This is Anthropic Claude API pricing as of July 2026: Anthropic's official per-token list price for every current Claude model, side by side with what the same model costs on Kunavo, plus worked cost examples and the levers that cut a Claude bill the most. Claude is the default choice for reasoning, coding and agentic work, and Kunavo undercuts Anthropic's list on every model — about 60% off the Claude 4.x generation and 30% off the new Claude 5 family (Fable 5, Sonnet 5) — behind one OpenAI-compatible API.
Rates last verified July 26, 2026. Kunavo's per-token prices below are read live from the model catalog, and the “Anthropic list” column tracks Anthropic's published rate — the official source is anthropic.com/pricing (developer detail at docs.anthropic.com).
Official Anthropic price list vs Kunavo — July 2026
Rates are per 1M tokens, in USD, as billed on Kunavo. The “Anthropic list” column is Anthropic's official published rate for the same model, taken from anthropic.com/pricing on the verification date above — so this table is the official price list and the discounted one in a single view.
| Model | Input / 1M | Output / 1M | Anthropic list (in / out) | You save |
|---|---|---|---|---|
claude-haiku-4-5 | $0.40 | $2.00 | $1.00 / $5.00 | ~60% |
claude-sonnet-4-6 | $1.20 | $6.00 | $3.00 / $15.00 | ~60% |
claude-sonnet-5 | $2.10 | $10.50 | $3.00 / $15.00 | ~30% |
claude-opus-4-7 | $2.00 | $10.00 | $5.00 / $25.00 | ~60% |
claude-opus-5 | $2.00 | $10.00 | $5.00 / $25.00 | ~60% |
claude-opus-5-fast | $7.00 | $35.00 | $10.00 / $50.00 | ~30% |
claude-fable-5 | $7.00 | $35.00 | $10.00 / $50.00 | ~30% |
Live rates always show on the pricing page and each model page. Haiku is the cheap workhorse, Sonnet the balanced default, Opus the heavy reasoner — and the Claude 5 family adds Sonnet 5 (near-Opus coding at Sonnet cost), Opus 5 and Fable 5, Anthropic's most capable model for frontier reasoning and long-horizon agents.
Claude Opus 5 is the value pick of the Claude 5 family. Anthropic lists it at $5.00 / $25.00 per 1M — half of Fable 5's $10.00 / $50.00 — for near-flagship reasoning. On Kunavo it is $2.00 / $10.00, i.e. ~60% under Anthropic's list and the same rate as the older claude-opus-4-7, so moving a workload from Opus 4.7 to Opus 5 is a one-word model change at no extra cost. A frontier-grade run that costs $0.42 on Fable 5 (50K in / 2K out) costs $0.12 on Opus 5.
What about Claude Opus 5 Fast? Anthropic also ships a latency-tuned claude-opus-5-fast — the same reasoning as Opus 5, with faster output, listed at $10.00 / $50.00 per 1M, exactly 2× standard Opus 5. On Kunavo it is $7.00 / $35.00, about 30% under Anthropic's list. Reach for it when time-to-answer is the thing you are optimizing — an interactive coding session, a user waiting on a response. For batch, agentic or long-context work, standard claude-opus-5 returns the same answers for a fraction of the price.
Pricing note on Claude Sonnet 5: the “Anthropic list” column anchors to Anthropic's standard sticker price of $3.00 / $15.00 per 1M. Anthropic is running an introductory rate of $2 / $10 through August 31, 2026 — during that window the intro rate is below Kunavo's $2.10 / $10.50; after it ends, Kunavo stays ~30% under list. Claude Fable 5 has no intro pricing — $7.00 / $35.00 vs Anthropic's $10.00 / $50.00 is a straight ~30% saving from day one.
How Anthropic API pricing works per token
Anthropic prices the Claude API per token, quoted per 1M tokens and billed on the exact count — there is no per-request fee, no minimum and no subscription. You pay for input tokens (system prompt, context, messages) and output tokens (the completion). Output is billed at roughly 5× the input rate across the family, so the largest lever on cost is how much the model writes. The second lever is prompt caching: stable, repeated context can be cached and billed at a fraction of the normal input rate.
A token is about 4 characters of English, so 1M tokens ≈ 750,000 words. At Kunavo's $6.00 per 1M output on Sonnet 4.6, a 500-token answer costs about $0.00300 in output. Reasoning models add a wrinkle: hidden reasoning tokens are billed at the output rate even though you never see them, which is why an output cap saves more than it looks like it should.
Worked cost examples
Real numbers at Kunavo's rates:
| Workload | Tokens (in / out) | Model | Cost |
|---|---|---|---|
| Support ticket | 800 / 200 | Haiku 4.5 | $0.00072 |
| RAG answer | 6,000 / 500 | Sonnet 4.6 | $0.0102 |
| Coding assistant call | 10,000 / 1,500 | Sonnet 4.6 | $0.021 |
| Coding agent turn | 10,000 / 1,500 | Sonnet 5 | $0.037 |
| Long-context analysis | 50,000 / 2,000 | Opus 4.7 | $0.12 |
| Frontier agent run | 50,000 / 2,000 | Fable 5 | $0.42 |
So 10,000 support tickets a day on Haiku is about $7.20/day. The math, runnable:
# Kunavo Claude rates (USD per 1M tokens): (input, output)
RATES = {
"claude-haiku-4-5": (0.40, 2.00),
"claude-sonnet-4-6": (1.20, 6.00),
"claude-sonnet-5": (2.10, 10.50),
"claude-opus-4-7": (2.00, 10.00),
"claude-opus-5": (2.00, 10.00),
"claude-fable-5": (7.00, 35.00),
}
def cost(model: str, in_tokens: int, out_tokens: int) -> float:
i, o = RATES[model]
return in_tokens / 1_000_000 * i + out_tokens / 1_000_000 * o
print(cost("claude-haiku-4-5", 800, 200)) # support ticket -> $0.00072
print(cost("claude-sonnet-4-6", 6_000, 500)) # RAG answer -> $0.0102
print(cost("claude-sonnet-5", 10_000, 1_500)) # coding agent -> $0.037
print(cost("claude-opus-4-7", 50_000, 2_000)) # long analysis -> $0.12
print(cost("claude-opus-5", 50_000, 2_000)) # Opus 5 analysis-> $0.12
print(cost("claude-fable-5", 50_000, 2_000)) # frontier run -> $0.42Prompt caching — the biggest single saving
If your system prompt or retrieved context is large and stable, prompt caching bills cached input at 10% of the input rate. For a long, reused system prompt that is a 60–90% cut on the input line. It is one extra field on the request — see the Anthropic prompt caching deep dive for the exact pattern and the Messages API reference.
Kunavo pricing and Stripe billing
No subscription, no Anthropic Console billing setup. Top up a balance (Stripe or local payment methods) and calls draw down at the rates above. Pay-as-you-go from a $5 minimum top-up, the balance never expires, and larger top-ups carry bonus credit. The same balance covers Claude, Gemini, GPT, image, video and audio models — one wallet, one invoice.
Claude vs Gemini: the cost decision
Match the model to the job rather than defaulting to the most capable one:
| Need | Pick | Kunavo in / out per 1M |
|---|---|---|
| Cheapest viable | gemini-2-5-flash | $0.09 / $0.75 |
| Cheap + Anthropic quality | claude-haiku-4-5 | $0.40 / $2.00 |
| Balanced reasoning | claude-sonnet-4-6 | $1.20 / $6.00 |
| Near-Opus coding at Sonnet cost | claude-sonnet-5 | $2.10 / $10.50 |
| Hardest reasoning on a budget | claude-opus-4-7 | $2.00 / $10.00 |
| Frontier reasoning & agents | claude-fable-5 | $7.00 / $35.00 |
See the Gemini and GPT pricing guides for the other providers, and the cost optimization guide for the difficulty-routing pattern in code.
Claude Code API pricing
Claude Code — Anthropic's agentic coding CLI — runs on these same Claude models, so its cost is ordinary Claude API token cost: the files and tool output it reads count as input tokens, and the edits and explanations it writes count as output tokens. Sonnet 4.6 ($1.20 / $6.00 per 1M) is the value driver, Sonnet 5 ($2.10 / $10.50) the newest near-Opus coder, and Opus 4.7 ($2.00 / $10.00) or the frontier Fable 5 ($7.00 / $35.00) handle the hardest refactors. Agentic sessions re-read context each turn, so they are token-heavy — which makes prompt caching the biggest lever, billing cached context at 10% of the input rate. Point Claude Code (or another agentic coding tool) at Kunavo's Anthropic-compatible Messages endpoint to pay the rates above — 30–60% under Anthropic's list depending on the model — instead of list price.
Claude Code reads ANTHROPIC_BASE_URL natively, so that redirect is three environment variables and no extra software — the Claude Code setup guide has the exact variables and the credential mistake behind most 401s. If you are still deciding between paying per token and paying for a plan, is Claude Code free works through the break-even, and getting an API key for Claude Code covers where the key goes.
FAQ
What is Anthropic's official API pricing in July 2026?
As of July 26, 2026, Anthropic's official list price per 1M tokens is $1.00 / $5.00 for Haiku 4.5, $3.00 / $15.00 for Sonnet 4.6, $3.00 / $15.00 for Sonnet 5, $5.00 / $25.00 for Opus 4.7 and $10.00 / $50.00 for Fable 5 (input / output). Anthropic publishes these at anthropic.com/pricing. The same models on Kunavo run 30–60% under those figures — the full comparison is in the table above.
Is this the official Anthropic price list?
No. Anthropic's own pricing page is the official source. This guide reproduces those official list prices, states the date they were verified, and puts Kunavo's rate for the same model next to each one. Kunavo is an independent gateway that resells these models — it is not Anthropic, and it does not set Anthropic's list price.
How much does the Anthropic API cost per token in 2026?
Anthropic quotes per 1M tokens and bills the exact token count — no per-request fee, no minimum, no subscription. A token is roughly 4 characters of English. In practice that means about $0.0007 for a support ticket on Haiku 4.5, about $0.01 for a RAG answer on Sonnet 4.6 and about $0.12 for a long-context analysis on Opus 4.7 at Kunavo's rates. Input and output are priced separately, with output about 5× input — see the cost calculator to run your own token counts.
Is the Claude API free?
Anthropic has no free Claude API tier — you pay per token from the first call. Kunavo is pay-as-you-go from a $5 minimum top-up, with per-token rates 30–60% under Anthropic's list depending on the model, and a balance that never expires.
How much does Claude Sonnet cost?
Claude Sonnet 5 is $2.10 per 1M input and $10.50 per 1M output on Kunavo — about 30% under Anthropic's $3.00 / $15.00 sticker. The previous-gen Sonnet 4.6 is $1.20 / $6.00, about 60% under list; a 6K-in / 500-out RAG answer on it costs about $0.01.
How much does the Claude Opus 5 API cost?
Anthropic lists Claude Opus 5 at $5.00 input / $25.00 output per 1M tokens — half of Fable 5 for near-flagship reasoning. On Kunavo it is $2.00 / $10.00, about 60% under list, and the same rate as the older claude-opus-4-7 — so the upgrade costs nothing extra.
What is the difference between Claude Opus 5 and Claude Opus 5 Fast?
Same model, different latency and price. Standard claude-opus-5 lists at $5.00 / $25.00 per 1M; claude-opus-5-fast returns the same reasoning faster and lists at $10.00 / $50.00 — exactly 2×. Choose Fast only when time-to-answer beats cost; for batch, agentic and long-context work standard Opus 5 gives identical answers for far less. Kunavo serves both — claude-opus-5 at $2.00 / $10.00 and claude-opus-5-fast at $7.00 / $35.00.
How much does the Claude Fable 5 API cost?
Claude Fable 5 — Anthropic's most capable model — lists at $10.00 input / $50.00 output per 1M tokens. On Kunavo it is $7.00 / $35.00, about 30% under list. A 50K-in / 2K-out frontier agent run costs about $0.48.
How do I reduce Claude API cost?
Prompt caching first (cached input at 10% of rate), then tier down to Haiku for simple tasks and cap output. Details in the cost optimization guide.
How much does the Claude Code API cost?
Claude Code runs on the standard Claude models, so it's billed as ordinary Claude token cost — Sonnet 4.6 at $1.20 / $6.00, Sonnet 5 at $2.10 / $10.50 and Opus 4.7 at $2.00 / $10.00 per 1M on Kunavo, 30–60% under Anthropic depending on the model. Prompt caching cuts the token-heavy agentic sessions most.
Does Kunavo support the Anthropic Messages API?
Yes — Claude is available through both the native Messages API (/v1/messages) and the OpenAI-compatible /v1/chat/completions endpoint. To start, see how to get a Claude API key.