# LLM API Token Pricing (2026)

> Canonical 2026 reference for LLM API token prices: Anthropic Claude, OpenAI GPT-5.x, and Google Gemini 3.x — input/output rates, output premiums, caching discounts, and batch savings, all sourced from official pricing pages.

Source: https://tokenade.net/en/stats/llm-api-token-pricing · Updated: 2026-08-04

## Why these numbers matter

The per-million-token prices from Anthropic, OpenAI, and Google are the single most actionable numbers for any developer running AI workloads at scale. A model that costs 5× more per output token doesn't just cost 5× more per response — it compounds across every turn of an agent loop, every test-generation run, and every large-file refactor. This page collects the canonical June 2026 figures from official pricing pages so developers can reason about cost before optimising.

Two ratios determine your bill more than the model name: how much more output costs than input (the output premium), and how cheaply caching serves repeated context (the caching discount). Both are covered here with exact numbers.

For how these prices translate into real coding-session costs, see [AI Coding Agent Token Costs](https://tokenade.net/en/stats/ai-coding-agent-token-costs). For the mechanics behind reducing the volume of tokens you send and receive, see the guide on [reducing AI coding agent token usage](https://tokenade.net/en/articles/reduce-ai-coding-agent-token-usage).

<div className="my-8 p-6 bg-amber-50 border-l-4 border-amber-500 rounded-r-lg">
  <h3 className="text-lg font-bold text-amber-800 mb-4">Key Takeaways</h3>
  <ul className="space-y-3">
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span><strong>Claude Opus 5</strong> costs <strong>$5.00 input / $25.00 output per million tokens</strong> — the 5× output premium is uniform across all three Claude tiers <a href="#source-1" className="text-blue-600 hover:underline text-sm">[1]</a></span>
    </li>
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span><strong>GPT-5.5</strong> costs <strong>$5.00 input / $30.00 output per million tokens</strong> — a 6× output premium, the steepest among the flagships surveyed <a href="#source-2" className="text-blue-600 hover:underline text-sm">[2]</a></span>
    </li>
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span><strong>Gemini 3.5 Flash</strong> costs <strong>$1.50 input / $9.00 output per million tokens</strong> — the most affordable single-tier flagship in 2026 <a href="#source-3" className="text-blue-600 hover:underline text-sm">[3]</a></span>
    </li>
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span>Claude prompt cache reads cost <strong>$0.50/MTok</strong> on Opus 5 — a <strong>90% discount</strong> vs the $5.00 base input price <a href="#source-1" className="text-blue-600 hover:underline text-sm">[1]</a></span>
    </li>
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span><strong>Batch APIs</strong> cut costs by 50% across Anthropic, OpenAI, and Google for asynchronous workloads <a href="#source-1" className="text-blue-600 hover:underline text-sm">[1]</a><a href="#source-2" className="text-blue-600 hover:underline text-sm">[2]</a><a href="#source-3" className="text-blue-600 hover:underline text-sm">[3]</a></span>
    </li>
    <li className="flex items-start gap-2">
      <span className="text-amber-600 font-bold">•</span>
      <span><strong>GPT-5.4-nano</strong> at <strong>$0.20 input / $1.25 output</strong> is the cheapest OpenAI text model — 25× cheaper input than GPT-5.5 <a href="#source-4" className="text-blue-600 hover:underline text-sm">[4]</a></span>
    </li>
  </ul>
</div>

## Anthropic Claude pricing in 2026

Anthropic's active line-up as of August 2026: Opus 5, Opus 4.8, Sonnet 5 and Haiku 4.5. Opus 5 shipped at the same rates as Opus 4.8, so the Opus row below covers both. All prices are list rates in USD per million tokens for standard (non-batch) synchronous API calls. <a href="#source-1" className="text-blue-600 hover:underline">[1]</a>

<div className="my-8 p-6 bg-white rounded-lg border border-gray-200 shadow-sm">
  <p className="text-lg font-semibold mb-4 text-center">Claude model prices — Input vs Output ($/MTok)</p>
  <div className="flex items-end justify-center gap-6 h-56 mt-4">
    <div className="flex flex-col items-center gap-1">
      <div className="flex gap-1 items-end">
        <div className="bg-blue-500 w-8 rounded-t" style={{height: '40px', maxHeight: '200px'}}></div>
        <div className="bg-orange-400 w-8 rounded-t" style={{height: '200px', maxHeight: '200px'}}></div>
      </div>
      <span className="text-xs mt-1 text-center">Opus 5</span>
      <span className="text-xs text-gray-500">$5 / $25</span>
    </div>
    <div className="flex flex-col items-center gap-1">
      <div className="flex gap-1 items-end">
        <div className="bg-blue-500 w-8 rounded-t" style={{height: '16px', maxHeight: '200px'}}></div>
        <div className="bg-orange-400 w-8 rounded-t" style={{height: '80px', maxHeight: '200px'}}></div>
      </div>
      <span className="text-xs mt-1 text-center">Sonnet 5</span>
      <span className="text-xs text-gray-500">$2 / $10</span>
    </div>
    <div className="flex flex-col items-center gap-1">
      <div className="flex gap-1 items-end">
        <div className="bg-blue-500 w-8 rounded-t" style={{height: '8px', maxHeight: '200px'}}></div>
        <div className="bg-orange-400 w-8 rounded-t" style={{height: '40px', maxHeight: '200px'}}></div>
      </div>
      <span className="text-xs mt-1 text-center">Haiku 4.5</span>
      <span className="text-xs text-gray-500">$1 / $5</span>
    </div>
  </div>
  <div className="flex justify-center gap-4 mt-3">
    <span className="flex items-center gap-1 text-xs"><span className="w-3 h-3 bg-blue-500 inline-block rounded"></span> Input</span>
    <span className="flex items-center gap-1 text-xs"><span className="w-3 h-3 bg-orange-400 inline-block rounded"></span> Output</span>
  </div>
  <p className="text-xs text-gray-500 mt-3 text-center">Source: <a href="#source-1" className="text-blue-600 hover:underline">[1]</a> Anthropic, anthropic.com/pricing, June 2026</p>
</div>

**Claude Opus 5** is priced at **$5.00 per million input tokens and $25.00 per million output tokens**. <a href="#source-1" className="text-blue-600 hover:underline">[1]</a> It supports a 1-million-token [context window](https://tokenade.net/en/glossary/context-window) on the Claude API and 128k max output tokens. Streaming is what lets you actually reach that ceiling — a non-streaming request with a large `max_tokens` tends to hit the SDK's HTTP timeout first — but it does not raise the ceiling itself.

**Claude Sonnet 5**, the standard production default for coding tasks, sits at **$2.00 / $10.00** per million tokens, also with a 1M context window. <a href="#source-1" className="text-blue-600 hover:underline">[1]</a>

That Sonnet rate carries an expiry date worth planning around: **$2 / $10 is introductory pricing, in effect through 31 August 2026**, after which Sonnet 5 moves to the standard **$3 / $15**. Any budget projection that runs past the summer should be built on the standard rate — it's a 50% increase on the model most coding workloads default to.

**Claude Haiku 4.5**, the fastest and most economical tier, is priced at **$1.00 / $5.00** per million tokens with a 200k context window. <a href="#source-1" className="text-blue-600 hover:underline">[1]</a>

The output-to-input ratio is a clean **5×** across all three Claude models. This consistency means model-switching within the Claude family preserves the same structural cost profile — it changes the absolute price but not the ratio. For a 128k-output session on Opus 5, output tokens alone cost $3.20 regardless of how the input is structured.

### Claude prompt caching prices

Anthropic's [prompt caching](https://tokenade.net/en/glossary/prompt-caching) allows frequently reused context (system prompts, reference documents, tool definitions) to be stored and re-read at a steep discount. The TTL is 5 minutes for standard prompt caching. <a href="#source-1" className="text-blue-600 hover:underline">[1]</a>

<div className="my-8 overflow-x-auto">
  <table className="min-w-full border-collapse border border-gray-300">
    <thead>
      <tr className="bg-gray-100">
        <th className="border border-gray-300 px-4 py-3 text-left font-semibold">Model</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Base Input $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Cache Write $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Cache Read $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Cache Read Discount</th>
      </tr>
    </thead>
    <tbody>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Claude Opus 5 / 4.8</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$5.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$6.25</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">$0.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">90%</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Claude Sonnet 5</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">$0.20</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">90%</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Claude Haiku 4.5</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.25</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">$0.10</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold text-green-700">90%</td>
      </tr>
    </tbody>
  </table>
  <p className="text-xs text-gray-500 mt-2">Source: <a href="#source-1" className="text-blue-600 hover:underline">[1]</a> Anthropic, anthropic.com/pricing, June 2026. Cache write is priced at 1.25× base input; cache read at 0.10× base input (5-minute TTL).</p>
</div>

The cache write penalty — 1.25× the base input rate — is recovered on the **second cache hit**. Every hit after that represents a net $4.50/MTok saving on Opus 5. For an agent that re-reads a 50k-token system context on every turn, enabling prompt caching cuts Opus 5 input costs from $0.25 per turn to $0.025 per turn after the first write.

## OpenAI GPT-5.x pricing in 2026

OpenAI's 2026 lineup has shifted from the GPT-4.x generation to a GPT-5.x family. The main production models are GPT-5.5 (frontier), GPT-5.4 (performance/cost balance), GPT-5.4-mini (lightweight), and GPT-5.4-nano (ultra-low-cost). All prices below are standard (non-batch) list rates. <a href="#source-2" className="text-blue-600 hover:underline">[2]</a><a href="#source-4" className="text-blue-600 hover:underline">[4]</a>

**GPT-5.5**, the flagship model, is priced at **$5.00 per million input tokens and $30.00 per million output tokens**, with cached input at **$0.50/MTok**. <a href="#source-2" className="text-blue-600 hover:underline">[2]</a> Context window: 1 million tokens.

**GPT-5.4** sits at **$2.50 / $15.00** with cached input at $0.25/MTok. <a href="#source-4" className="text-blue-600 hover:underline">[4]</a> Context window: 1.05 million tokens. Note: prompts exceeding 272k tokens are billed at 2× input and 1.5× output for the full session.

**GPT-5.4-mini** is priced at **$0.75 / $4.50** with cached input at $0.075/MTok. <a href="#source-4" className="text-blue-600 hover:underline">[4]</a> Context window: 400k tokens.

**GPT-5.4-nano**, OpenAI's cheapest text model, costs **$0.20 / $1.25** with cached input at $0.02/MTok. <a href="#source-4" className="text-blue-600 hover:underline">[4]</a>

<div className="my-8 p-6 bg-white rounded-lg border border-gray-200 shadow-sm">
  <p className="text-lg font-semibold mb-4">OpenAI GPT-5.x model pricing — Input cost comparison ($/MTok)</p>
  <div className="space-y-4 overflow-hidden">
    <div>
      <div className="flex justify-between mb-1">
        <span className="text-sm font-medium">GPT-5.5</span>
        <span className="text-sm font-semibold">$5.00 in / $30.00 out</span>
      </div>
      <div className="w-full bg-gray-200 rounded-full h-4 overflow-hidden">
        <div className="bg-green-600 h-4 rounded-full" style={{width: '100%', maxWidth: '100%'}}></div>
      </div>
    </div>
    <div>
      <div className="flex justify-between mb-1">
        <span className="text-sm font-medium">GPT-5.4</span>
        <span className="text-sm font-semibold">$2.50 in / $15.00 out</span>
      </div>
      <div className="w-full bg-gray-200 rounded-full h-4 overflow-hidden">
        <div className="bg-green-600 h-4 rounded-full" style={{width: '50%', maxWidth: '100%'}}></div>
      </div>
    </div>
    <div>
      <div className="flex justify-between mb-1">
        <span className="text-sm font-medium">GPT-5.4-mini</span>
        <span className="text-sm font-semibold">$0.75 in / $4.50 out</span>
      </div>
      <div className="w-full bg-gray-200 rounded-full h-4 overflow-hidden">
        <div className="bg-green-600 h-4 rounded-full" style={{width: '15%', maxWidth: '100%'}}></div>
      </div>
    </div>
    <div>
      <div className="flex justify-between mb-1">
        <span className="text-sm font-medium">GPT-5.4-nano</span>
        <span className="text-sm font-semibold">$0.20 in / $1.25 out</span>
      </div>
      <div className="w-full bg-gray-200 rounded-full h-4 overflow-hidden">
        <div className="bg-green-600 h-4 rounded-full" style={{width: '4%', maxWidth: '100%'}}></div>
      </div>
    </div>
  </div>
  <p className="text-xs text-gray-500 mt-4">Source: <a href="#source-2" className="text-blue-600 hover:underline">[2]</a><a href="#source-4" className="text-blue-600 hover:underline">[4]</a> OpenAI, openai.com/api/pricing and platform.openai.com/docs/pricing, June 2026</p>
</div>

The output-to-input ratio on GPT-5.5 is **6×** ($30 ÷ $5) — the highest among the flagship models in this comparison. GPT-5.4 and GPT-5.4-mini both carry a 6× ratio at lower absolute prices. GPT-5.4-nano's ratio drops to **6.25×** ($1.25 ÷ $0.20). The 6× ratio across OpenAI's lineup is consistently higher than Claude's 5×, which makes OpenAI models comparatively less sensitive to input reduction and more sensitive to output reduction.

OpenAI's **Batch API** cuts input and output prices by **50%** for asynchronous tasks processed within 24 hours. <a href="#source-2" className="text-blue-600 hover:underline">[2]</a> At batch rates, GPT-5.5 costs $2.50 / $15.00 per million tokens — matching GPT-5.4 standard pricing.

## Google Gemini 3.x pricing in 2026

Google's Gemini API has moved to a Gemini 3.x generation as of mid-2026. The primary developer-facing models are Gemini 3.5 Flash (the new fast flagship), Gemini 3.1 Flash-Lite (lightweight), and Gemini 3.1 Pro Preview (high-performance, preview status). <a href="#source-3" className="text-blue-600 hover:underline">[3]</a>

**Gemini 3.5 Flash** is priced at **$1.50 per million input tokens and $9.00 per million output tokens** (paid tier), with context caching at **$0.15/MTok**. <a href="#source-3" className="text-blue-600 hover:underline">[3]</a> Context window: 1 million tokens. The output price includes thinking tokens.

**Gemini 3.1 Flash-Lite** costs **$0.25 input / $1.50 output** per million tokens (text/image/video; audio is double), with context caching at **$0.025/MTok**. <a href="#source-3" className="text-blue-600 hover:underline">[3]</a> Context window: 1 million tokens.

**Gemini 3.1 Pro Preview** operates on a two-tier input price: **$2.00 / $12.00** per million tokens for prompts up to 200k tokens, scaling to **$4.00 / $18.00** for prompts exceeding 200k tokens. Context caching is $0.20/MTok (≤200k) or $0.40/MTok (>200k). <a href="#source-3" className="text-blue-600 hover:underline">[3]</a> Context window: 1 million tokens.

<div className="my-8 overflow-x-auto">
  <table className="min-w-full border-collapse border border-gray-300">
    <thead>
      <tr className="bg-gray-100">
        <th className="border border-gray-300 px-4 py-3 text-left font-semibold">Model</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Input $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Output $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Context Cache $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Output Premium</th>
      </tr>
    </thead>
    <tbody>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Gemini 3.5 Flash</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$9.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.15</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Gemini 3.1 Flash-Lite</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.25</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.025</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Gemini 3.1 Pro Preview (≤200k)</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$12.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.20</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Gemini 3.1 Pro Preview ({'>'}&gt;200k)</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$4.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$18.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.40</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">4.5×</td>
      </tr>
    </tbody>
  </table>
  <p className="text-xs text-gray-500 mt-2">Source: <a href="#source-3" className="text-blue-600 hover:underline">[3]</a> Google, ai.google.dev/gemini-api/docs/pricing, June 2026. Context caching = cache-read price. Output includes thinking tokens where applicable.</p>
</div>

Gemini 3.5 Flash's output-to-input ratio is **6×** ($9 ÷ $1.50), identical to the OpenAI flagship ratio. The 3.1 Pro Preview drops to **4.5×** on long-context prompts because the input price doubles while the output price increases by only 50%. Gemini's **Batch API** cuts all prices by **50%** for asynchronous workloads. <a href="#source-3" className="text-blue-600 hover:underline">[3]</a>

Google's context caching is priced at roughly **10% of base input** across all three Gemini models — numerically similar to Anthropic's 90% cache-read discount. The storage cost ($1.00/MTok per hour) applies on top, making Gemini's caching economics most favourable for frequently reused large contexts accessed many times within a short window.

## Master comparison: all models, all prices (June 2026)

<div className="my-8 overflow-x-auto">
  <table className="min-w-full border-collapse border border-gray-300">
    <thead>
      <tr className="bg-gray-100">
        <th className="border border-gray-300 px-4 py-3 text-left font-semibold">Provider</th>
        <th className="border border-gray-300 px-4 py-3 text-left font-semibold">Model</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Input $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Output $/MTok</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Output Premium</th>
        <th className="border border-gray-300 px-4 py-3 text-center font-semibold">Context Window</th>
      </tr>
    </thead>
    <tbody>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Anthropic</td>
        <td className="border border-gray-300 px-4 py-2">Claude Opus 5 / 4.8</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$5.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$25.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">5×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Anthropic</td>
        <td className="border border-gray-300 px-4 py-2">Claude Sonnet 5</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$10.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">5×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Anthropic</td>
        <td className="border border-gray-300 px-4 py-2">Claude Haiku 4.5</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$5.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">5×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">200k tokens</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">OpenAI</td>
        <td className="border border-gray-300 px-4 py-2">GPT-5.5</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$5.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$30.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">OpenAI</td>
        <td className="border border-gray-300 px-4 py-2">GPT-5.4</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$15.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1.05M tokens</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">OpenAI</td>
        <td className="border border-gray-300 px-4 py-2">GPT-5.4-mini</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.75</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$4.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">400k tokens</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">OpenAI</td>
        <td className="border border-gray-300 px-4 py-2">GPT-5.4-nano</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.20</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.25</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6.25×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">—</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Google</td>
        <td className="border border-gray-300 px-4 py-2">Gemini 3.5 Flash</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$9.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
      <tr>
        <td className="border border-gray-300 px-4 py-2 font-medium">Google</td>
        <td className="border border-gray-300 px-4 py-2">Gemini 3.1 Flash-Lite</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$0.25</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$1.50</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
      <tr className="bg-gray-50">
        <td className="border border-gray-300 px-4 py-2 font-medium">Google</td>
        <td className="border border-gray-300 px-4 py-2">Gemini 3.1 Pro Preview (≤200k)</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$2.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center">$12.00</td>
        <td className="border border-gray-300 px-4 py-2 text-center font-semibold">6×</td>
        <td className="border border-gray-300 px-4 py-2 text-center">1M tokens</td>
      </tr>
    </tbody>
  </table>
  <p className="text-xs text-gray-500 mt-2">Sources: <a href="#source-1" className="text-blue-600 hover:underline">[1]</a><a href="#source-2" className="text-blue-600 hover:underline">[2]</a><a href="#source-3" className="text-blue-600 hover:underline">[3]</a><a href="#source-4" className="text-blue-600 hover:underline">[4]</a>. All prices are standard (non-batch) list rates per million tokens ($/MTok), USD, as of June 2026. Verify before quoting in a cost model — prices change at model release.</p>
</div>

## The output premium: why it dominates your bill

The output-to-input price ratio ranges from **5× to 6.25×** across the models on this page. Claude's 5× ratio is the most favourable for output-heavy workloads; OpenAI and Gemini consistently run at 6×.

<div className="my-6 grid grid-cols-1 md:grid-cols-3 gap-4">
  <div className="p-6 bg-gradient-to-br from-purple-50 to-purple-100 rounded-lg border border-purple-200 text-center">
    <div className="text-4xl font-bold text-purple-700">5×</div>
    <div className="text-sm text-purple-600 mt-2">Claude output premium (all tiers)</div>
    <div className="text-xs text-gray-500 mt-2">Source: <a href="#source-1" className="text-blue-600 hover:underline">[1]</a></div>
  </div>
  <div className="p-6 bg-gradient-to-br from-green-50 to-green-100 rounded-lg border border-green-200 text-center">
    <div className="text-4xl font-bold text-green-700">6×</div>
    <div className="text-sm text-green-700 mt-2">OpenAI GPT-5.x &amp; Gemini 3.x output premium</div>
    <div className="text-xs text-gray-500 mt-2">Source: <a href="#source-2" className="text-blue-600 hover:underline">[2]</a><a href="#source-3" className="text-blue-600 hover:underline">[3]</a></div>
  </div>
  <div className="p-6 bg-gradient-to-br from-blue-50 to-blue-100 rounded-lg border border-blue-200 text-center">
    <div className="text-4xl font-bold text-blue-700">50%</div>
    <div className="text-sm text-blue-600 mt-2">Batch API discount (all three providers)</div>
    <div className="text-xs text-gray-500 mt-2">Source: <a href="#source-1" className="text-blue-600 hover:underline">[1]</a><a href="#source-2" className="text-blue-600 hover:underline">[2]</a><a href="#source-3" className="text-blue-600 hover:underline">[3]</a></div>
  </div>
</div>

The practical implication: if an agent emits 10k output tokens per turn and runs 100 turns, the output cost alone on Claude Opus 5 is **$25.00**. Cutting output volume by 30% saves $7.50 per 100 turns — more than the total input cost of many sessions. The [token](https://tokenade.net/en/glossary/token) volume, not the model tier, is the primary bill driver for agentic workloads.

Tools that reduce token volume — trimming context, filtering file reads, compressing repetitive content — apply a fixed multiplier to costs regardless of which model or provider is running. A 40% token reduction at $5.00 input / $30.00 output on GPT-5.5 saves more in absolute terms than the same reduction on Haiku 4.5, but both yield the same percentage saving. If you want to reduce your API bill proportionally across the stack, [Tokenade](https://tokenade.net/en) compresses the tokens sent and received by AI coding agents at the proxy layer.

## Batch API and caching: the two structural discounts

Both prompt caching and batch APIs represent **orthogonal discounts** — they can be combined, and they target different workload shapes.

**Batch processing** (50% off, all three providers) suits large asynchronous jobs: nightly test runs, bulk document processing, offline refactor passes. The constraint is a 24-hour turnaround window and the inability to use real-time results mid-run.

**Prompt caching** (90% off cache reads on Claude; ≈90% on Gemini; ≈90% on OpenAI cached input) targets repeated context — system prompts, knowledge bases, long preambles — that recurs on every turn of a live conversation or agent loop. It rewards real-time interactive workloads that batch APIs cannot serve.

Applied together (for batch workloads that also carry repeated context), the effective discount on cached input tokens is multiplicative: **50% batch × 90% cache-read = 95% discount on that portion of input**. At scale on Opus 5, that is a $0.25/MTok effective input price for cached context in a batch job, versus the $5.00 standard list rate.

## Source notes

<div className="my-8 p-6 bg-gray-50 rounded-lg" id="sources">
  <h2 className="text-xl font-bold mb-4">Sources and references</h2>
  <ol className="space-y-3 text-sm">
    <li className="flex gap-2" id="source-1">
      <span className="font-semibold text-gray-500">[1]</span>
      <span>Anthropic. "API Pricing — Claude models". anthropic.com/pricing, June 2026. <a href="https://www.anthropic.com/pricing" className="text-blue-600 hover:underline ml-1" target="_blank" rel="noopener noreferrer">Link ↗</a></span>
    </li>
    <li className="flex gap-2" id="source-2">
      <span className="font-semibold text-gray-500">[2]</span>
      <span>OpenAI. "OpenAI API Pricing". openai.com/api/pricing, June 2026. <a href="https://openai.com/api/pricing/" className="text-blue-600 hover:underline ml-1" target="_blank" rel="noopener noreferrer">Link ↗</a></span>
    </li>
    <li className="flex gap-2" id="source-3">
      <span className="font-semibold text-gray-500">[3]</span>
      <span>Google. "Gemini Developer API Pricing". ai.google.dev/gemini-api/docs/pricing, June 2026. <a href="https://ai.google.dev/gemini-api/docs/pricing" className="text-blue-600 hover:underline ml-1" target="_blank" rel="noopener noreferrer">Link ↗</a></span>
    </li>
    <li className="flex gap-2" id="source-4">
      <span className="font-semibold text-gray-500">[4]</span>
      <span>OpenAI. "Pricing — Detailed model table". platform.openai.com/docs/pricing, June 2026. <a href="https://platform.openai.com/docs/pricing" className="text-blue-600 hover:underline ml-1" target="_blank" rel="noopener noreferrer">Link ↗</a></span>
    </li>
    <li className="flex gap-2" id="source-5">
      <span className="font-semibold text-gray-500">[5]</span>
      <span>Anthropic. "Models overview — context windows and max output". platform.claude.com/docs/en/about-claude/models/overview, June 2026. <a href="https://platform.claude.com/docs/en/about-claude/models/overview" className="text-blue-600 hover:underline ml-1" target="_blank" rel="noopener noreferrer">Link ↗</a></span>
    </li>
  </ol>
  <p className="text-xs text-gray-500 mt-4">All prices are standard (non-batch) USD list rates per million tokens as of June 2026. Batch discounts (50%), data-residency surcharges (typically +10%), and volume-tier discounts are not reflected in the base rates. Re-verify all figures before using in a cost model — LLM API prices change at each model release without notice.</p>
</div>