Fast mode

Fast mode delivers up to 2.5× faster speeds and more consistent latency while keeping pay-as-you-go flexibility. Fast mode is ideal for high-value, user-facing applications with regular traffic where latency is paramount.

Configuring Fast mode

You can configure requests to the Responses API or Chat Completions API to use Fast mode through either a request parameter or a project setting.

To opt in to Fast mode for an individual request, set the service_tier parameter to fast. Setting service_tier to priority provides the same behavior for supported models.

1
2
3
4
5
curl https://api.openai.com/v1/responses   -H "Authorization: Bearer $OPENAI_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "gpt-5.6-sol",
    "input": "What does 'fit check for my napalm era' mean?",
    "service_tier": "fast"
  }'

1
2
3
4
5
6
7
8
9
10
11
import OpenAI from "openai";

const openai = new OpenAI();

const response = await openai.responses.create({
  model: "gpt-5.6-sol",
  input: "What does 'fit check for my napalm era' mean?",
  service_tier: "priority",
});

console.log(response);

1
2
3
4
5
6
7
8
9
10
from openai import OpenAI

client = OpenAI()

response = client.responses.create(
    model="gpt-5.6-sol",
    input="What does 'fit check for my napalm era' mean?",
    service_tier="fast",
)
print(response)

To opt in at the project level, open Settings, select General under Project, and change Project Service Tier to Fast. Requests that don’t specify a service_tier then default to Fast mode. Requests for the project transition gradually to Fast mode over time.

The service_tier field in the Responses or Chat Completions response object identifies the tier used to process the request. For GPT-5.6 and earlier models, the response returns priority whether the request specifies priority or fast.

Rate limits and ramp rate

Baseline limits

Fast mode consumption counts toward rate limits the same way as Standard processing. Use your usual retry logic and wait between attempts. For a given model, Standard processing and Fast mode share the same rate limit.

Ramp rate limit

If your traffic ramps too fast, the system may downgrade some Fast mode requests to standard speeds and charge standard rates. When this happens, the response contains service_tier: "default". The ramp rate limit may apply if you send at least 1 million tokens per minute (TPM) and increase TPM by more than 50% within 15 minutes.

To avoid triggering the ramp rate limit:

• Ramp gradually when changing models or snapshots.
• Use feature flags to shift traffic over hours, not instantly.
• Avoid running large extract, transform, and load (ETL) or batch jobs in Fast mode.

Usage considerations

• Fast mode charges a per-token premium over Standard processing. See the pricing page for details and supported models.
• Cached input discounts still apply to Fast mode requests.
• Fast mode supports multimodal requests, including image inputs.
• To view Fast mode requests in the usage dashboard, select the option to group by service tier. For GPT-5.6 and earlier models, these requests appear as priority even when you specify fast.
• Long context, fine-tuned models, and embeddings are not supported.

Frequently asked questions

For account and policy information, see the Fast mode FAQ.

Is Fast mode available in all regions?

Availability depends on the laws and regulations in each jurisdiction. Contact your account director if you have questions about availability in your region.

How does Fast mode interact with Scale Tier?

Scale Tier and Fast mode are separate. Fast mode requests have separate billing and don’t count against purchased Scale Tier TPM bundles. Scale Tier spillover traffic doesn’t automatically move to Fast mode.

How is Fast mode billed?

Fast mode charges a per-token premium compared with Standard processing. All processing modes count toward your annual Enterprise spend commitment, and eligible cached input tokens receive the same discounts available for Standard processing.

To review usage, open the usage dashboard, select Responses or Chat Completions, and group by service tier. To review costs, group by line item.

Which models and modalities support Fast mode?

Fast mode supports the multimodal capabilities available with Standard processing, including image inputs. Long context, fine-tuned models, and embeddings aren’t supported. Future GPT models may support Fast mode, but support isn’t guaranteed for every model.

Are ramp rate limits shared across projects or organizations?

Yes. All your traffic contributes to the same ramp rate limit. If you routinely encounter ramp rate limits, consider purchasing Scale Tier quota.

What happens if Fast mode doesn’t meet its latency target?

Contact your account director if you have questions or concerns. Fast mode and Scale Tier receive the same service-level agreement treatment, and eligible Enterprise agreements may provide service credits when those targets aren’t met.

Is Fast mode compatible with data residency, Zero Data Retention, and a BAA?

Yes. Fast mode is compatible with data residency, Zero Data Retention, and a Business Associate Agreement (BAA). Existing endpoint, tool, eligibility, and contractual requirements still apply. See the Your data guide for details.