Hard software engineering
Anthropic reported its biggest gains over Opus 4.6 on the most difficult coding tasks, the kind that used to need close supervision.
Anthropic
Operational· 100% uptime, 7 daysClaude Opus 4.7 API
Claude Opus 4.7 API pricing at 64% below list, for apps tuned on Opus 4.7.
Price per 1M tokens64%off
- Input
- $1.78
$5.00 - Output
- $8.93
$25.00 - Cached input
- $0.178
Model ID
claude-opus-4-7chat.py
from openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)stream = client.chat.completions.create( model="claude-opus-4-7", messages=[{"role": "user", "content": "Explain quicksort in two sentences."}], stream=True,)for chunk in stream: if chunk.choices: print(chunk.choices[0].delta.content or "", end="")Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK, and the Anthropic SDK and Claude Code.
- Context window
- 1M tokens
- Max output
- 128K tokens
- Input
- Text, Image
- Output
- Text
- Released
- Apr 16, 2026
- Uptime, 7 days
- 100%
Pricing
Claude Opus 4.7 API pricing. A fraction of the list price.
Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.
| Rate | zurelay | Anthropic list | You save |
|---|---|---|---|
Input per 1M tokens | $1.78 | 64%off | |
Output per 1M tokens | $8.93 | 64%off | |
Cached input per 1M tokens | $0.178 | — | — |
One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.
Savings calculator
Move the sliders to your monthly usage.
Input tokens per month50M
Output tokens per month10M
zurelay
$178.30
Anthropic list price
$500.00
You save every month$321.70
$3,860 a year
Overview
What is Claude Opus 4.7?
Claude Opus 4.7 is the April 2026 Opus model that introduced xhigh effort, high-resolution vision and a new tokenizer. The zurelay Claude Opus 4.7 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints, priced at 64% below Anthropic's list price. It suits teams whose prompts, evals or agents are tuned to Opus 4.7 and should not move yet.
Claude Opus 4.7 was released by Anthropic on April 16, 2026 as the successor to Opus 4.6, at the same list price. Anthropic described it as a clear step up from Opus 4.6 in advanced software engineering, with the biggest gains on the hardest tasks, and said it handles long-running work with rigor and finds ways to check its own output. On zurelay, Claude Opus 4.7 API pricing is $1.78 per 1M input tokens and $8.93 per 1M output tokens, compared with Anthropic's list price of $5.00 and $25.00.
Several things arrived with Opus 4.7 and carried into later Opus models. It was the first Claude model with high-resolution image support, taking images up to 2,576 pixels on the long edge, up from 1,568, with pointing coordinates that map 1:1 to image pixels. It added the xhigh effort level between high and max, which Anthropic recommends as the starting point for coding and agentic work. It also introduced a new tokenizer that can use roughly 1.0 to 1.35 times as many tokens as Opus 4.6 for the same text.
The specs: a 1M-token context window, up to 128K output tokens, text and image input, and text output. Reliable knowledge runs through January 2026. Thinking is adaptive only and off unless you enable it. The older budget_tokens mode and non-default temperature, top_p and top_k values return an error. The minimum cacheable prompt is 2,048 tokens. Opus 4.7 also shipped real-time cybersecurity safeguards that can decline prohibited or high-risk security requests.
Opus 4.8 accepts exactly the same requests, so moving up is a model ID change. Keep Opus 4.7 when agents, prompts or evals are validated on it and you want pinned behavior until you re-test. Anthropic's current retirement date for it is not sooner than April 16, 2027.
Strengths
Where Claude Opus 4.7 shines. And what teams build with it.
High-resolution vision
Reads screenshots, documents and charts at up to 2,576 pixels on the long edge, with coordinates that map 1:1 to image pixels.
Scoped, predictable work
It respects low and medium effort strictly and scopes work to what was asked, which suits tuned pipelines and structured extraction.
Fine-grained effort
Five effort levels, including the xhigh level it introduced, let you set cost and depth per route.
Use cases
Pinned production agents
Keep an agent that passed your evals on Opus 4.7 running unchanged while you test newer Opus models on the same key.
Screenshot and document analysis
Extract text, numbers and layout from dense screenshots, scanned pages and charts at full resolution.
Structured extraction
Turn documents into JSON with predictable scope, using low or medium effort to keep simple calls cheap.
Difficult coding tasks
Hand off multi-step fixes and features that need rigor, and let the model check its output before it reports back.
Get started
Call Claude Opus 4.7 in three steps.
No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.
- 1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
- 2
Point your SDK at zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1 - 3
Use claude-opus-4-7
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
claude-opus-4-7
Works with the tools you already use
Compare
Similar models. All on the same key.
65%off
Claude Opus 4.8
$1.75 / $8.75 per 1M tokens
Pick Claude Opus 4.8 at the same list price: it takes the same requests, catches more flaws in its own code and uses a smaller tool-use system prompt.
Claude Opus 4.8 API65%off
Claude Opus 4.6
$1.75 / $8.75 per 1M tokens
Pick Claude Opus 4.6 if you still need temperature, top_p, top_k or budget_tokens thinking, or its older tokenizer, which uses fewer tokens for the same text.
Claude Opus 4.6 API65%off
Claude Opus 5
$1.75 / $8.75 per 1M tokens
Pick Claude Opus 5 at the same list price for stronger results on hard coding and research, with thinking on by default.
Claude Opus 5 APIFAQ
Claude Opus 4.7 API questions.
Anything else, write to sales@zurelay.com and an engineer will answer.
What is Claude Opus 4.7 API pricing on zurelay?
zurelay charges $1.78 per 1M input tokens and $8.93 per 1M output tokens, with cached input at $0.178. Anthropic's list price for Claude Opus 4.7 is $5.00 input and $25.00 output, so you save 64%. The rate is the same at every prompt length, and you pay from prepaid credit with no subscription.
Is there a cheaper Claude Opus 4.7 API than Anthropic's?
Yes. zurelay serves claude-opus-4-7 at 64% below Anthropic's list price. It is the same model, not a smaller substitute. You keep your code and change the base URL and API key.
How do I call the Claude Opus 4.7 API with the OpenAI SDK?
Create a zurelay API key, set the base URL to https://api.zurelay.com/v1 and set the model to claude-opus-4-7. Chat completions, streaming and tool calls use the request shapes you already know. Leave out temperature, top_p and top_k: Opus 4.7 rejects non-default sampling values, and some frameworks set them for you.
Can I use Claude Opus 4.7 with the Anthropic SDK or Claude Code?
Yes. Set the Anthropic SDK base URL, or ANTHROPIC_BASE_URL for Claude Code, to https://api.zurelay.com with no /v1, because the client adds /v1/messages itself. Authenticate with your zurelay key and select claude-opus-4-7. For thinking, send the adaptive thinking type; budget_tokens returns an error on this model.
What is the Claude Opus 4.7 context window?
Claude Opus 4.7 has a 1M-token context window and returns up to 128K output tokens per request. On its tokenizer, 1M tokens is roughly 555k English words. At xhigh or max effort, give it a large output limit, starting around 64K tokens, and stream the response.
What is Claude Opus 4.7 best at?
Hard software engineering and long-running tasks that need rigor, plus vision work on dense screenshots, charts and documents. It follows the scope of a prompt closely, which suits pipelines with carefully tuned instructions. For new projects, Opus 4.8 takes the same requests and is the stronger model.
Why does Claude Opus 4.7 use more tokens than Opus 4.6?
Opus 4.7 introduced a new tokenizer, and Anthropic says the same text can map to roughly 1.0 to 1.35 times as many tokens, depending on content. Full-resolution images can also use up to about 3 times more image tokens, up to 4,784 per image. Re-check output limits and cost estimates when you switch, and downsample images you do not need at full detail.
Does the zurelay Claude Opus 4.7 API support streaming, and what are the limits?
Yes. Streaming is supported, and on chat completions you can set stream_options.include_usage to get token counts in the final chunk. Each key can carry its own monthly budget and requests-per-minute cap. If a route fails, zurelay retries the request on another route, and failed requests are never billed.
Is Claude Opus 4.7 on zurelay the same model as on Anthropic's API?
Yes. Requests to claude-opus-4-7 run on Claude Opus 4.7 itself, not a smaller or different model. Outputs are sampled, so exact wording can differ between calls on any API, including Anthropic's. zurelay is an independent service and is not affiliated with or endorsed by Anthropic.
More models on zurelay
All models- Claude Opus 5.5 API$1.40 / $7.00 per 1M tokens−65%
- GPT-6 Astra API$2.50 / $12.50 per 1M tokens−75%
- Nano Banana Pro APIfrom $0.035 per image−74%
- Nano Banana 2 APIfrom $0.025 per image−63%
- Claude Sonnet 5.5 API$0.80 / $4.00 per 1M tokens−60%
- GPT-6.1 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Luna API$0.025 / $0.125 per 1M tokens−75%
- Grok 4.7 API$0.70 / $2.10 per 1M tokens−65%
- MiMo V2.6 Pro API$0.18 / $0.36 per 1M tokens−59%
- MiMo V2.6 Flash API$0.06 / $0.12 per 1M tokens−57%
- DeepSeek V4.1 Flash API$0.037 / $0.15 per 1M tokens−88%
- DeepSeek V4 Flash API$0.045 / $0.18 per 1M tokens−85%
- DeepSeek V4 Flash 0731 API$0.022 / $0.06 per 1M tokens−61%
- DeepSeek V4 Pro 0813 API$0.23 / $0.62 per 1M tokens−84%
- Claude Fable 5.1 API$3.50 / $17.50 per 1M tokens−65%
- Claude Fable 5 API$3.50 / $17.50 per 1M tokens−65%
- Claude Opus 5 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.8 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.6 API$1.75 / $8.75 per 1M tokens−65%
- Claude Haiku 4.5 API$0.38 / $1.90 per 1M tokens−62%
- GPT-5.6 Sol API$1.14 / $5.70 per 1M tokens−72%
- GPT-5.6 Terra API$0.54 / $3.26 per 1M tokens−73%
- GPT-5.6 Luna API$0.08 / $0.49 per 1M tokens−59%
- Gemini 3.7 Flash API$0.32 / $1.59 per 1M tokens−58%
- Gemini 3.5 Flash-Lite API$0.12 / $1.04 per 1M tokens−58%
- Gemini 3.1 Flash-Lite API$0.10 / $0.59 per 1M tokens−61%
- GLM-5.3 API$0.38 / $1.21 per 1M tokens−73%
- GLM-5.2 API$0.38 / $1.21 per 1M tokens−73%
- Kimi K3 API$1.27 / $6.37 per 1M tokens−58%
- Qwen 3.8 Max API$1.20 / $3.60 per 1M tokens−40%
- Qwen 3.8 Flash API$0.07 / $0.22 per 1M tokens−53%
- Qwen 3.8 Omni Flash API$0.075 / $0.235 per 1M tokens−50%
- HY4 Preview API$0.40 / $1.20 per 1M tokens−52%
- MiniMax M2.7 API$0.13 / $0.51 per 1M tokens−57%
- GPT Image 2.5 Flare API$0.02 per image−62%
- GPT Image 2.5 Sunburst API$0.02 per image−62%
- GPT Image 2 API$0.02 per image−62%
- Seedance 2.5 APIfrom $0.14 per secondVideo
- Seedance 2.0 APIfrom $0.097 per secondVideo
- Seedance 2.0 Fast APIfrom $0.074 per secondVideo
- Seedance 2.0 Mini APIfrom $0.047 per secondVideo
Stop paying list price.
Start saving today.
Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.