cd /news/large-language-models/openai-cuts-gpt-6-2-astra-api-costs-… · home › topics › large-language-models › article
[ARTICLE · art-172218] src=alphasignal.ai ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

OpenAI Cuts GPT-6.2 Astra API Costs 40% for Overnight Background Jobs

OpenAI added two discounted completion windows to background mode in its Responses API, now in public beta: requests assigned to the 2h window cost 30% less than Standard processing and 8h requests cost 40% less, with the discounts covering multi-turn agent follow-ups. The beta supports GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Terra and GPT-6 Luna; GPT-6.2 Astra drops from $8/$40 to $5.60/$28 per 1M tokens at 2h and $4.80/$24 at 8h, while GPT-6.2 Sol at 8h costs $1.20/$6. OpenAI says model behavior and output quality remain unchanged, though the windows are completion targets rather than guarantees, and the mode lacks streaming, requires the Standard tier, shares rate limits with Batch and keeps prompt caches separate.

key takeaway

Route deferrable work to the Responses API background 2h window for 30% off or 8h for 40% off, and reuse one continuation ID per workflow to get follow-up requests higher queue priority, which Batch cannot do.

read6 min views4 publishedNov 18, 2026
OpenAI Cuts GPT-6.2 Astra API Costs 40% for Overnight Background Jobs
Image: Alphasignal (auto-discovered)

OpenAI's Responses API now gives 30% off for jobs that can wait 2 hours and 40% off for jobs that can wait 8 hours, and the discount covers multi-turn agent runs.

  • OpenAI's Responses API background mode adds discounted 2h and 8h completion windows, now in public beta.
  • The 2h window costs 30% less than Standard and the 8h window costs 40% less, follow-up requests included.
  • Works on GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Terra and GPT-6 Luna. Sol at 8h costs $1.20/$6 per 1M tokens.
  • Reusing a continuation ID gives multi-turn agent follow-ups higher queue priority, which Batch can't do.
  • Gotchas: no streaming, Standard tier required, rate limits shared with Batch, prompt caches kept separate.
  • Windows are targets, not guarantees. Critics want clarity on missed targets. See pricing .

OpenAI has added two discounted completion windows to background mode in the Responses API, now in public beta. Requests assigned to 2h cost 30% less than Standard processing, while 8h requests cost 40% less. The option targets work that can finish later, such as turning meeting notes submitted at the end of the day into a morning brief.

Background mode runs model requests asynchronously, allowing an application to submit work and retrieve the result later. The beta supports GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Terra, and GPT-6 Luna. OpenAI says model behavior and output quality remain unchanged, although requests may spend longer in the queue.

Three windows, two discounts #

The background mode guide defines three completion windows. The default, soonest, uses Standard pricing and suits reports or responses awaiting immediate review. The 2h window fits work such as analyzing morning support tickets before an afternoon triage meeting. The 8h window covers overnight document review, summaries, and scheduled research.

OpenAI starts the timer when the API accepts a request. Each window is a completion target, and delivery can occur after its stated deadline. The following examples come from the pricing page.

Token prices per 1 million tokens
Model Standard input / output 2h input / output 8h input / output Batch input / output
--- --- --- --- ---
GPT-6.2 Astra $8 / $40 $5.60 / $28 $4.80 / $24 $4 / $20
GPT-6.2 Sol $2 / $10 $1.40 / $7 $1.20 / $6 $1 / $5

Batch offers a larger 50% discount for independent requests that can be prepared and submitted together. Background windows cover workflows whose next prompt depends on an earlier model response, tool result, or external event.

Agents get room to loop #

A Batch job requires a complete set of independent requests at submission time. An agent may instead request a document, inspect the result, call a tool, and use that tool output to decide its next step. The discounted background window applies to every eligible request in that sequence, including follow-ups.

A continuation ID connects those requests. The client supplies one string for a workflow run and reuses it with the same model, project, and completion window. Eligible follow-ups then receive higher queue priority, reducing the risk that every step in a multi-stage workflow waits at the back of the queue.

Overnight loop, step by step

  1. Send an 8h request with a function tool and a client-generated continuation ID.
  2. Wait for a response.completed event throughwebhooks , or poll with the response ID.
  3. Run the tool call requested by the model.
  4. Return the tool result with the same window and continuation ID, along with previous_response_id .

Send an eight-hour request

from openai import OpenAI

client = OpenAI()

resp = client.responses.create(
    model="gpt-6.2-sol",
    input="Turn these meeting notes into a morning brief: ...",
    background=True,
    service_tier="default",  # discount requires Standard processing
    background_options={
        "completion_window": "8h",
        "continuation_id": "brief-run-42",
    },
)

print(resp.id, resp.status)  # save the ID and wait for the webhook

Queues, caches, and retention #

  • Streaming: Leavestream unset or set it tofalse . Streaming supports only thesoonest window.
  • Service tier: Discounted windows require Standard processing. Withservice_tier="auto" , the discount applies only when the API selects Standard.
  • Rate limits: These requests share the Batch/Background rate limit with Batch jobs. Input tokens count against the limit when the request is submitted.
  • Prompt caches: Standard requests cannot reuse cache entries created by2h or8h requests, even when the prompts match.
  • Temporary storage: Background mode briefly stores response data whenstore isfalse and under Zero Data Retention. OpenAI says the data is encrypted at rest.
  • Model allowlist: Support is limited to the announced models. GPT-6.1 Sol falls outside that list, and a reported request returned an HTTP 400 error for an unsupported completion window.
  • Capacity retries: After accepting a2h or8h request, the API automatically retries eligible capacity errors.

Missed deadlines and billing gaps #

The pricing model turns latency into a scheduling input. When a job can finish at any point before a morning deadline, OpenAI can queue it alongside similar work or route it to otherwise idle hardware. The discount compensates developers for that scheduling flexibility.

Joshua Wendt of S5 Labs noted that OpenAI describes the windows as targets and has not documented what happens when a target is missed. He also identified unresolved billing questions involving some prompt-caching and long-context cases.

Early implementation work includes a GitHub proposal that would let users assign 2h or 8h windows to individual agent roles, including overnight proposal generation. A separate pricing analysis noted that GPT-6.2 Sol has no Flex tier, leaving Batch and discounted background windows as its lower-cost processing options.

Jobs that can wait #

Choosing a processing option by workload
Workload Option Reason
--- --- ---
Chat replies, fraud checks, and live copilots soonest A user or system is waiting for the result.
Support-ticket analysis before a scheduled meeting 2h The task has a near-term deadline and can tolerate queueing.
Nightly summaries, compliance reviews, and morning briefs 8h The result remains useful after an overnight run.
Multi-step research or reconciliation agents 2h or8h Later steps depend on earlier model responses or tool calls.
Large sets of independent prompts Batch The requests can be assembled in advance and qualify for the larger discount.

At Astra rates, a workload using 10 million input tokens and 2 million output tokens costs $160 with Standard processing and $96 with the 8h window, a $64 saving. That pricing makes delayed background processing useful for stateful workflows whose deadlines allow several hours of queueing.

── more in #large-language-models 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/openai-cuts-gpt-6-2-…] indexed:0 read:6min 2026-11-18 · —