Claude Sonnet 4.6 Thinking
nano-gpt/claude-sonnet-4-6-thinking제공: nano-gpt · 패밀리: claude-sonnet · 출시 2026-02-17 · 지식 컷오프: 2025-08-31
⚠ 이 모델은 커뮤니티 파인튜닝 / 파생본으로, 벤더 공식 릴리스가 아닙니다.
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
기능
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding91
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability1/10
Agents91
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output70
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control0/10
- Price-friendly for high-volume0/20
Cost efficiency31
- Headline price (log-scaled)31/95
- Has prompt-cache pricing0/5
Long context90
- Context window (100K → 2M)80/90
- Has published price for full window10/10
Vision91
- Accepts image input50/50
- Context window (10K → 1M)30/30
- Has published price10/10
- Provider availability1/10
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $22.46 $0.02 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $44.91 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $13.48 $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $38.93 $0.04 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $44.90 $0.04 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
가격 상세
추천 가격 제공자: nano-gpt · anthropic/claude-sonnet-4.6:thinking
1곳 제공사에서 이용 가능
| 제공자 | 제공자 모델 ID | 입력 / 1M | 출력 / 1M | 컨텍스트 | 출시일 |
|---|---|---|---|---|---|
| NanoGPT nano-gpt | anthropic/claude-sonnet-4.6:thinking | $2.99 | $14.99 | 1M | 2026-02-17 |
Frequently asked questions
How much does Claude Sonnet 4.6 Thinking cost?
Claude Sonnet 4.6 Thinking costs $2.99 per 1M input tokens and $14.99 per 1M output tokens, sourced from nano-gpt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Claude Sonnet 4.6 Thinking?
Claude Sonnet 4.6 Thinking has a context window of 1M tokens, with a max output of 128K tokens per reply. This is the total combined size of prompt + completion.
Does Claude Sonnet 4.6 Thinking support tool calling?
Yes. Claude Sonnet 4.6 Thinking supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Claude Sonnet 4.6 Thinking support structured output / JSON mode?
Yes. Claude Sonnet 4.6 Thinking supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Claude Sonnet 4.6 Thinking accept image input?
Yes. Claude Sonnet 4.6 Thinking accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check nano-gpt's docs for the exact rule.
Is Claude Sonnet 4.6 Thinking open-weight?
No. Claude Sonnet 4.6 Thinking is a proprietary model — only nano-gpt (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Claude Sonnet 4.6 Thinking?
If Claude Sonnet 4.6 Thinking doesn't fit, consider Brave (Answers), Exa (Research), Auto model (Basic). Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More nano-gpt models
- Brave (Answers)$5.00 in / $5.00 out
- Exa (Research)$2.50 in / $2.50 out
- Auto model (Basic)$10.00 in / $19.99 out
- Jamba Mini$0.20 in / $0.41 out
- Yi Large$3.20 in / $3.20 out
Capability lists this model is in
마지막 업데이트:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.