Skip to content
HIPS
  • Earn with your GPU
  • Pricing
  • Docs
Sign inJoin early access
⌘K

Get started

  1. 01Developer hub
  2. 02Quickstart
  3. 03Migrate to HIPS

Guides

  1. 04HIPS SDK
    1. APython
    2. BTypeScript and JavaScript
    3. CGo
    4. DRust
    5. EJava
    6. F.NET
    7. GPHP
    8. HRuby
  2. 05Import and run your model
  3. 06Model and task guides
    1. ATask guides
    2. BLanguage (chat)
    3. CClassification
    4. DImage
    5. EVideo
    6. FAudio
    7. GDocument processing
  4. 07Batch jobs
  5. 08Prompt caching
  6. 09Coding-tool setup
    1. AClaude Code
    2. BOther coding tools and editor integrations
  7. 10Command line
    1. ASign in

Reference

  1. 11API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DModels
    5. ETasks
    6. FJobs
    7. GUploads
    8. HDeployments
    9. IRequirements and headers
    10. JErrors
    11. KUsage
    12. LVersioning
  2. 12Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 13Changelog
Sheet indexOperating guidance

Get started

  1. 01Developer hub
  2. 02Quickstart
  3. 03Migrate to HIPS

Guides

  1. 04HIPS SDK
    1. APython
    2. BTypeScript and JavaScript
    3. CGo
    4. DRust
    5. EJava
    6. F.NET
    7. GPHP
    8. HRuby
  2. 05Import and run your model
  3. 06Model and task guides
    1. ATask guides
    2. BLanguage (chat)
    3. CClassification
    4. DImage
    5. EVideo
    6. FAudio
    7. GDocument processing
  4. 07Batch jobs
  5. 08Prompt caching
  6. 09Coding-tool setup
    1. AClaude Code
    2. BOther coding tools and editor integrations
  7. 10Command line
    1. ASign in

Reference

  1. 11API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DModels
    5. ETasks
    6. FJobs
    7. GUploads
    8. HDeployments
    9. IRequirements and headers
    10. JErrors
    11. KUsage
    12. LVersioning
  2. 12Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 13Changelog
12
  1. Docs/
  2. Operating guidance/
  3. Idempotency
(Detail D)

PreviewNot yet validated. Join early access

llms.txt

Idempotency

idempotency-key is accepted on POST /v1/tasks, POST /v1/jobs, POST /v1/uploads and POST /v1/jobs/{id}/cancel; its value is the client's, up to a length Not decided yet, scoped to the key. The SDK generates one per task and job call.

F
Fig. 1, sheet 12Operating guidance
RuleBehavior
First requestServed; the key, the body's hash and the response are kept for the window Not decided yet
Same key, same body, within the windowThe stored response is returned, same status and body, with the original x-hips-request-id. Nothing runs, nothing is billed again
Same key, different body400 idempotency_key_reused
Same key while the first is still being answered400 idempotency_in_progress
A replay of a jobReturns the job object; the job's result is read from the job, not from a stored copy
Not on chat completionsPOST /v1/chat/completions and /v1/responses take no idempotency-key: a replay would need the gateway to store a completion body, which it never does. A retried chat completion is a new request, a new quote and a new charge
  • Rule
    First request
    Behavior
    Served; the key, the body's hash and the response are kept for the window Not decided yet
  • Rule
    Same key, same body, within the window
    Behavior
    The stored response is returned, same status and body, with the original x-hips-request-id. Nothing runs, nothing is billed again
  • Rule
    Same key, different body
    Behavior
    400 idempotency_key_reused
  • Rule
    Same key while the first is still being answered
    Behavior
    400 idempotency_in_progress
  • Rule
    A replay of a job
    Behavior
    Returns the job object; the job's result is read from the job, not from a stored copy
  • Rule
    Not on chat completions
    Behavior
    POST /v1/chat/completions and /v1/responses take no idempotency-key: a replay would need the gateway to store a completion body, which it never does. A retried chat completion is a new request, a new quote and a new charge

How to use it

  • Generate the key before the first attempt and reuse it on every retry of the same body.
  • Treat a 400 idempotency_in_progress as a signal to wait and retry with the same key, not as a failure.
  • A different body with the same key is a 400 idempotency_key_reused: a bug in the caller, never retried.
  • The replay carries the original x-hips-request-id, so the Console shows one request and one charge.

Related sheets

  • Tasks reference
  • Retries and billing outcomes
Previous sheetRetries and billing outcomes
Next sheetStreaming
Sheet
12 of 13
Detail
D
Updated
2026-10-21
Status
Preview
Join early access

On this sheet

  1. How to use it

Product

  • Inference
  • Models
  • Deploy your model
  • Always-on GPU capacity
  • How it works
  • Use cases
  • Pricing

Developer

  • Docs
  • Quickstart preview
  • Migrate to HIPS
  • HIPS SDK
  • Batch jobs
  • API reference

Provider

  • Earn with your GPU
  • Register GPU interest
  • Download for Mac
  • Download for Windows
  • Download for Linux

Resource

  • Security and Data
  • Resources
  • llms.txt

Company

  • About
  • Contact
  • Affiliate program
  • HIPS Payments

Legal

  • Legal
  • Consumer Health Data Privacy Policy
  • Report content
  • Cookie settings

Support

  • Contact HIPS
  • Looking for payments support?

HIPS. AI inference for builders.

hips.com

Hyperscale Inference Processing Systems OÜ