Claude 3.7 Sonnet: pricing, performance, and how to route requests

Route requests to
Claude 3.7 Sonnet
with Merge Gateway

Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.

What Claude 3.7 Sonnet costs to run

| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention | | --- | ---: | ---: | --- | | Amazon Bedrock | $3.00 | $15.00 | Yes |

Test Claude 3.7 Sonnet
with Gateway’s Simulator

See a prompt's output, token spend, latency, and more with Claude 3.7 Sonnet.

Route requests to Claude 3.7 Sonnet in minutes

To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.

Install the Merge Gateway SDK

Python

1$ pip install merge-gateway-sdk

Send a request

Python

1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6    model="openai/gpt-5.2",
7    input=[
8        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10    ],
11)
12
13print(response.output[0].content[0].text)

Try a diffrent model

Swap the model string to route to a different provider. No other code changes needed.

Anthropic

1response = client.responses.create(
2    model="anthropic/claude-sonnet-4-20250514",
3    input=[
4        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6    ],
7)

Point to Gateway

Python

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="YOUR_API_KEY",
5    base_url="https://api-gateway.merge.dev/v1/openai",
6)

Send a request

Use the standard chat.completions.create method. No provider prefix needed on the model name.

Python

1response = client.chat.completions.create(
2    model="gpt-5.2",
3    messages=[
4        {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6    ],
7)
8
9print(response.choices[0].message.content)

Install packages

1npm install merge-gateway-ai-sdk-provider ai

Create the provider

TypeScript

1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4  apiKey: "YOUR_API_KEY",
5});

Send a request

Use generateText to send a request. Model names use the provider/model format.

TypeScript

1import { generateText } from "ai";
2
3const { text } = await generateText({
4  model: gateway("openai/gpt-4o"),
5  prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);

If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:

TypeScript

1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4  apiKey: "YOUR_API_KEY",
5  baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchanged

Install the Merge Gateway SDK

Anthropic SDK

1from anthropic import Anthropic
2
3client = Anthropic(
4    api_key="YOUR_API_KEY",
5    base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9    model="claude-sonnet-4-20250514",
10    max_tokens=1024,
11    messages=[
12        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13    ],
14)
15
16print(message.content[0].text)

Explore other models available in Merge Gateway

Amazon Nova 2 Lite

Amazon Nova 2 Sonic

Amazon Nova Lite

Amazon Nova Micro

Amazon Nova Premier

Amazon Nova Pro

Bland Speech v3

Claude 3.7 Sonnet

Claude 4 Opus 20250514

Claude Fable 5

Claude Fable 5.1

Claude Haiku 4.5 (20251001)

Claude Opus 4.1 (20250805)

Claude Opus 4 (20250514)

Claude Opus 4.5 (20251101)

Claude Opus 4.6

Claude Opus 4.7

Claude Opus 4.8

Claude 3.7 Sonnet FAQ

Have more questions about Claude 3.7 Sonnet? We've answered a few more below. Note that this was written in July, 2026 and is subject to change.

Heading

What other models does Anthropic offer?

Anthropic's Claude family is split into Opus, Sonnet, and Haiku tiers that balance quality, cost, and speed. Here are some other models Anthropic supports:

Claude Opus 4.8: the flagship tier, with the highest reasoning and coding quality in the lineup

Claude Sonnet 5: the newest mid-tier model, Anthropic's most agentic Sonnet, with a 1M-token context window at a steep discount to Opus

Claude Sonnet 4.6: a more recent Sonnet offering near-Opus performance at Sonnet pricing

Claude Opus 4.7: an earlier flagship generation for teams standardized on that version

How does Claude 3.7 Sonnet differ from Anthropic's other models?

Claude 3.7 Sonnet is an earlier-generation Sonnet, notable as the first Claude to combine standard and extended-thinking modes in one model.

Hybrid reasoning: introduced a toggle between fast standard responses and extended step-by-step thinking, a capability the newer Sonnet and Opus tiers build on

Context window: 200K tokens, below the 1M-token window on Claude Sonnet 5

Generation: superseded by Claude Sonnet 4.6 and Claude Sonnet 5, which are stronger at agentic and coding tasks

Use case fit: a stable, well-understood Sonnet for teams that have already built and validated against it

Reach for Claude 3.7 Sonnet when you need a proven, fixed Sonnet version, but evaluate the newer Sonnet tiers for new builds.

What models should I consider using alongside Claude 3.7 Sonnet?

No single model is optimal for every task. Here are models worth pairing with Claude 3.7 Sonnet depending on what your product needs:

Claude Sonnet 5 as the upgrade path for agentic and coding work that needs stronger tool use and a larger context window

Claude Opus 4.8 for the hardest reasoning or coding tasks where you want top-tier quality

Gemini 3.5 Flash for high-volume, low-complexity work where Sonnet-tier quality is unnecessary

Gemini 3.1 Pro for multimodal reasoning over long documents or video

GPT-5.5 as a second high-quality general model for cross-provider comparison

What are the challenges of using Claude 3.7 Sonnet in my product?

Like any production LLM, Claude 3.7 Sonnet comes with tradeoffs worth planning for:

Superseded generation: newer Sonnet tiers outperform it on agentic and coding tasks, so it may not be the best quality-per-dollar choice for new work

Provider dependency: relying only on Anthropic creates fragility during outages or model retirements

Cost at scale: at standard Sonnet output pricing, high-volume workloads compound quickly without active budgeting

Extended-thinking overhead: turning on extended thinking raises output tokens and latency, so use it selectively

Context ceiling: the 200K-token window is smaller than the 1M available on the newest Sonnet, which matters for very long inputs

Why should I use Merge Gateway to route LLM requests with Claude 3.7 Sonnet and every other model?

Routing Claude 3.7 Sonnet through Merge Gateway pairs the model with the infrastructure you'd otherwise build yourself:

One API, every provider: Call Claude 3.7 Sonnet and every other major model from a single endpoint and key, switching models with a string change rather than a code change

Intelligent routing and automatic failover: Merge fails over around Anthropic outages on its own, and routing on cost, latency, or quality can lower spend by 40 to 60% with no code edits

Cost governance: Cap spend with project budgets and see every request attributed by model, project, and tag in one cross-provider dashboard

Build Your Own Router: Define "best" for your traffic with curated benchmarks or your own evals, and let the router choose per request and explain why

Security and compliance controls: Run DLP and prompt injection checks before requests reach Anthropic, and enforce per-project model and region rules centrally

How can I start routing requests to Claude 3.7 Sonnet via Merge Gateway?

Getting Claude 3.7 Sonnet running through Merge Gateway takes a few minutes:

1. Create an account and get your API key from the dashboard.

2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.

3. Make your first request using the provider/model format. For Claude 3.7 Sonnet, the model string is anthropic/claude-3.7-sonnet. Swap the model string to route to any other provider without changing anything else.

4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming Claude 3.7 Sonnet as primary with one fallback.

Full setup instructions and SDK references are in the Merge Gateway docs.