agent = new Agent({ model: 'global.anthropic.claude-sonnet-5' })
```
(( /tab "TypeScript" ))
(( /tab "SDK" ))

For a provider Strands harness does not have an alias for, or for a model you have already configured (custom endpoint, credentials, request fields), build the `Model` instance yourself and pass it. Strands harness uses it as-is:

(( tab "Python" ))
```python
from strands.models import BedrockModel
from strands_harness import create_harness

model = BedrockModel(model_id="global.anthropic.claude-opus-4-8", region_name="us-west-2")
agent = create_harness(model=model)
```
(( /tab "Python" ))

(( tab "TypeScript" ))
```typescript
import { BedrockModel } from '@strands-agents/sdk'
import { createHarness } from '@strands-agents/harness'

const model = new BedrockModel({ modelId: 'global.anthropic.claude-opus-4-8' })
const agent = await createHarness({ model })
```
(( /tab "TypeScript" ))

An unknown provider prefix fails at construction with the list of supported providers, so a typo surfaces immediately rather than as a request error later.

## Set reasoning effort

`effort` maps one reasoning level onto whatever each provider’s API expects, so you set it once regardless of provider:

-   `"auto"` (the default) uses each provider’s recommended level.
-   `"low"`, `"medium"`, and `"high"` set it explicitly.
-   `"off"` (or `off` on the CLI) turns reasoning off.

(( tab "Strands harness" ))
(( tab "Python" ))
```python
from strands_harness import create_harness

agent = create_harness(model="anthropic/claude-opus-4-8", effort="high")
```
(( /tab "Python" ))

(( tab "TypeScript" ))
```typescript
import { createHarness } from '@strands-agents/harness'

const agent = await createHarness({ model: 'anthropic/claude-opus-4-8', effort: 'high' })
```
(( /tab "TypeScript" ))
(( /tab "Strands harness" ))

(( tab "SDK" ))
(( tab "Python" ))
```python
from strands import Agent
from strands.models import BedrockModel

bedrock_model = BedrockModel(
    model_id="global.anthropic.claude-sonnet-5",
    additional_request_fields={
        "thinking": {"type": "enabled", "budget_tokens": 4096}
    },
)
agent = Agent(model=bedrock_model)
```
(( /tab "Python" ))

(( tab "TypeScript" ))
```typescript
import { Agent, BedrockModel } from '@strands-agents/sdk'

const bedrockModel = new BedrockModel({
  modelId: 'global.anthropic.claude-sonnet-5',
  additionalRequestFields: {
    thinking: { type: 'enabled', budget_tokens: 4096 },
  },
})
const agent = new Agent({ model: bedrockModel })
```
(( /tab "TypeScript" ))
(( /tab "SDK" ))

A level a provider does not accept fails at construction rather than mid-request. Some providers accept finer levels (for example `minimal` or `xhigh`); Strands harness validates against the resolved provider’s own set, so use the levels that provider documents.

Reasoning does not apply to a pre-built `Model` instance: configure reasoning on the instance itself when you pass one.

## Note on web search and caching

Two model-level features follow from the provider you pick. Native `web_search` works on OpenAI, Anthropic, Google, and GPT-5/GPT-6 models on bedrock-mantle; prompt caching is configured by Strands harness on Amazon Bedrock and Anthropic direct and is automatic elsewhere. Both are covered where you enable them: [web access](/docs/user-guide/harness/tools/web-access/index.md) and [manage context and caching](/docs/user-guide/harness/configure/context-and-caching/index.md).

For the full option list, see the [configuration reference](/docs/user-guide/harness/reference/configuration/index.md).

## Implementation

### Python

- [harness-sdk/harness-py/src/strands_harness/models.py](https://github.com/strands-agents/harness-sdk/blob/main/harness-py/src/strands_harness/models.py)
- [harness-sdk/harness-py/src/strands_harness/defaults.py](https://github.com/strands-agents/harness-sdk/blob/main/harness-py/src/strands_harness/defaults.py)

### TypeScript

- [harness-sdk/harness-ts/src/models.ts](https://github.com/strands-agents/harness-sdk/blob/main/harness-ts/src/models.ts)