TokenRex
Models & PricingFeaturesIntegrationsDocsFAQ
Get API
Home/Features/Native Claude API
Feature

Native Claude API

Call Claude models in the Anthropic Messages format, with Claude Code support.

Claude models on TokenRex are served in Anthropic's own Messages format, so the official Anthropic SDK and Claude Code work by simply pointing them at TokenRex. Thinking summaries, PDF and image inputs, and your own tools are all supported — no translation layer, no lost features.

Format
Anthropic Messages
Models
Opus 5.5 · Fable 5.1 · Sonnet 5 · Haiku 4.5
Tools
Claude Code ready

What you get

  • Works with the official Anthropic SDK
  • Streaming responses with thinking summaries
  • PDF and image inputs supported
  • Claude Code connects with one environment variable
  • Same wallet and keys as every other model

Common use cases

Claude CodeDocument analysisAgents with toolsLong-context reasoningCoding assistants

How it works

  1. 1
    Create your account and key
    Sign up, top up your wallet and generate an API key from the dashboard.
  2. 2
    Point the Anthropic SDK at TokenRex
    Set the base URL to the TokenRex endpoint and use your TokenRex key.
  3. 3
    Call Claude models
    Use the Messages API exactly as documented by Anthropic — streaming, tools and thinking included.
  4. 4
    Track spend
    Every request appears in your dashboard with tokens, cost and latency.

Code examples

1
2
3
4
5
6
7
8
9
10
11
12
13
import anthropic

client = anthropic.Anthropic(
    api_key="sk-tb-YOUR_KEY",
    base_url="https://tokenrex.ai/api/public",
)

msg = client.messages.create(
    model="claude-fable-5-1",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(msg.content[0].text)

Frequently asked questions

Does the official Anthropic SDK work?

Yes. Set the SDK's base URL to TokenRex and use your TokenRex key — no code changes beyond that.

Does Claude Code work?

Yes. Claude Code connects through the Anthropic format; see the Claude Code integration guide for the exact configuration.

Are thinking summaries supported?

Yes, on Claude models that support thinking, with streaming.

Related features

OpenAI-compatible API

Keep the OpenAI SDK. Swap the base URL and key. Ship in minutes.

Every frontier model, one endpoint

GPT-6 Astra, Claude Opus 5.5, Claude Fable 5.1, Gemini 3.8 and more — one key, one wallet.

Secure API keys

Hashed keys, per-key limits and model permissions. Revoke any key instantly.

Get API key Models & PricingCost calculatorAPI documentation
All featuresNext: Video generation

Live pricing & comparison

Claude models at live market prices — filter the table for the Claude family.

Chat

ModelInputOutput / unit
chat-latest

Latest Instant model used in ChatGPT — natural conversation

$5.00$30.00Details
claude-fable-5-1

Claude Fable 5.1 with medium thinking (default)

$10.00$50.00Details
claude-fable-5-1-high

Claude Fable 5.1 with high thinking — deeper reasoning

$10.00$50.00Details
claude-fable-5-1-low

Claude Fable 5.1 with low thinking — fastest, cheapest per answer

$10.00$50.00Details
claude-fable-5-1-xhigh

Claude Fable 5.1 with extra-high thinking — deepest reasoning

$10.00$50.00Details
claude-haiku-4-5

Claude Haiku 4.5 with medium thinking (default)

$1.00$5.00Details
claude-haiku-4-5-high

Claude Haiku 4.5 with high thinking — deeper reasoning

$1.00$5.00Details
claude-haiku-4-5-low

Claude Haiku 4.5 with low thinking — fastest, cheapest per answer

$1.00$5.00Details
claude-haiku-4-5-xhigh

Claude Haiku 4.5 with extra-high thinking — deepest reasoning

$1.00$5.00Details
claude-opus-5

Claude Opus 5 with medium thinking (default)

$5.00$25.00Details
claude-opus-5-5

Claude Opus 5.5 with medium thinking (default)

$4.00$20.00Details
claude-opus-5-5-fast

Claude Opus 5.5 fast mode (quicker output, premium rate) with medium thinking (default)

$8.00$40.00Details
claude-opus-5-5-fast-high

Claude Opus 5.5 fast mode (quicker output, premium rate) with high thinking — deeper reasoning

$8.00$40.00Details
claude-opus-5-5-fast-low

Claude Opus 5.5 fast mode (quicker output, premium rate) with low thinking — fastest, cheapest per answer

$8.00$40.00Details
claude-opus-5-5-fast-xhigh

Claude Opus 5.5 fast mode (quicker output, premium rate) with extra-high thinking — deepest reasoning

$8.00$40.00Details
claude-opus-5-5-high

Claude Opus 5.5 with high thinking — deeper reasoning

$4.00$20.00Details
claude-opus-5-5-low

Claude Opus 5.5 with low thinking — fastest, cheapest per answer

$4.00$20.00Details
claude-opus-5-5-xhigh

Claude Opus 5.5 with extra-high thinking — deepest reasoning

$4.00$20.00Details
claude-opus-5-fast

Claude Opus 5 fast mode (quicker output, premium rate) with medium thinking (default)

$10.00$50.00Details
claude-opus-5-fast-high

Claude Opus 5 fast mode (quicker output, premium rate) with high thinking — deeper reasoning

$10.00$50.00Details
claude-opus-5-fast-low

Claude Opus 5 fast mode (quicker output, premium rate) with low thinking — fastest, cheapest per answer

$10.00$50.00Details
claude-opus-5-fast-xhigh

Claude Opus 5 fast mode (quicker output, premium rate) with extra-high thinking — deepest reasoning

$10.00$50.00Details
claude-opus-5-high

Claude Opus 5 with high thinking — deeper reasoning

$5.00$25.00Details
claude-opus-5-low

Claude Opus 5 with low thinking — fastest, cheapest per answer

$5.00$25.00Details
claude-opus-5-xhigh

Claude Opus 5 with extra-high thinking — deepest reasoning

$5.00$25.00Details
claude-sonnet-5

Claude Sonnet 5 with medium thinking (default)

$2.00$10.00Details
claude-sonnet-5-high

Claude Sonnet 5 with high thinking — deeper reasoning

$2.00$10.00Details
claude-sonnet-5-low

Claude Sonnet 5 with low thinking — fastest, cheapest per answer

$2.00$10.00Details
claude-sonnet-5-xhigh

Claude Sonnet 5 with extra-high thinking — deepest reasoning

$2.00$10.00Details
gemini-2.5-flash

Balanced Gemini 2.5

$0.30$2.50Details
gemini-2.5-flash-lite

Cheapest Gemini 2.5

$0.10$0.40Details
gemini-2.5-pro

Strong multimodal reasoning

$1.25$10.00Details
gemini-3-flash-preview

Fast Gemini preview

$0.50$3.00Details
gemini-3.1-flash-lite

Cost-efficient high volume

$0.25$1.50Details
gemini-3.1-pro-preview

Next-gen Gemini Pro reasoning

$2.00$12.00Details
gemini-3.5-flash

High-efficiency Gemini 3.5

$1.50$9.00Details
gemini-3.6-flash

High-efficiency Gemini 3.6

$0.75$3.75Details
gemini-3.7-flash

Latest Gemini Flash (default)

$0.75$3.75Details
gemini-3.8-flash

Latest-generation Gemini Flash model for fast coding, reasoning, and agentic workflows.

$0.75$3.75Details
gemini-4-argon

Frontier Gemini model for long-horizon coding, reasoning and enterprise knowledge work — 1M context, text/image/audio/video input

$2.00$10.00Details
gpt-5

Powerful multimodal all-rounder

$1.25$10.00Details
gpt-5-high

GPT-5 with high thinking — deeper reasoning

$1.25$10.00Details
gpt-5-low

GPT-5 with low thinking — fastest replies, lowest cost

$1.25$10.00Details
gpt-5-mini

Fast, affordable GPT-5

$0.25$2.00Details
gpt-5-mini-high

GPT-5 Mini with high thinking — deeper reasoning

$0.25$2.00Details
gpt-5-mini-low

GPT-5 Mini with low thinking — fastest replies, lowest cost

$0.25$2.00Details
gpt-5-mini-xhigh

GPT-5 Mini with extra-high thinking — deepest reasoning

$0.25$2.00Details
gpt-5-nano

Ultra-cheap GPT-5 for simple tasks

$0.05$0.40Details
gpt-5-nano-high

GPT-5 Nano with high thinking — deeper reasoning

$0.05$0.40Details
gpt-5-nano-low

GPT-5 Nano with low thinking — fastest replies, lowest cost

$0.05$0.40Details
gpt-5-nano-xhigh

GPT-5 Nano with extra-high thinking — deepest reasoning

$0.05$0.40Details
gpt-5-xhigh

GPT-5 with extra-high thinking — deepest reasoning

$1.25$10.00Details
gpt-5.2

Complex reasoning & problem solving

$1.75$14.00Details
gpt-5.2-high

GPT-5.2 with high thinking — deeper reasoning

$1.75$14.00Details
gpt-5.2-low

GPT-5.2 with low thinking — fastest replies, lowest cost

$1.75$14.00Details
gpt-5.2-xhigh

GPT-5.2 with extra-high thinking — deepest reasoning

$1.75$14.00Details
gpt-5.4

Affordable frontier model

$2.50$15.00Details
gpt-5.4-high

GPT-5.4 with high thinking — deeper reasoning

$2.50$15.00Details
gpt-5.4-low

GPT-5.4 with low thinking — fastest replies, lowest cost

$2.50$15.00Details
gpt-5.4-mini

Strong mini for high volume

$0.75$4.50Details
gpt-5.4-mini-high

GPT-5.4 Mini with high thinking — deeper reasoning

$0.75$4.50Details
gpt-5.4-mini-low

GPT-5.4 Mini with low thinking — fastest replies, lowest cost

$0.75$4.50Details
gpt-5.4-mini-xhigh

GPT-5.4 Mini with extra-high thinking — deepest reasoning

$0.75$4.50Details
gpt-5.4-nano

Cheapest GPT-5.4 for simple tasks

$0.20$1.25Details
gpt-5.4-nano-high

GPT-5.4 Nano with high thinking — deeper reasoning

$0.20$1.25Details
gpt-5.4-nano-low

GPT-5.4 Nano with low thinking — fastest replies, lowest cost

$0.20$1.25Details
gpt-5.4-nano-xhigh

GPT-5.4 Nano with extra-high thinking — deepest reasoning

$0.20$1.25Details
gpt-5.4-pro

Premium GPT-5.4 deep reasoning

$30.00$180.00Details
gpt-5.4-pro-high

GPT-5.4 Pro with high thinking — deeper reasoning

$30.00$180.00Details
gpt-5.4-pro-xhigh

GPT-5.4 Pro with extra-high thinking — deepest reasoning

$30.00$180.00Details
gpt-5.4-xhigh

GPT-5.4 with extra-high thinking — deepest reasoning

$2.50$15.00Details
gpt-5.5

Frontier coding & analysis

$5.00$30.00Details
gpt-5.5-high

GPT-5.5 with high thinking — deeper reasoning

$5.00$30.00Details
gpt-5.5-low

GPT-5.5 with low thinking — fastest replies, lowest cost

$5.00$30.00Details
gpt-5.5-pro

Extended-reasoning GPT-5.5 Pro

$30.00$180.00Details
gpt-5.5-pro-high

GPT-5.5 Pro with high thinking — deeper reasoning

$30.00$180.00Details
gpt-5.5-pro-xhigh

GPT-5.5 Pro with extra-high thinking — deepest reasoning

$30.00$180.00Details
gpt-5.5-xhigh

GPT-5.5 with extra-high thinking — deepest reasoning

$5.00$30.00Details
gpt-5.6-luna

Fast, low-cost GPT-5.6

$0.20$1.20Details
gpt-5.6-luna-high

GPT-5.6 Luna with high thinking — deeper reasoning

$0.20$1.20Details
gpt-5.6-luna-low

GPT-5.6 Luna with low thinking — fastest replies, lowest cost

$0.20$1.20Details
gpt-5.6-luna-xhigh

GPT-5.6 Luna with extra-high thinking — deepest reasoning

$0.20$1.20Details
gpt-5.6-sol

Flagship GPT-5.6 reasoning & agentic

$4.00$20.00Details
gpt-5.6-sol-high

GPT-5.6 Sol with high thinking — deeper reasoning

$4.00$20.00Details
gpt-5.6-sol-low

GPT-5.6 Sol with low thinking — fastest replies, lowest cost

$4.00$20.00Details
gpt-5.6-sol-xhigh

GPT-5.6 Sol with extra-high thinking — deepest reasoning

$4.00$20.00Details
gpt-5.6-terra

Balanced everyday GPT-5.6

$2.00$12.00Details
gpt-5.6-terra-high

GPT-5.6 Terra with high thinking — deeper reasoning

$2.00$12.00Details
gpt-5.6-terra-low

GPT-5.6 Terra with low thinking — fastest replies, lowest cost

$2.00$12.00Details
gpt-5.6-terra-xhigh

GPT-5.6 Terra with extra-high thinking — deepest reasoning

$2.00$12.00Details
gpt-6-astra

OpenAI's most capable model for complex reasoning, coding and research — balanced thinking

$10.00$50.00Details
gpt-6-astra-fast

GPT-6 Astra on priority serving for faster replies — 2x price, balanced thinking

$20.00$100.00Details
gpt-6-astra-fast-high

GPT-6 Astra on priority serving with high thinking — 2x price

$20.00$100.00Details
gpt-6-astra-fast-low

GPT-6 Astra on priority serving with low thinking — 2x price

$20.00$100.00Details
gpt-6-astra-fast-xhigh

GPT-6 Astra on priority serving with extra-high thinking — 2x price

$20.00$100.00Details
gpt-6-astra-high

GPT-6 Astra with high thinking — deeper reasoning for hard problems

$10.00$50.00Details
gpt-6-astra-low

GPT-6 Astra with low thinking — quicker replies, same price

$10.00$50.00Details
gpt-6-astra-xhigh

GPT-6 Astra with extra-high thinking — deepest reasoning, slowest

$10.00$50.00Details
gpt-6-luna

Low-cost GPT-6 model from OpenAI

$0.10$0.50Details
gpt-6-luna-high

GPT-6 Luna with high thinking — deeper reasoning

$0.10$0.50Details
gpt-6-luna-low

GPT-6 Luna with low thinking — fastest replies, lowest cost

$0.10$0.50Details
gpt-6-luna-xhigh

GPT-6 Luna with extra-high thinking — deepest reasoning

$0.10$0.50Details
gpt-6-sol

OpenAI's mid-tier GPT-6 model — strong reasoning at a lower price, balanced thinking

$2.00$10.00Details
gpt-6-sol-fast

GPT-6 Sol on priority serving for faster replies — 2x price, balanced thinking

$4.00$20.00Details
gpt-6-sol-fast-high

GPT-6 Sol on priority serving with high thinking — 2x price

$4.00$20.00Details
gpt-6-sol-fast-low

GPT-6 Sol on priority serving with low thinking — 2x price

$4.00$20.00Details
gpt-6-sol-fast-xhigh

GPT-6 Sol on priority serving with extra-high thinking — 2x price

$4.00$20.00Details
gpt-6-sol-high

GPT-6 Sol with high thinking — deeper reasoning for hard problems

$2.00$10.00Details
gpt-6-sol-low

GPT-6 Sol with low thinking — quicker replies, same price

$2.00$10.00Details
gpt-6-sol-xhigh

GPT-6 Sol with extra-high thinking — very deep reasoning

$2.00$10.00Details
gpt-6.1-sol

Near-Astra performance for complex coding and professional work — balanced thinking

$2.00$10.00Details
gpt-6.1-sol-fast

GPT-6.1 Sol on priority serving for faster replies — 2x price, balanced thinking

$4.00$20.00Details
gpt-6.1-sol-fast-high

GPT-6.1 Sol on priority serving with high thinking — 2x price

$4.00$20.00Details
gpt-6.1-sol-fast-low

GPT-6.1 Sol on priority serving with low thinking — 2x price

$4.00$20.00Details
gpt-6.1-sol-fast-xhigh

GPT-6.1 Sol on priority serving with extra-high thinking — 2x price

$4.00$20.00Details
gpt-6.1-sol-high

GPT-6.1 Sol with high thinking — deeper reasoning for hard problems

$2.00$10.00Details
gpt-6.1-sol-low

GPT-6.1 Sol with low thinking — quicker replies, same price

$2.00$10.00Details
gpt-6.1-sol-xhigh

GPT-6.1 Sol with extra-high thinking — very deep reasoning

$2.00$10.00Details

Live market prices in your display currency. Full details, cache rates and variants on each model page and the Models & Pricing page.