Anthropic · Llm model

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5).
Claude AI on Coinis.

Sonnet, Opus, and Haiku with one API key.

Generate on Coinis Read the docs

One API key. Every model.

per 1m tokens
Example
AI text
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5).

One model. Three ways to call it. Same key, same bill.

IN

Llm

One call. Same key. Same bill.

$5.1 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$25.5 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$8.5 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$42.5 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$1.7 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$8.5 / 1m tokens

Capabilities

What it does best.

Claude AI capabilities

Context windows

  • Claude Sonnet 4.6 and Claude Opus 4.7 support a 1M-token context window at standard per-token pricing[^1]
  • Claude Haiku 4.5 supports a 200K-token context window[^2]

Reasoning and coding

  • Claude Opus 4.7 is built for long-running asynchronous agents, large codebases, multi-stage debugging, and end-to-end project orchestration[^3]
  • Claude Sonnet 4.6 excels at iterative development, codebase navigation, document creation, and computer-use workflows[^4]
  • Claude Haiku 4.5 introduces extended thinking to the Haiku line and scores above 73% on SWE-bench Verified[^5]

Tool use

  • All three tiers support server-side tools: web search, web fetch, bash, text editor, code execution, and computer use[^6]

Cost optimizations

  • Prompt caching: cache-hit reads cost 10% of the standard input price, cutting repeated large-context call costs sharply[^7]
  • Batch API: 50% discount on both input and output tokens for asynchronous, non-time-sensitive workloads across all Claude 4.x models[^8]

Tokenizer note

  • Claude Opus 4.7 uses a new tokenizer that may consume up to 35% more tokens for the same text compared to prior Claude generations. Factor this into migration cost estimates[^9]
API

Call Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5) in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/llm/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.llm.generate({
  model: "models/anthropic/claude-sonnet-4",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.llm.generate(
    model="models/anthropic/claude-sonnet-4",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/anthropic/claude-sonnet-4",
  "output": {
    "image_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5) · IN
51 tokens
per 1m tokens · $5.10
Frontier LLM
$5.10 / 1m tokens
One key. Every model. One invoice. 1 token = $0.10
1 1m tokens ≈ 51 tokens ($5.10)
Budget variant: IN · $1.70 / 1m tokens
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

IN

Final renders, studios
Resolution —
Price $5.1 / 1m tokens

OUT

Rapid tests, high volume
Resolution —
Price $25.5 / 1m tokens
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Autonomous coding agents and long-running tasks. Claude Opus 4.7 Point Opus 4.7 at a multi-step engineering problem and walk away. It is designed for asynchronous pipelines where tasks unfold over time, across large codebases and multi-stage debugging runs.[^3]

Codebase navigation, refactoring, and document drafting. Claude Sonnet 4.6 Sonnet 4.6 covers the daily workload: iterative code review, refactoring, navigation across a live repo, and producing polished written deliverables from a long brief.[^4]

Long-context research and analysis over 500K-token corpora. Claude Sonnet 4.6 Load an entire contract set, financial dataset, or research corpus into the 1M-token window. Sonnet 4.6 ranks highly in Finance, Legal, Health, and Academia categories for deep-context analysis.[^10]

High-volume support ticket automation and orchestration sub-agents. Claude Haiku 4.5 Haiku 4.5 is the fast, low-cost tier built for parallelized sub-agent execution and real-time chat. Route compliance checks, ticket classification, and ad copy generation through it to keep pipeline costs low.[^11]

Real-time chat and latency-sensitive UX. Claude Haiku 4.5 When response speed matters more than depth, Haiku 4.5 delivers extended thinking at a fraction of the cost of upper tiers. It is the right choice for consumer-facing chat interfaces and live orchestration hops.[^5]

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5) FAQs

How much does the Claude API cost on Coinis vs Anthropic direct?

On Coinis, Claude Sonnet 4.6 is priced at $5.10 per 1M input tokens and $25.50 per 1M output tokens. Claude Opus 4.7 is $8.50 per 1M input and $42.50 per 1M output. Claude Haiku 4.5 is $1.70 per 1M input and $8.50 per 1M output. Anthropic direct API pricing is $3/$15, $5/$25, and $1/$5 respectively. The Coinis platform markup covers unified billing, a single API key across all models, and managed infrastructure.

What is the difference between Claude Sonnet 4.6, Opus 4.7, and Haiku 4.5?

Sonnet 4.6 is the balanced workhorse. It handles iterative coding, document creation, and computer use inside a 1M-token window. Opus 4.7 is the top tier for long-running autonomous agents, complex multi-step reasoning, and large codebase orchestration, also at 1M context. Haiku 4.5 is the fast, low-cost tier with a 200K-token window, extended thinking, and a score above 73% on SWE-bench Verified. Match the tier to the workload and you pay only for what you need.

Which Claude model should I pick for coding agents?

Use Claude Opus 4.7 for fully autonomous, long-running agent pipelines that need to plan, debug, and execute across large codebases over time. Use Claude Sonnet 4.6 when the agent loop is shorter and you want the best cost-to-capability ratio. Use Claude Haiku 4.5 as an orchestration sub-agent for high-frequency, low-complexity hops inside a larger pipeline.

Does Coinis support Claude's 1M-token context window?

Yes. Claude Sonnet 4.6 and Claude Opus 4.7 both support a 1M-token context window on Coinis, billed at the standard per-token rate. A 900K-token request is billed at the same per-token rate as a 9K-token request. Claude Haiku 4.5 supports 200K tokens.

Can I use prompt caching and the Batch API discount through Coinis?

Prompt caching and the Batch API are Anthropic-side features billed by the vendor. Cache-hit reads cost 10% of the standard input price. The Batch API provides a 50% discount on input and output tokens for asynchronous workloads. Check the Coinis pricing page and the official Anthropic docs to confirm which optimizations are passed through on your plan.

Is Claude Haiku 4.5 cheap enough for high-volume support automation?

Haiku 4.5 is priced at $1.70 per 1M input tokens and $8.50 per 1M output tokens on Coinis, making it the most affordable tier in the Claude family. It supports parallelized sub-agent execution and real-time chat, and is used inside Coinis's own compliance, script, and ad copy flows. For high-volume support ticket pipelines, the Batch API discount reduces effective token costs further.

Why does Opus 4.7 use more tokens than older Claude models for the same text?

Claude Opus 4.7 and later models use a new tokenizer that can consume up to 35% more tokens for the same fixed text compared to prior Claude generations. This directly affects cost when migrating from Claude Opus 4 or earlier. Re-benchmark your typical prompt lengths against the new tokenizer before migrating to get an accurate cost estimate. The official Anthropic pricing docs cover this in detail.

Related

Pair it with.

ChatGPT API / GPT-5.4

Model

DeepSeek V4 Flash

Model

Gemini 3.1 / 2.5

Model

All LLM models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .