Language models · Anthropic

Claude API: every Claude model on one key

Every Claude model Anthropic ships to its API, 20 on Revana today, through one OpenAI-compatible endpoint. Point any OpenAI SDK at https://api.revana.si/v1, name the model, and pay per token from prepaid credit, up to 44% below Anthropic’s list price on the newest models. A request that gets no answer costs $0.00.

Claude Opus 5.5 $2.24 in / $11.20 out per 1M tokens, 44% below Anthropic’s $4.00 / $20.00
Claude Sonnet 5.5 $1.12 in / $5.60 out per 1M tokens, 44% below Anthropic’s $2.00 / $10.00
Claude Haiku 5.5 $0.056 in / $0.28 out per 1M tokens, 44% below Anthropic’s $0.10 / $0.50
Revana prices as of November 2026; Anthropic list prices read 2026-11-16 from platform.claude.com.

Every Claude model and what it costs

USD per million tokens on Revana as of November 2026. Click a model for its full price sheet, cache-write rates and code. Reasoning and thinking tokens bill as output.

Claude Opus

The top tier, for hard code changes, planning and long agent runs. 8 models on Revana, USD per million tokens.

Opus prices
ModelInputCached inputOutputContextAnthropic list (in / out)Revana vs list
Claude Opus 5.5
claude-opus-5-5
$2.24$0.112$11.201M$4.00 / $20.0044% below
Claude Opus 5
claude-opus-5
$2.80$0.28$14.001M$5.00 / $25.0044% below
Claude Opus 4.8
claude-opus-4-8
$2.80$0.28$14.001M$5.00 / $25.0044% below
Claude Opus 4.7
claude-opus-4-7
$7.20$0.72$36.00128K––
Claude Opus 4.6 (thinking)
claude-opus-4-6-thinking
$7.20$7.20$36.00–––
Claude Opus 4.6
claude-opus-4-6
$7.20$0.72$14.401M––
Claude Opus 4.5 (thinking)
claude-opus-4-5-20251101-thinking
$7.20$7.20$36.00–––
Claude Opus 4.5
claude-opus-4-5-20251101
$7.20$7.20$36.00–––

Claude Sonnet

The middle tier most production apps run on. 6 models on Revana, USD per million tokens.

Sonnet prices
ModelInputCached inputOutputContextAnthropic list (in / out)Revana vs list
Claude Sonnet 5.5
claude-sonnet-5-5
$1.12$0.056$5.601M$2.00 / $10.0044% below
Claude Sonnet 5
claude-sonnet-5
$1.12$0.112$5.601M$2.00 / $10.0044% below
Claude Sonnet 4.6 (thinking)
claude-sonnet-4-6-thinking
$4.32$4.32$21.60–––
Claude Sonnet 4.6
claude-sonnet-4-6
$4.32$0.432$21.60128K––
Claude Sonnet 4.5 (thinking)
claude-sonnet-4-5-20250929-thinking
$4.32$4.32$21.60–––
Claude Sonnet 4.5
claude-sonnet-4-5-20250929
$4.32$0.432$21.60128K––

Claude Haiku

The fast, low-cost tier for routing, tagging and short replies. 3 models on Revana, USD per million tokens.

Haiku prices
ModelInputCached inputOutputContextAnthropic list (in / out)Revana vs list
Claude Haiku 5.5
claude-haiku-5-5
$0.056$0.0056$0.281M$0.10 / $0.5044% below
Claude Haiku 4.5 (thinking)
claude-haiku-4-5-20251001-thinking
$1.44$1.44$7.20–––
Claude Haiku 4.5
claude-haiku-4-5-20251001
$1.44$0.144$7.20128K––

Claude Fable

Anthropic’s Fable models, its most expensive line. 3 models on Revana, USD per million tokens.

Fable prices
ModelInputCached inputOutputContextAnthropic list (in / out)Revana vs list
Claude Fable 5.2
claude-fable-5-2
$4.48$0.112$22.401M$8.00 / $40.0044% below
Claude Fable 5.1
claude-fable-5-1
$5.60$0.14$28.001M$10.00 / $50.0044% below
Claude Fable 5
claude-fable-5
$5.60$0.56$28.001M$10.00 / $50.0044% below

Revana against Anthropic’s list price

The 9 Claude models where both of Revana’s per-token prices are below Anthropic’s own list. The last two columns price 1,000 requests that each read 3,000 tokens and write 500, a typical chat or support call. Anthropic list prices from https://platform.claude.com/docs/en/about-claude/pricing, read 2026-11-16.

Revana vs Anthropic list
ModelAnthropic list (in / out)Revana (in / out)Below by1,000 calls at Anthropic1,000 calls on Revana
Claude Sonnet 5.5$2.00 / $10.00$1.12 / $5.6044%$11.00$6.16
Claude Opus 5.5$4.00 / $20.00$2.24 / $11.2044%$22.00$12.32
Claude Haiku 5.5$0.10 / $0.50$0.056 / $0.2844%$0.55$0.31
Claude Sonnet 5$2.00 / $10.00$1.12 / $5.6044%$11.00$6.16
Claude Opus 5$5.00 / $25.00$2.80 / $14.0044%$27.50$15.40
Claude Opus 4.8$5.00 / $25.00$2.80 / $14.0044%$27.50$15.40
Claude Fable 5.2$8.00 / $40.00$4.48 / $22.4044%$44.00$24.64
Claude Fable 5.1$10.00 / $50.00$5.60 / $28.0044%$55.00$30.80
Claude Fable 5$10.00 / $50.00$5.60 / $28.0044%$55.00$30.80

Older Claude models are not in this table because they cost more on Revana than at Anthropic. Same model, same answer: Revana passes the request to Anthropic’s model unchanged.

Match the Claude model to the job

What a workload costs on Revana at today’s prices, worked out from the token rates above.

Coding agents

100 agent steps that each read 40K tokens (30K of them cached) and write 2K: Claude Opus 5.5: $4.82 · Claude Haiku 5.5: $0.13. Claude Haiku 5.5 costs 97% less for this job. Send planning and hard edits to Opus and let Haiku handle tool routing and short checks: one key, one balance, a different model name per step.

Support and chat replies

1,000 replies that each read 3,000 tokens and write 500: Claude Haiku 5.5: $0.31 · Claude Sonnet 5.5: $6.16. Claude Haiku 5.5 costs 95% less for this job. Answer the easy questions on Haiku and pass the ones that need care to Sonnet.

Long documents

1 question about a 200K-token contract or codebase: Claude Sonnet 5.5: $0.23 · Claude Opus 5.5: $0.46. Claude Sonnet 5.5 costs 50% less for this job. Put the document first and the question last: the next question about the same document reads it from the cache at the cached rate.

Batch extraction and tagging

10,000 records that each read 800 tokens and write 100: Claude Haiku 5.5: $0.73. Set max_tokens low so each request holds only what it needs, and try a sample on two models before the full run.

Call Claude with the code you already have

Two settings change: the base URL and the key. Messages, tools, response_format and streaming stay in the OpenAI format, and switching to another Claude model, or another maker’s, is a change to the model field.

curl
curl https://api.revana.si/v1/chat/completions \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-5-5","messages":[{"role":"user","content":"Write a haiku about routing."}]}'
Python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.revana.si/v1", api_key=os.environ["REVANA_API_KEY"])
reply = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[{"role": "user", "content": "Write a haiku about routing."}],
)
print(reply.choices[0].message.content)
print(reply.usage.cost_usd)  # what this request cost, in USD
Node.js
import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://api.revana.si/v1", apiKey: process.env.REVANA_API_KEY })
const reply = await client.chat.completions.create({
  model: "claude-sonnet-5-5",
  messages: [{ role: "user", content: "Write a haiku about routing." }],
})
console.log(reply.choices[0].message.content, reply.usage.cost_usd)

The answer is OpenAI’s chat.completion object, and usage.cost_usd is the exact amount taken from your balance. For 3,000 tokens in and 500 out on Claude Sonnet 5.5:

Response
{
  "id": "chat_3f9c…",
  "object": "chat.completion",
  "model": "claude-sonnet-5-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "…"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 3000,
    "completion_tokens": 500,
    "total_tokens": 3500,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "cost_usd": 0.00616
  }
}

Send "stream": true for server-sent events, and "stream_options": {"include_usage": true} to get the cost in the last chunk. Every field is in the chat completions docs.

Pay only for the answers you get

  • Automatic fallback. A model with more than one route starts on its lowest-cost route; a busy or failed route hands the request to the next before any answer is sent. Each model page shows its routes.
  • Held, then charged. While a request runs, Revana holds its prompt plus max_tokens (8,192 output tokens when you set none). When it ends the hold is released and only the tokens used are charged.
  • No answer costs $0.00. If every route fails you get an OpenAI-shaped error and no charge; 503 model_busy is never billed, so a short retry is safe.
  • Backup routes stay under the hold. When a model’s listed route is busy, a backup can cost more; you are charged that route’s cost, never more than the hold, and it is always in cost_usd.

Make images and video from Claude Code, Cursor and ChatGPT

  • Connect the Revana MCP server to Claude Code, Claude Desktop, claude.ai, Cursor, VS Code, Codex CLI or ChatGPT, and your agent can quote, generate and download images and video on your credit.
  • Every language model and its price is published as llms.json and through GET /v1/models, so code can pick a model by price at run time.
  • Any tool that sends HTTP works too, such as n8n’s HTTP Request node: POST https://api.revana.si/v1/chat/completions with your key as a Bearer token.

Images and video without another account

Have Claude write the script, shot list or image prompt, then send it to an image or video model on Revana with the same key and the same prepaid balance. One integration, one bill.

Media models on the same key
ModelKindFrom
Nano Banana Proimage$0.04 an image
Veo 3.1video$0.20 a second
Seedance 2.5video$0.059 a second
Kling 4.0video$0.08 a second

Every image, video and audio model and its price is at revana.si/models. A generation that fails costs nothing.

From signup to your first Claude call

  1. Create a key. Sign up and create an API key in the dashboard. It works with every language, image and video model.
  2. Add prepaid credit. Packs start at $10 and 100 credits are $1. Credit never expires; no subscription or monthly minimum.
  3. Send the sample request. Copy the curl above, set your key, and read the answer and its cost_usd.

FAQ

How do I access the Claude API through Revana?

Create a Revana API key, add prepaid credit and point any OpenAI SDK at https://api.revana.si/v1 with a Claude model id such as claude-sonnet-5-5. Revana passes the request to Anthropic's model unchanged and returns the answer in the OpenAI format, with what it cost.

How much does Claude cost per million tokens?

On Revana, Claude runs from $0.056 in and $0.28 out per million tokens (Claude Haiku 5.5) to $7.20 in and $36.00 out (Claude Opus 4.7), prices as of November 2026. Every model and its cached rate is in the table on this page.

Is Claude cheaper on Revana than on Anthropic?

For the newer models, yes: Claude Haiku 5.5 costs $0.056 in and $0.28 out against $0.10 and $0.50 (44% below); Claude Opus 5.5 costs $2.24 in and $11.20 out against $4.00 and $20.00 (44% below); Claude Sonnet 5.5 costs $1.12 in and $5.60 out against $2.00 and $10.00 (44% below). Anthropic's list prices were read on 2026-11-16. Older models (Claude Haiku 4.5, Claude Opus 4.5 and Claude Opus 4.6) cost more on Revana than at Anthropic, so keep those on Anthropic's own API if price is what matters.

What is the difference between Claude, Claude Code and the Claude API?

Claude is Anthropic's chat app, Claude Code is its coding agent, and the API is how your own software calls Claude models and pays per token. Through Revana you call the same models with an OpenAI-compatible request and one prepaid balance.

Does prompt caching work through Revana?

Yes. Automatic prompt caching works as it does at Anthropic and cached tokens are billed at each model's cached rate. Explicit cache_control markers are removed from the request, so keep a stable prompt prefix to get the most from the cache.

Do I need an Anthropic account?

No. A Revana key and prepaid credit are enough. Keys, usage and billing live in your Revana dashboard next to your image and video jobs, and credit never expires.

Which Claude features are not supported?

The Revana chat endpoint takes text, pictures as image_url and function tools. Web search, audio, files, video input and built-in tools are refused with 400 unsupported_parameter, so keep those on Anthropic's API if you rely on them.

Start with one API key

One key for every language, image, video and audio model on Revana. Prepaid credit, no subscription, and a request that fails costs nothing.