Fast mode (research preview)

Fast mode delivers up to 2.5x higher output tokens per second from Claude Opus 4.8 and Claude Opus 4.7 at premium pricing. Set speed: "fast" with the fast-mode-2026-02-01 beta header on your request to opt in.



Supported models

Fast mode is supported on the following models:

• Claude Opus 4.8 (claude-opus-4-8)
• Claude Opus 4.7 (claude-opus-4-7)



How fast mode works

Fast mode runs the same model with a faster inference configuration. There is no change to intelligence or capabilities.

• Up to 2.5x higher output tokens per second compared to standard speed
• Speed benefits are focused on output tokens per second (OTPS), not time to first token (TTFT)
• Same model weights and behavior (not a different model)
• Compatible with streaming, where the OTPS gain is most visible



Basic usage

client = anthropic.Anthropic()

response = client.beta.messages.create(
    model="claude-opus-4-8",
    max_tokens=4096,
    speed="fast",
    betas=["fast-mode-2026-02-01"],
    messages=[
        {"role": "user", "content": "Refactor this module to use dependency injection"}
    ],
)

print(response.content[0].text)



Pricing

Fast mode is priced at a per-model multiplier on standard rates across the full context window, including requests over 200k input tokens. The following table shows fast mode pricing for each supported model:

Fast mode pricing stacks with other pricing modifiers:

• Prompt caching multipliers apply on top of fast mode pricing
• Data residency multipliers apply on top of fast mode pricing

For complete pricing details, see the Pricing page.



Rate limits

Fast mode has a dedicated rate limit that is separate from standard Opus rate limits. When your fast mode rate limit is exceeded, the API returns a 429 error with a retry-after header indicating when capacity will be available.

The response includes headers that indicate your fast mode rate limit status:

For tier-specific rate limits, see the Rate limits page.



Checking which speed was used

The response usage object includes a speed field that indicates which speed was used, either "fast" or "standard". On supported models, fast mode doesn't silently fall back to standard speed on rate limits or capacity (you'll get a 429 or 529 instead), so when you request speed: "fast" on Claude Opus 4.8 or Claude Opus 4.7, usage.speed is "fast". On Claude Opus 4.6, where fast mode is not available, requests with speed: "fast" run at standard speed and return usage.speed: "standard". Check this field to confirm which speed served a request.

client = anthropic.Anthropic()

response = client.beta.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    speed="fast",
    betas=["fast-mode-2026-02-01"],
    messages=[{"role": "user", "content": "Hello"}],
)

print(response.usage.speed)  # "fast" or "standard"

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
// ...
  "usage": {
    "input_tokens": 8,
    "output_tokens": 12,
    "speed": "fast"
  }
}

To track fast mode usage and costs across your organization, see the Usage and Cost API.



Retries and fallback



Automatic retries

When fast mode rate limits are exceeded, the API returns a 429 error with a retry-after header. The Anthropic SDKs automatically retry these requests up to 2 times by default (configurable with max_retries), waiting for the server-specified delay before each retry. Because fast mode uses continuous token replenishment, the retry-after delay is typically short and requests succeed once capacity is available.



Falling back to standard speed

If you'd prefer to fall back to standard speed rather than wait for fast mode capacity, catch the rate limit error and retry without speed: "fast". Set max_retries to 0 on the initial fast request to skip automatic retries and fail immediately on rate limit errors.

Because setting max_retries to 0 also disables retries for other transient errors (overloaded, internal server errors), the following examples reissue the original request with default retries for those cases.

client = anthropic.Anthropic()


def create_message_with_fast_fallback(max_retries=0, max_attempts=3, **params):
    try:
        return client.with_options(max_retries=max_retries).beta.messages.create(
            **params
        )
    except anthropic.RateLimitError:
        if params.get("speed") == "fast":
            del params["speed"]
            return create_message_with_fast_fallback(max_retries=max_retries, **params)
        raise
    except (
        anthropic.APIStatusError,
        anthropic.APIConnectionError,
    ) as error:
        if isinstance(error, anthropic.APIStatusError) and error.status_code < 500:
            raise
        if max_attempts > 1:
            return create_message_with_fast_fallback(
                max_retries=max_retries, max_attempts=max_attempts - 1, **params
            )
        raise


message = create_message_with_fast_fallback(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
    betas=["fast-mode-2026-02-01"],
    speed="fast",
    max_retries=0,
)



Considerations

• Prompt caching: Switching between fast and standard speed invalidates the prompt cache. Requests at different speeds do not share cached prefixes.
• Supported models: Fast mode is supported on Claude Opus 4.8 and Claude Opus 4.7 (fast mode deprecated; removal on July 24, 2026, with the model itself unaffected). On Claude Opus 4.6, requests with speed: "fast" do not return an error: they run at standard speed and are billed at standard rates. On any other model, sending speed: "fast" returns an error.
• TTFT: Fast mode's benefits are focused on output tokens per second (OTPS), not time to first token (TTFT).
• Batch API: Fast mode is not available with the Batch API.
• Priority Tier: Fast mode is not available with a Priority Tier commitment.
• Claude Platform on AWS: Fast mode is not currently available on Claude Platform on AWS.



Next steps