impulse

Claude Opus 4.1

Frontier lab

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

API id claude-opus-4.1Released 5 Aug 2025 (Aug 2025)
A newer model in this line is out: Claude Opus 5.5, released 22 Sep 2026.
Amazon Bedrock retires it on 8 Jan 2027 (in 51 days). 2 hosts keep serving it.
Input / 1M
$15.00
at Vercel AI Gateway
Output / 1M
$75.00
at Vercel AI Gateway
Context window
200K
tokens
Max output
32K
tokens per reply
Hosts
3
5 listings
Released
Aug 2025
5 Aug 2025

Pricing

List prices at Vercel AI Gateway, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$15.00$75.00
Cached input
90% off input
$1.50
Cache write, 5 minutes$18.75

What it costs a month

At Vercel AI Gateway list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$8,910
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$6,660
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$11,160
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$54,000
Use your own numbers

Where to run it

3 hosts serve Claude Opus 4.1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
2025-08-05
anthropic.claude-opus-4-1-20250805-v1:0
$15.00 / $75.00
Retires 8 Jan 2027
claude-opus-4.1
$15.00 / $75.00
databricks-claude-opus-4-1
$15.00 / $75.00
Show 2 more listings: regions, snapshots and variants
Amazon Bedrock
eu · 2025-08-05
eu.anthropic.claude-opus-4-1-20250805-v1:0
$15.00 / $75.00
Retires 8 Jan 2027
us · 2025-08-05
us.anthropic.claude-opus-4-1-20250805-v1:0
$15.00 / $75.00
Retires 8 Jan 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Features
Assistant prefillComputer usePrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Vercel AI Gateway.

Smaller Anthropic models

  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
    47% less
  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    73% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    87% less

Other frontier labs

  • GPT-6.2 Astra
    OpenAI · on OpenAI
    $8.00 / $40.00
    Has every key capability
    47% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    87% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    90% less
  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    84% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    87% less
  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    93% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    94% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    98% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026Claude Opus 5.5Latest$4.00 / $20.00
  2. Jul 2026Claude Opus 5$5.00 / $25.00
  3. May 2026Claude Opus 4.8$5.00 / $25.00
  4. Apr 2026Claude Opus 4.7$5.00 / $25.00
  5. Feb 2026Claude Opus 4.6$5.00 / $25.00
  6. Nov 2025Claude Opus 4.5$5.00 / $25.00
  7. Aug 2025Claude Opus 4.1This page$15.00 / $75.00
  8. May 2025Claude Opus 4$5.00 / $25.00

Call it

Using Vercel AI Gateway's API.

Python
from litellm import completion

response = completion(
    model="vercel_ai_gateway/claude-opus-4.1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Claude Opus 4.1 cost?

On Vercel AI Gateway, Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens. Cached input costs $1.50 per million tokens.

Which APIs offer Claude Opus 4.1?

Claude Opus 4.1 runs on 3 APIs: Amazon Bedrock, Vercel AI Gateway and Databricks.

What is Claude Opus 4.1's context window?

200K tokens, with up to 32K tokens in one reply.

Is Claude Opus 4.1 being retired?

Amazon Bedrock retires it on 8 Jan 2027. 2 hosts keep serving it.

Is there a newer version of Claude Opus 4.1?

Yes. Claude Opus 5.5 is the newest model in this line, released on 22 Sep 2026.

What are cheaper alternatives to Claude Opus 4.1?

Models that cost less and keep most of what it can do: Claude Fable 5.2 on Anthropic (47% less), GPT-6.2 Astra on OpenAI (47% less), Gemini 4 Carbon on Google AI Studio (87% less) and Kimi K3.1 Pro on Databricks (87% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Claude Opus 4.1 released?

Anthropic released it on 5 Aug 2025.

What is Claude Opus 4.1's API model id?

Use claude-opus-4.1 with Vercel AI Gateway. Other hosts use their own ids: anthropic.claude-opus-4-1-20250805-v1:0 on Amazon Bedrock, databricks-claude-opus-4-1 on Databricks.

Sources

Raw catalog entry for claude-opus-4.1 on Vercel AI Gateway
{
  "cache_creation_input_token_cost": 0.00001875,
  "cache_read_input_token_cost": 0.0000015,
  "input_cost_per_token": 0.000015,
  "litellm_provider": "vercel_ai_gateway",
  "max_input_tokens": 200000,
  "max_output_tokens": 32000,
  "mode": "chat",
  "output_cost_per_token": 0.000075,
  "supports_assistant_prefill": true,
  "supports_computer_use": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true,
  "prompt_cache_min_tokens": 1024
}