anthropic
Claude Opus API Pricing (September 2026)
anthropic/claude-opus-5Compare Claude Opus API pricing, explore each model’s capabilities, and start building with one NanoGPT API key.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,856
- Context
- 1,000,000
Get 3% extra credit when you top up with crypto. Top up with crypto
Build with Claude Opus 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-opus-5",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
Opus model pricing per 1M tokens
| Model / API ID | Input | Cache read | Cache creation | Output | Context | Average output tokens | Estimated query cost |
|---|---|---|---|---|---|---|---|
Claude 4 Opusclaude-opus-4-20250514 | $15.00 | $1.50 | $18.751-hour: $30.00 | $75.00 | 200,000 | 110 | $0.02325 |
Claude 4 Opus Thinkingclaude-opus-4-thinking | $15.00 | $1.50 | $18.751-hour: $30.00 | $75.00 | 200,000 | Unavailable | Unavailable |
Claude 4.1 Opusclaude-opus-4-1-20250805 | $15.00 | $1.50 | $18.751-hour: $30.00 | $75.00 | 200,000 | 722 | $0.06915 |
Claude 4.1 Opus Thinkingclaude-opus-4-1-thinking | $15.00 | $1.50 | $18.751-hour: $30.00 | $75.00 | 200,000 | 600 | $0.06 |
Claude 4.5 Opusclaude-opus-4-5-20251101 | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 200,000 | 435 | $0.01588 |
Claude 4.5 Opus Thinkingclaude-opus-4-5-20251101:thinking | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 200,000 | 1,131 | $0.03328 |
Claude 4.6 Opusanthropic/claude-opus-4.6 | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 281 | $0.01203 |
Claude 4.6 Opus Thinkinganthropic/claude-opus-4.6:thinking | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,735 | $0.04838 |
Claude 4.6 Opus Thinking Lowanthropic/claude-opus-4.6:thinking:low | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,317 | $0.03793 |
Claude 4.6 Opus Thinking Maxanthropic/claude-opus-4.6:thinking:max | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,470 | $0.04175 |
Claude 4.6 Opus Thinking Mediumanthropic/claude-opus-4.6:thinking:medium | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 930 | $0.02825 |
Claude 4.7 Opusanthropic/claude-opus-4.7 | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 834 | $0.02585 |
Claude 4.7 Opus Thinkinganthropic/claude-opus-4.7:thinking | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,412 | $0.0403 |
Claude Opus 4.8anthropic/claude-opus-4.8 | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 910 | $0.02775 |
Claude Opus 4.8 Thinkinganthropic/claude-opus-4.8:thinking | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,914 | $0.05285 |
Claude Opus 5anthropic/claude-opus-5 | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | 1,856 | $0.0514 |
Claude Opus Latestanthropic/claude-opus-latest | $5.00 | $0.50 | $6.251-hour: $10.00 | $25.00 | 1,000,000 | Unavailable | Unavailable |
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 Opus 5
anthropic/claude-opus-5Claude Opus 5 is Anthropic's flagship model for advanced coding, long-running agentic tasks, research, and complex knowledge work.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,856
- Context
- 1,000,000
Build with Claude Opus 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-opus-5",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude Opus 4.8
anthropic/claude-opus-4.8Anthropic Claude Opus 4.8 with text, image, and file inputs and a 1M-token context window.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 910
- Context
- 1,000,000
Build with Claude Opus 4.8
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.8",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude Opus 4.8 Thinking
anthropic/claude-opus-4.8:thinkingAnthropic Claude Opus 4.8 with thinking enabled.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,914
- Context
- 1,000,000
Build with Claude Opus 4.8 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-opus-4.8:thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.7 Opus
anthropic/claude-opus-4.7Claude Opus 4.7 is a major upgrade for advanced software engineering, long-running complex tasks, and high-resolution vision understanding.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 834
- Context
- 1,000,000
Build with Claude 4.7 Opus
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.7",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.7 Opus Thinking
anthropic/claude-opus-4.7:thinkingClaude Opus 4.7 with thinking enabled (default budget: 16k tokens).
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,412
- Context
- 1,000,000
Build with Claude 4.7 Opus 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-opus-4.7:thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.6 Opus
anthropic/claude-opus-4.6Claude Opus 4.6 is Anthropic's newest Opus model with stronger coding and agentic performance, plus support for up to a 1M-token context window.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 281
- Context
- 1,000,000
Build with Claude 4.6 Opus
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.6",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.6 Opus Thinking
anthropic/claude-opus-4.6:thinkingClaude Opus 4.6 with adaptive thinking enabled (default effort: high).
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,735
- Context
- 1,000,000
Build with Claude 4.6 Opus 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-opus-4.6:thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.6 Opus Thinking Low
anthropic/claude-opus-4.6:thinking:lowClaude Opus 4.6 with adaptive thinking (effort: low).
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,317
- Context
- 1,000,000
Build with Claude 4.6 Opus Thinking Low
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.6:thinking:low",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.6 Opus Thinking Max
anthropic/claude-opus-4.6:thinking:maxClaude Opus 4.6 with adaptive thinking (effort: max).
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,470
- Context
- 1,000,000
Build with Claude 4.6 Opus Thinking Max
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.6:thinking:max",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.6 Opus Thinking Medium
anthropic/claude-opus-4.6:thinking:mediumClaude Opus 4.6 with adaptive thinking (effort: medium).
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 930
- Context
- 1,000,000
Build with Claude 4.6 Opus Thinking Medium
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-4.6:thinking:medium",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.5 Opus
claude-opus-4-5-20251101Claude Opus 4.5 is the top model for coding, agentic workflows, and computer use—now stronger at deep research, slides, and spreadsheets. It pushes state-of-the-art software engineering and lifts vision, reasoning, and math across the board.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 435
- Context
- 200,000
Build with Claude 4.5 Opus
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-5-20251101",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.5 Opus Thinking
claude-opus-4-5-20251101:thinkingClaude Opus 4.5 with visible thinking for tougher coding, agent, and research work—built to show its reasoning while tackling long, complex tasks.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Average output tokens
- 1,131
- Context
- 200,000
Build with Claude 4.5 Opus Thinking
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-5-20251101:thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.1 Opus
claude-opus-4-1-20250805Claude Opus 4.1 is a powerful model from Anthropic that delivers sustained performance for complex coding and other long-running tasks that require thousands of steps, expanding the capabilities of AI agents.
- Input / 1M tokens
- $15.00
- Output / 1M tokens
- $75.00
- Cache read / 1M tokens
- $1.50
- Cache creation / 1M tokens
- $18.75
- 1-hour cache creation / 1M tokens
- $30.00
- Average output tokens
- 722
- Context
- 200,000
Build with Claude 4.1 Opus
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-1-20250805",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4.1 Opus Thinking
claude-opus-4-1-thinkingAnthropic's Claude 4.1 Opus with the ability to show its thinking process step by step.
- Input / 1M tokens
- $15.00
- Output / 1M tokens
- $75.00
- Cache read / 1M tokens
- $1.50
- Cache creation / 1M tokens
- $18.75
- 1-hour cache creation / 1M tokens
- $30.00
- Average output tokens
- 600
- Context
- 200,000
Build with Claude 4.1 Opus Thinking
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-1-thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4 Opus
claude-opus-4-20250514Claude 4 Opus by Anthropic. The premium version of the new Claude models. A new generation model with improved capabilities, especially on programming and development.
- Input / 1M tokens
- $15.00
- Output / 1M tokens
- $75.00
- Cache read / 1M tokens
- $1.50
- Cache creation / 1M tokens
- $18.75
- 1-hour cache creation / 1M tokens
- $30.00
- Average output tokens
- 110
- Context
- 200,000
Build with Claude 4 Opus
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-20250514",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude 4 Opus Thinking
claude-opus-4-thinkingAnthropic's Claude 4 Opus with the ability to show its thinking process step by step.
- Input / 1M tokens
- $15.00
- Output / 1M tokens
- $75.00
- Cache read / 1M tokens
- $1.50
- Cache creation / 1M tokens
- $18.75
- 1-hour cache creation / 1M tokens
- $30.00
- Context
- 200,000
Build with Claude 4 Opus Thinking
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-thinking",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Set NANOGPT_API_KEY in your environment. Keep your API key on the server.
anthropic
Claude Opus Latest
anthropic/claude-opus-latestCompatibility alias that routes to the newest version of Claude Opus. Currently routes to Claude Opus 5.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $25.00
- Cache read / 1M tokens
- $0.50
- Cache creation / 1M tokens
- $6.25
- 1-hour cache creation / 1M tokens
- $10.00
- Context
- 1,000,000
Build with Claude Opus 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-opus-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
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.