Claude Sonnet 5

Claude Sonnet 5 is Anthropic's most agentic Sonnet model, released June 30, 2026, with performance close to Opus 4.8 at a lower price. On GPTProto the Sonnet 5 API runs from $1.6 / $8 per 1M tokens — roughly 20% below Anthropic's own rate — billed from a single balance shared across every model on the platform.

Modalities

Context

API Usage Examples

curl --request POST "https://gptproto.com/v1/chat/completions" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "claude-sonnet-5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Claude Sonnet 5 pricing

Estimate a request with real work scenarios. GPTProto token pricing is 20% below official rates.

Cost calculator

Multi-turn agent with cached context.

Input tokens$1.6 / 1M$0.0024

Output tokens$8 / 1M$0.0064

Cache write tokens$2 / 1M$0.006

Cache read tokens$0.16 / 1M$0.004

Cost per request$0.0188

Top up

GPTProto vs official pricing.

Requests

You pay

20% off

$100

You receive$100.00

Save$25.00 (20%)vs Claude official

Sonnet 5 API

Run the Claude Sonnet 5 API on GPTProto from $1.6 / $8 per 1M tokens — about 20% under Anthropic's own rate, on one shared balance that also covers 200+ other models.

Built for Multi-File Coding

Strong on multi-file coding and debugging: Sonnet 5 reaches 63.2% on Anthropic's reported agentic-coding benchmark, above Sonnet 4.6 (58.1%) and near Opus 4.8 (69.2%).

Most Agentic Sonnet Yet

Sonnet 5 plans and runs multi-step jobs on its own — driving browsers, terminals, and other tools through the API, and finishing tasks that earlier Sonnet models would stop short on.

Cheaper Than Calling Anthropic Direct

Call the Sonnet 5 API from $1.6 / $8 per 1M tokens — about 20% under Anthropic's current rate — all billed from one shared balance across 200+ models on GPTProto.

Adjustable Thinking Effort

Dial reasoning up for hard problems or down for cheaper, faster calls — one effort parameter, same claude-sonnet-5 model string. Sonnet 5 also carries a 1M-token context window for whole codebases in one request.

Related Models

All Models

Model					Input → Output
Claude Sonnet 5Current		1M	$1.60 / $8.00 per 1M	$2.00 / $0.16 per 1M	Input: TextInput: Document Output: Text
Gemini 3.7 Flash		—	$0.45 / $2.25 per 1M	— / $0.04 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.6		500K	$1.20 / $3.60 per 1M	— / $0.30 per 1M	Input: TextInput: Image Output: Text
Qwen3.8 Max		1M	$1.80 / $5.40 per 1M	$2.25 / $0.23 per 1M	Input: TextInput: ImageInput: VideoInput: Document Output: Text
Claude Opus 5		1M	$4.00 / $20.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.6 Flash		1.05M	$0.45 / $2.25 per 1M	— / $0.04 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.5 Flash Lite		1.05M	$0.18 / $1.50 per 1M	$0.02 / $0.02 per 1M	Input: TextInput: ImageInput: Document Output: Text
Kimi K3		1.05M	$2.70 / $13.50 per 1M	$0.27 / $0.27 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Luna		1.05M	$0.16 / $0.96 per 1M	$0.20 / $0.02 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Terra		1.05M	$1.60 / $9.60 per 1M	$2.00 / $0.16 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Sol		1.05M	$4.00 / $24.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.5		500K	$1.20 / $3.60 per 1M	$0.30 / $0.30 per 1M	Input: TextInput: Image Output: Text
Minimax M3		1.05M	$0.48 / $0.96 per 1M	$0.10 / $0.10 per 1M	Input: TextInput: ImageInput: Document Output: Text
GLM 5.2		1.05M	$1.26 / $3.96 per 1M	$0.23 / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Claude Fable 5		1M	$8.00 / $40.00 per 1M	$10.00 / $0.80 per 1M	Input: TextInput: Document Output: Text
Qwen3.7 Max		1M	$0.36 / $1.44 per 1M	$0.07 / $0.07 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.8 Thinking		1M	$4.00 / $20.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.8		1M	$4.00 / $20.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: Document Output: Text
DeepSeek v4 Flash	—	1.05M	$0.14 / $0.28 per 1M	— / $0.0028 per 1M	Input: Text Output: Text
DeepSeek v4 Pro		1.05M	$1.04 / $2.09 per 1M	$0.0087 / $0.0087 per 1M	Input: Text Output: Text
Grok 4.3		1M	$0.75 / $1.50 per 1M	$0.12 / $0.12 per 1M	Input: TextInput: Image Output: Text
Kimi K2.6		262K	$0.85 / $3.60 per 1M	$0.14 / $0.14 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.7 Thinking		1M	$4.00 / $20.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.7		1M	$4.00 / $20.00 per 1M	$5.00 / $0.40 per 1M	Input: TextInput: Document Output: Text
GLM 5.1		205K	$1.26 / $3.96 per 1M	$0.23 / $0.23 per 1M	Input: TextInput: Document Output: Text
GLM 5 Turbo		203K	$1.08 / $3.60 per 1M	$0.22 / $0.22 per 1M	Input: TextInput: Document Output: Text
DeepSeek v3.2		164K	$0.17 / $0.25 per 1M	$0.02 / $0.02 per 1M	Input: Text Output: Text
Minimax M2.5		205K	$0.24 / $0.96 per 1M	$0.30 / $0.02 per 1M	Input: TextInput: Document Output: Text
Kimi K2.5		262K	$0.54 / $2.70 per 1M	$0.09 / $0.09 per 1M	Input: TextInput: Document Output: Text
Qwen Turbo		—	$0.04 / $0.18 per 1M	$0.009 / $0.009 per 1M	Input: Text Output: Text
Doubao Seed 1.6 Thinking 250715		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Thinking 250615		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Flash 250615		262K	$0.02 / $0.18 per 1M	—	Input: TextInput: Image Output: Text

What Is Claude Sonnet 5?

Claude Sonnet 5 is Anthropic's Sonnet-class model released June 30, 2026, positioned as its most agentic Sonnet yet. It plans, uses tools like browsers and terminals, and carries multi-step tasks to completion — often finishing work where earlier Sonnet models would stop partway. On Anthropic's own benchmarks its agentic performance lands close to Opus 4.8 while costing less per token, which is why the Sonnet 5 API is aimed squarely at developers running agents and high-volume coding workloads on a budget.

On GPTProto you call the same claude-sonnet-5 model string through one API key and one balance, at a price below Anthropic's direct rate — and the same key already works across 200+ other models if you want to route cheaper tasks elsewhere.

Sonnet 5 Specifications

Spec	Claude Sonnet 5
Provider	Anthropic
Model string	`claude-sonnet-5`
Modality (on GPTProto)	Text → Text (no image input)
Context window	1M tokens (standard pricing, no long-context surcharge)
Thinking effort	Adjustable (dial reasoning per request)
GPTProto price /1M	$1.6 input / $8 output
Anthropic price /1M	$2 / $10 (intro, through Aug 31 2026) → $3 / $15 standard
Endpoint	`https://gptproto.com/v1/messages`

Sonnet 5 vs Sonnet 4.6 vs Opus 4.8

All three are on GPTProto, so this compares real, callable models — not a placeholder baseline. Prices are GPTProto's; Anthropic list shown for reference.

	Sonnet 5	Sonnet 4.6	Opus 4.8 (reference)
GPTProto input /1M	$1.6	$2.4	$4
GPTProto output /1M	$8	$12	~$20
Anthropic list /1M	$2/$10 → $3/$15	$3/$15	$5/$25
Agentic coding	63.2%	58.1%	69.2%
Context window	1M	1M	1M

On GPTProto, Sonnet 5 is both the newer model and the cheaper one — it undercuts Sonnet 4.6 ($1.6/$8 vs $2.4/$12) while scoring higher on agentic coding. Opus 4.8 stays ahead on the hardest reasoning tasks; reach for it when accuracy matters more than cost, and route the rest to Sonnet 5.

One honest caveat: Sonnet 5 uses a newer tokenizer that generates about 30% more tokens for the same text than Sonnet 4.6. The per-token price is lower, but your token count per request is higher — so benchmark cost on your own prompts before assuming a flat 20% saving. Agentic-coding figures are Anthropic's reported numbers

Switching From the Official Anthropic API

Moving an existing Anthropic integration to the Sonnet 5 API on GPTProto is a drop-in change — you keep the same request format and model string:

Base URL → point requests to https://gptproto.com/v1/messages.
Auth → use Authorization: Bearer YOUR_GPTPROTO_API_KEY (keep the anthropic-version: 2023-06-01 header).
Model string → unchanged: claude-sonnet-5.

Your message payloads stay the same, so most SDKs migrate by swapping two lines. Runnable Python/cURL is in the Quick Start above. The payoff: one key and one balance across 200+ models, no separate Anthropic account, and a per-token price below Anthropic's direct rate.

Claude Sonnet 5 FAQs

Get expert answers about integrating Claude 5 Sonnet into your applications via the GPTProto API aggregation layer.

How does the Sonnet 5 API on GPTProto differ from Anthropic's?

Same model (claude-sonnet-5), lower price and one shared key. GPTProto runs it at $1.6 / $8 per 1M tokens versus Anthropic's $2 / $10 introductory rate, and the same key works across 200+ models with no separate provider sign-ups.

Is my data used to train the Claude model?

No. Data privacy is a core pillar of our service. Any information or prompts you send to Claude 3.5 Sonnet via our API are not used by Anthropic or GPTProto to train the underlying Claude model. We adhere to strict enterprise-grade security standards, ensuring that your proprietary codebases, sensitive documents, and user interactions remain private and are only used to generate the specific response you requested from the Claude API.

What is the typical latency for Claude 3.5 Sonnet?

Claude 3.5 Sonnet is optimized for speed. The typical time-to-first-token (TTFT) ranges between 400ms and 600ms. Once generation begins, Claude produces text at a rate of approximately 60 to 80 tokens per second. This makes Claude 3.5 Sonnet significantly faster than Claude 3 Opus, allowing for real-time chat experiences and rapid processing of complex reasoning tasks without sacrificing the quality of the model's output.

Can I migrate from GPT-4o to Claude 3.5 Sonnet?

Yes. Point requests at GPTProto's endpoint, swap your model string to claude-sonnet-5, and use the Anthropic-style message format. No separate Anthropic account is needed — one GPTProto key covers it.

Does Claude 3.5 Sonnet support fine-tuning?

Anthropic does not offer customer fine-tuning for Claude models. Shape behavior with system prompts and the adjustable thinking-effort control instead.

How much is the Sonnet 5 API?

On GPTProto, $1.6 per 1M input tokens and $8 per 1M output tokens. That is about 20% under Anthropic's introductory rate ($2 / $10) and roughly 47% under the standard rate ($3 / $15) that starts September 1, 2026.

Is the Sonnet 5 API cheaper than going direct?

Yes. At $1.6 / $8 per 1M, GPTProto is below Anthropic's own list price for the same model. Note that Sonnet 5 uses a newer tokenizer that produces roughly 30% more tokens per text than Sonnet 4.6, so compare on real workloads, not headline rates alone.

Sonnet 5 vs Claude Sonnet 4.6 — which should I call?

Sonnet 5 is the newer model and, on GPTProto, the cheaper one: $1.6 / $8 versus Sonnet 4.6 at $2.4 / $12. It scores higher on agentic coding (63.2% vs 58.1%). Sonnet 4.6 remains a stable pinned option if you need version consistency.

Guides, comparisons, and updates related to this model.

All Articles

Seedance 2.0 Mini vs Seedance 2.0: Price, Quality, and Which One to Actually Use

Seedance 2.0 Mini isn't "half price"—on the API it's ~20% cheaper. The big saving comes from 720p drafting. Real pricing, runnable code, which tier to ship.

Claude Fable 5: The Complete Guide and Honest Review (2026)

Claude Fable 5 is Anthropic's first public Mythos-class model. See what it does, what it costs, and when to pick it over Opus 4.8.

Sora 2 Is Gone: Your 6 Real Sora 2 Alternatives for 2026

OpenAI shut down Sora 2. Here are 6 real alternatives for 2026: Seedance, Veo, Kling & more — ranked by a neutral benchmark, all on one API key.

Claude Sonnet 5: What's New, What It Costs, and How It Compares to Sonnet 4.6 (2026 Guide)

laude Sonnet 5 guide: what's new vs Sonnet 4.6, benchmarks, $2/$10 pricing, the tokenizer catch that changes your bill, and runnable API code.