Nano GPT logo
NanoGPT

anthropic

Claude Sonnet API Pricing (September 2026)

anthropic/claude-sonnet-5

Compare Claude Sonnet API pricing, explore each model’s capabilities, and start building with one NanoGPT API key.

VisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$2.00
Output / 1M tokens
$10.00
Cache read / 1M tokens
$0.20
Cache creation / 1M tokens
$2.50
1-hour cache creation / 1M tokens
$4.00
Average output tokens
875
Context
1,000,000

Get 3% extra credit when you top up with crypto. Top up with crypto

Build with Claude Sonnet 5

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

Compare model intelligence and coding benchmarks

Compare models using published benchmark scores. Higher scores are better. Each chart uses one benchmark and source version; these are current comparisons, not scores recorded at launch. Ranking pairs each model’s standard and thinking evaluations on one row, Value plots score against the output token rate, and Generations tracks each family release by release. Thinking evaluations are labeled with their published settings, and evaluation effort can affect scores.

Artificial Analysis Intelligence Index

Source version not published · 24 models scored

Using cached Artificial Analysis scores. Recent models and evaluations may be missing.

Which model scores highest, and what does thinking add?

Artificial Analysis Intelligence Index, highest score firstEach row is one model. The hollow marker is its standard evaluation, the filled marker its thinking evaluation, and the bar between them is what thinking adds.0102030405060Index score$ / 1M outputClaude Opus 5.5Claude Opus 5.5: 57.6 · thinking57.6thinking only$20Claude Sonnet 5.5Claude Sonnet 5.5 Thinking: 56 · thinking56thinking only$10Claude Fable 5.1Claude Fable 5.1: 53.4 · thinking53.4thinking only$50Claude Haiku 4.5Claude Haiku 4.5: 15.4 · standardClaude Haiku 4.5 Thinking: 16.9 · thinking16.9+1.5 thinking$5
StandardThinkingWhat thinking adds
Hover, tap, or focus a marker for its evaluation settings and rate.

Source: Artificial Analysis. Missing scores mean no verified matching result is available here for this version; they do not mean the model was never evaluated. Token rates are NanoGPT standard catalogue rates.

View all benchmark scores and evaluation details
Artificial Analysis Intelligence Index (unversioned) by model · index points
ModelScoreOutput / 1M
Claude Fable 5
49.6
$50
Claude Fable 5.1
53.4
$50
Claude Haiku 4.5
15.4
$5
Claude Haiku 4.5 Thinking
16.9
$5
Claude 4 Opus
16.6
$75
Claude 4 Opus Thinking
20.6
$75
Claude 4.1 Opus
18.6
$75
Claude 4.1 Opus Thinking
22.8
$75
Claude 4.5 Opus
23.7
$25
Claude 4.5 Opus Thinking
29.1
$25
Claude 4.6 Opus
26.4
$25
Claude 4.6 Opus Thinking
Score unavailable
$25
Claude 4.6 Opus Thinking Low
Score unavailable
$25
Claude 4.6 Opus Thinking Max
Score unavailable
$25
Claude 4.6 Opus Thinking Medium
Score unavailable
$25
Claude 4.7 Opus
30.9
$25
Claude 4.7 Opus Thinking
40.7
$25
Claude Opus 4.8
Score unavailable
$25
Claude Opus 4.8 Thinking
41.8
$25
Claude Opus 5
50.8
$25
Claude Opus 5.5
57.6
$20
Claude 4 Sonnet
16.6
$15
Claude 4 Sonnet Thinking
Score unavailable
$15
Claude Sonnet 4.5
19.3
$15
Claude Sonnet 4.5 Thinking
20.7
$15
Claude Sonnet 4.6
24.7
$15
Claude Sonnet 4.6 Thinking
30.1
$15
Claude Sonnet 5
23.2
$10
Claude Sonnet 5 Thinking
38.2
$10
Claude Sonnet 5.5
Score unavailable
$10
Claude Sonnet 5.5 Thinking
56
$10
Artificial Analysis Coding Index (unversioned) by model · index points
ModelScoreOutput / 1M
Claude Fable 5
76.5
$50
Claude Fable 5.1
81.6
$50
Claude Haiku 4.5
Score unavailable
$5
Claude Haiku 4.5 Thinking
43.9
$5
Claude 4 Opus
Score unavailable
$75
Claude 4 Opus Thinking
Score unavailable
$75
Claude 4.1 Opus
Score unavailable
$75
Claude 4.1 Opus Thinking
Score unavailable
$75
Claude 4.5 Opus
Score unavailable
$25
Claude 4.5 Opus Thinking
Score unavailable
$25
Claude 4.6 Opus
Score unavailable
$25
Claude 4.6 Opus Thinking
Score unavailable
$25
Claude 4.6 Opus Thinking Low
Score unavailable
$25
Claude 4.6 Opus Thinking Max
Score unavailable
$25
Claude 4.6 Opus Thinking Medium
Score unavailable
$25
Claude 4.7 Opus
Score unavailable
$25
Claude 4.7 Opus Thinking
73.6
$25
Claude Opus 4.8
Score unavailable
$25
Claude Opus 4.8 Thinking
74.3
$25
Claude Opus 5
78
$25
Claude Opus 5.5
Score unavailable
$20
Claude 4 Sonnet
Score unavailable
$15
Claude 4 Sonnet Thinking
Score unavailable
$15
Claude Sonnet 4.5
Score unavailable
$15
Claude Sonnet 4.5 Thinking
52.1
$15
Claude Sonnet 4.6
Score unavailable
$15
Claude Sonnet 4.6 Thinking
63
$15
Claude Sonnet 5
66.4
$10
Claude Sonnet 5 Thinking
71.5
$10
Claude Sonnet 5.5
Score unavailable
$10
Claude Sonnet 5.5 Thinking
Score unavailable
$10
LiveBench Overall (2026-06-25) by model · percent
ModelScoreOutput / 1M
Claude Fable 5Evaluation: claude-fable-5-max-effort
83.4%
$50
Claude Fable 5.1Evaluation: claude-fable-5-1-max-effort
83.8%
$50
Claude Haiku 4.5
Score unavailable
$5
Claude Haiku 4.5 Thinking
Score unavailable
$5
Claude 4 Opus
Score unavailable
$75
Claude 4 Opus Thinking
Score unavailable
$75
Claude 4.1 Opus
Score unavailable
$75
Claude 4.1 Opus Thinking
Score unavailable
$75
Claude 4.5 Opus
Score unavailable
$25
Claude 4.5 Opus ThinkingEvaluation: claude-opus-4-5-20251101-thinking-64k-high-effort
72.9%
$25
Claude 4.6 Opus
Score unavailable
$25
Claude 4.6 Opus ThinkingEvaluation: claude-opus-4-6-thinking-auto-high-effort
75.1%
$25
Claude 4.6 Opus Thinking Low
Score unavailable
$25
Claude 4.6 Opus Thinking Max
Score unavailable
$25
Claude 4.6 Opus Thinking Medium
Score unavailable
$25
Claude 4.7 Opus
Score unavailable
$25
Claude 4.7 Opus ThinkingEvaluation: claude-opus-4-7-xhigh-effort
77%
$25
Claude Opus 4.8
Score unavailable
$25
Claude Opus 4.8 ThinkingEvaluation: claude-opus-4-8-max-effort
77.1%
$25
Claude Opus 5Evaluation: claude-opus-5-max-effort
80.5%
$25
Claude Opus 5.5
Score unavailable
$20
Claude 4 Sonnet
Score unavailable
$15
Claude 4 Sonnet Thinking
Score unavailable
$15
Claude Sonnet 4.5
Score unavailable
$15
Claude Sonnet 4.5 Thinking
Score unavailable
$15
Claude Sonnet 4.6
Score unavailable
$15
Claude Sonnet 4.6 ThinkingEvaluation: claude-sonnet-4-6-thinking-auto-medium-effort
73.4%
$15
Claude Sonnet 5
Score unavailable
$10
Claude Sonnet 5 ThinkingEvaluation: claude-sonnet-5-xhigh-effort
76.6%
$10
Claude Sonnet 5.5
Score unavailable
$10
Claude Sonnet 5.5 Thinking
Score unavailable
$10
LiveBench Coding (2026-06-25) by model · percent
ModelScoreOutput / 1M
Claude Fable 5Evaluation: claude-fable-5-max-effort
86%
$50
Claude Fable 5.1Evaluation: claude-fable-5-1-max-effort
86.4%
$50
Claude Haiku 4.5
Score unavailable
$5
Claude Haiku 4.5 Thinking
Score unavailable
$5
Claude 4 Opus
Score unavailable
$75
Claude 4 Opus Thinking
Score unavailable
$75
Claude 4.1 Opus
Score unavailable
$75
Claude 4.1 Opus Thinking
Score unavailable
$75
Claude 4.5 Opus
Score unavailable
$25
Claude 4.5 Opus ThinkingEvaluation: claude-opus-4-5-20251101-thinking-64k-high-effort
79.7%
$25
Claude 4.6 Opus
Score unavailable
$25
Claude 4.6 Opus ThinkingEvaluation: claude-opus-4-6-thinking-auto-high-effort
78.2%
$25
Claude 4.6 Opus Thinking Low
Score unavailable
$25
Claude 4.6 Opus Thinking Max
Score unavailable
$25
Claude 4.6 Opus Thinking Medium
Score unavailable
$25
Claude 4.7 Opus
Score unavailable
$25
Claude 4.7 Opus ThinkingEvaluation: claude-opus-4-7-xhigh-effort
82.1%
$25
Claude Opus 4.8
Score unavailable
$25
Claude Opus 4.8 ThinkingEvaluation: claude-opus-4-8-max-effort
81.8%
$25
Claude Opus 5Evaluation: claude-opus-5-max-effort
81.4%
$25
Claude Opus 5.5
Score unavailable
$20
Claude 4 Sonnet
Score unavailable
$15
Claude 4 Sonnet Thinking
Score unavailable
$15
Claude Sonnet 4.5
Score unavailable
$15
Claude Sonnet 4.5 Thinking
Score unavailable
$15
Claude Sonnet 4.6
Score unavailable
$15
Claude Sonnet 4.6 ThinkingEvaluation: claude-sonnet-4-6-thinking-auto-medium-effort
79.3%
$15
Claude Sonnet 5
Score unavailable
$10
Claude Sonnet 5 ThinkingEvaluation: claude-sonnet-5-xhigh-effort
80.7%
$10
Claude Sonnet 5.5
Score unavailable
$10
Claude Sonnet 5.5 Thinking
Score unavailable
$10

Sonnet model pricing per 1M tokens

USD per 1 million tokens · NanoGPT standard catalogue rates
Model / API IDInputCache readCache creationOutputContextAverage output tokensEstimated query cost
Claude 4 Sonnetclaude-sonnet-4-20250514$3.00$0.30$3.751-hour: $6.00$15.00200,000381$0.00872
Claude 4 Sonnet Thinkingclaude-sonnet-4-thinking$3.00$0.30$3.751-hour: $6.00$15.001,000,000UnavailableUnavailable
Claude Sonnet 4.5claude-sonnet-4-5-20250929$3.00$0.30$3.751-hour: $6.00$15.00200,000648$0.01272
Claude Sonnet 4.5 Thinkingclaude-sonnet-4-5-20250929-thinking$3.00$0.30$3.751-hour: $6.00$15.00200,0001,272$0.02208
Claude Sonnet 4.6anthropic/claude-sonnet-4.6$3.00$0.30$3.751-hour: $6.00$15.001,000,000521$0.01082
Claude Sonnet 4.6 Thinkinganthropic/claude-sonnet-4.6:thinking$3.00$0.30$3.751-hour: $6.00$15.001,000,0001,547$0.02621
Claude Sonnet 5anthropic/claude-sonnet-5$2.00$0.20$2.501-hour: $4.00$10.001,000,000875$0.01075
Claude Sonnet 5 Thinkinganthropic/claude-sonnet-5:thinking$2.00$0.20$2.501-hour: $4.00$10.001,000,0001,252$0.01452
Claude Sonnet Latestanthropic/claude-sonnet-latest$2.00$0.20$2.501-hour: $4.00$10.001,000,0001,273$0.01473

Base text-token rates. Long-context pricing, tool charges, service tiers, and provider selection can change the total. Cache creation is charged when writing tokens to the cache; cache read applies when reusing them. The default cache duration applies unless labeled otherwise. Unsupported cache rates are marked unavailable.

Estimated query cost combines your input-token count with the model’s average output, rounded to whole tokens, at current standard rates. It assumes uncached input and excludes tool charges. This is an estimate for that workload, not a measured average total bill.

anthropic

Claude Sonnet 5

anthropic/claude-sonnet-5

Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.

VisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$2.00
Output / 1M tokens
$10.00
Cache read / 1M tokens
$0.20
Cache creation / 1M tokens
$2.50
1-hour cache creation / 1M tokens
$4.00
Average output tokens
875
Context
1,000,000

Build with Claude Sonnet 5

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet 5 Thinking

anthropic/claude-sonnet-5:thinking

Claude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$2.00
Output / 1M tokens
$10.00
Cache read / 1M tokens
$0.20
Cache creation / 1M tokens
$2.50
1-hour cache creation / 1M tokens
$4.00
Average output tokens
1,252
Context
1,000,000

Build with Claude Sonnet 5 Thinking

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-5:thinking",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Average output tokens
521
Context
1,000,000

Build with Claude Sonnet 4.6

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-4.6",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet 4.6 Thinking

anthropic/claude-sonnet-4.6:thinking

Claude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Average output tokens
1,547
Context
1,000,000

Build with Claude Sonnet 4.6 Thinking

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-4.6:thinking",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet 4.5

claude-sonnet-4-5-20250929

Frontier‑level coding and agentic performance. Claude Sonnet 4.5 leads on real‑world coding tasks and shows substantial gains in computer use, reasoning, and math. Designed for long‑horizon, multi‑step work across IDE + terminal workflows, large codebases, and complex agents — a drop‑in upgrade over previous Sonnet versions.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Average output tokens
648
Context
200,000

Build with Claude Sonnet 4.5

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-5-20250929",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet 4.5 Thinking

claude-sonnet-4-5-20250929-thinking

Adds extended, step‑by‑step reasoning for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows, complex problem solving, and scenarios that benefit from explicit thinking traces.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Average output tokens
1,272
Context
200,000

Build with Claude Sonnet 4.5 Thinking

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-5-20250929-thinking",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude 4 Sonnet

claude-sonnet-4-20250514

Claude 4 Sonnet by Anthropic. A new generation model with improved capabilities, especially on programming and development. NOTE: Inputs > 200k tokens are charged at 2x input, 1.5x output rate.

VisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Average output tokens
381
Context
200,000

Build with Claude 4 Sonnet

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude 4 Sonnet Thinking

claude-sonnet-4-thinking

Anthropic's Claude 4 Sonnet with the ability to show its thinking process step by step.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cache read / 1M tokens
$0.30
Cache creation / 1M tokens
$3.75
1-hour cache creation / 1M tokens
$6.00
Context
1,000,000

Build with Claude 4 Sonnet Thinking

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-thinking",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

anthropic

Claude Sonnet Latest

anthropic/claude-sonnet-latest

Compatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.

ReasoningVisionNative PDF inputTool CallingStructured Output
Input / 1M tokens
$2.00
Output / 1M tokens
$10.00
Cache read / 1M tokens
$0.20
Cache creation / 1M tokens
$2.50
1-hour cache creation / 1M tokens
$4.00
Average output tokens
1,273
Context
1,000,000

Build with Claude Sonnet Latest

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-latest",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Set NANOGPT_API_KEY in your environment. Keep your API key on the server.

Estimate a request’s token cost

$0.03

One request, standard uncached text tokens. Excludes tools and other charges. Known long-context rates apply automatically; invalid workloads or missing rates cannot be estimated.

Related questions

  • Can you use Claude Sonnet for free?

    Yes, you can use it free on the web and mobile apps with no credit card. The limit is roughly 15 to 40 messages every 5 hours, and paid users get served first when traffic spikes.

  • How to get Claude Pro for a less price?

    The cheapest ways to get and use Claude depend on whether you need the standard web chat interface, developer API access, or tool integrations like Claude Code.

  • What Claude model is best for Roleplay?

    It's Claude Opus, either 4.8 or 5. It scores 97% on our Roleplay benchmark, the highest of any model we track. Sonnet is the faster storyteller, and Fable handles long multi-day campaigns.

Browse all FAQs →