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
  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
  8. 11Console
    1. AAccount
    2. BWorkspaces
    3. CAPI keys
    4. DSettings
    5. EUsage
    6. FModels
    7. GPlayground
    8. HDeployments
  9. 12Billing
  10. 13Provider setup
    1. AWhen it works
    2. BCommands
    3. CSettings
    4. DProvider Console
    5. EEarnings
    6. FCrash reports
    7. GData centers
  11. 14Router
  12. 15Guardrails
  13. 16Knowledge

Reference

  1. 17API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DMessages
    5. ECount tokens
    6. FModels
    7. GTasks
    8. HEmbeddings and rerank
    9. IJobs
    10. JUploads
    11. KFiles
    12. LBatches
    13. MWebhooks
    14. NVector stores
    15. ODeployments
    16. PRequirements and headers
    17. QErrors
    18. RUsage
    19. SVersioning
  2. 18Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 19Changelog
Sheet indexAPI reference

Get started

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

Guides

  1. 04HIPS SDK
  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
  8. 11Console
    1. AAccount
    2. BWorkspaces
    3. CAPI keys
    4. DSettings
    5. EUsage
    6. FModels
    7. GPlayground
    8. HDeployments
  9. 12Billing
  10. 13Provider setup
    1. AWhen it works
    2. BCommands
    3. CSettings
    4. DProvider Console
    5. EEarnings
    6. FCrash reports
    7. GData centers
  11. 14Router
  12. 15Guardrails
  13. 16Knowledge

Reference

  1. 17API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DMessages
    5. ECount tokens
    6. FModels
    7. GTasks
    8. HEmbeddings and rerank
    9. IJobs
    10. JUploads
    11. KFiles
    12. LBatches
    13. MWebhooks
    14. NVector stores
    15. ODeployments
    16. PRequirements and headers
    17. QErrors
    18. RUsage
    19. SVersioning
  2. 18Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 19Changelog
17
  1. Docs/
  2. API reference/
  3. Batches
(Detail L)
llms.txt

Batches

OpenAI's Batch API at the API root, with HIPS's additions an OpenAI client ignores: windows longer than 24h, the hips object and signed webhooks. How to use it, the price and the limits are on Batch jobs; times on these routes are Unix seconds.

Note

Files and batches are built and not offered in production yet: every route on this page answers 404 route_not_available until they are switched on.

POST/v1/batchesnot offered

OpenAI's Batch API. Not offered in production yet: 404 route_not_available.

GET/v1/batches/{batch_id}not offered

The Batch object. Not offered in production yet.

POST/v1/batches/{batch_id}/cancelnot offered

Cancels a batch. Not offered in production yet.

GET/v1/batchesnot offered

The batches the credential reaches, newest first. Not offered in production yet.

F
Fig. 1, sheet 17API reference

Create

00000000000000000000000000000000000000001{"input_file_id": "file_...", "endpoint": "/v1/chat/completions", "completion_window": "72h", "metadata": {"run": "nightly-summaries"}}
Create sample

Parts list: POST /v1/batches

  1. 01
    input_file_idRequired

    A file of the workspace with purpose batch, within the credential's reach; unknown is a 404 file_not_found.

  2. 02
    endpointRequired

    /v1/chat/completions, the one endpoint a batch takes as built, equal to the file's url. Any other is a 400 unsupported_value.

  3. 03
    completion_windowAccepted

    A whole number of hours or days from 24h to 7d (24h, 36h, 3d, 7d), 24h when absent, one price for every window. Anything else is a 400 invalid_value.

  4. 04
    metadataAccepted

    OpenAI's: up to 16 pairs, keys up to 64 characters, values up to 512.

  5. 05
    output_expires_afterAccepted

    {"anchor": "created_at", "seconds"}, for the output and error files. 30 days by default.

  6. 06
    RequirementsHeaders

    x-hips-pool, x-hips-region and x-hips-fallback over the key's defaults set the requirements of every line, frozen on the batch. A batch is priced in market mode: x-hips-pricing-mode: stable is a 400 unsupported_value.

The gateway answers at once with the Batch object in validating, the quote bound; a model sold without batch is a 400 batch_not_offered, and a model the catalog does not know a 404 model_not_found. Takes idempotency-key.

Batch object

00000000000000000000000000000000000000001{2  "id": "batch_...",3  "object": "batch",4  "endpoint": "/v1/chat/completions",5  "model": "<pinned id>",6  "errors": null,7  "input_file_id": "file_...",8  "completion_window": "72h",9  "status": "in_progress",10  "output_file_id": null,11  "error_file_id": null,12  "created_at": 1792576800,13  "in_progress_at": 1792576860,14  "expires_at": 1792836000,15  "finalizing_at": null,16  "completed_at": null,17  "failed_at": null,18  "expired_at": null,19  "cancelling_at": null,20  "cancelled_at": null,21  "request_counts": {"total": 2, "completed": 1, "failed": 0},22  "usage": {"input_tokens": 0, "input_tokens_details": {"cached_tokens": 0}, "output_tokens": 0, "output_tokens_details": {"reasoning_tokens": 0}, "total_tokens": 0},23  "metadata": {"run": "nightly-summaries"},24  "hips": {"quote": "quote_...", "requirements": {"pool": "certified", "pricing_mode": "market", "region": null, "fallback": false}, "batch_discount_percent": 50, "max_charge_micros": 0, "held_micros": 0, "cost_micros": 0, "task_units": null, "request_counts": {"expired": 0, "cancelled": 0}}25}
Batch object sample

Parts list: The Batch object

  1. 01
    model

    The pinned id every line runs on: an id or alias in the lines resolves at creation and does not move during the window.

  2. 02
    status

    validating, failed, in_progress, finalizing, completed, expired, cancelling, cancelled, each with its time (Batch jobs says what each means).

  3. 03
    request_counts

    total, completed (lines answered 2xx) and failed (every line in the error file, expired and cancelled ones included).

  4. 04
    usage

    OpenAI's, summed over the finished lines.

  5. 05
    errors

    Set only in failed: {"object": "list", "data": [{"code", "message", "param", "line"}]}, the validation codes of Batch jobs.

  6. 06
    hips

    The bound quote, the frozen requirements, batch_discount_percent (50), max_charge_micros computed at validation, held_micros still held against the balance, cost_micros of the lines finished so far, task_units, and the expired and cancelled lines among failed.

Parts list: Cancel and list

  1. 01
    POST /v1/batches/{batch_id}/cancel

    No body. A batch in validating or in_progress enters cancelling; one already cancelling or ended answers unchanged. Takes idempotency-key.

  2. 02
    GET /v1/batches

    Newest first, after and limit; OpenAI's list with first_id, last_id and has_more. A full key lists the workspace's batches; an inference_only key and a person's token those they created.

Output and error lines

Line kindWhereShape
Answered 2xxOutput fileid (batch_req_...), custom_id, response with status_code, request_id and body, error: null
Answered with an error statusError fileThe same response, its body the error envelope; not charged
Never answeredError fileresponse: null, error with code (batch_expired, batch_cancelled, attempt_failed) and message; not charged
  • Line kind
    Answered 2xx
    Where
    Output file
    Shape
    id (batch_req_...), custom_id, response with status_code, request_id and body, error: null
  • Line kind
    Answered with an error status
    Where
    Error file
    Shape
    The same response, its body the error envelope; not charged
  • Line kind
    Never answered
    Where
    Error file
    Shape
    response: null, error with code (batch_expired, batch_cancelled, attempt_failed) and message; not charged
StatusTypeCodeSituationRetry
400invalid_request_errormissing_required_parameterA required field or header is absent; param names itNo
400invalid_request_errorinvalid_valueA value is out of range or malformed: stop with more than 16 entries, a prompt_cache_key over 512 characters, a string holding a lone surrogate escape, a router name with an empty or unknown suffix, both max_tokens names with different valuesNo
400invalid_request_errorunsupported_valuen other than 1, stream_options without stream, a message role, part, item or tool type not accepted, a hosted tool that is not servedNo
400invalid_request_errorfile_too_large, invalid_file_format, batch_not_offeredA batch input file over 200 MB; one that is not UTF-8 JSON Lines of objects, is empty, holds more than 50,000 lines, or names more than one model, one url or a router (the message names the first line at fault); a batch of a model sold without batch. Batches and files are not offered in production yetNo
403permission_errorguardrail_unsupportedA content moderation guardrail applies to text it does not scan yet: a batch, or a task request with text; the guardrail named, unchargedNo
404not_found_errormodel_not_foundUnknown catalog id, alias, pinned id or dep_; another workspace's dep_; a name starting with hips-router that is not one of the four routersNo
404not_found_errorupload_not_found, file_not_found, batch_not_foundAn id in the path, or input_file_id, that is unknown, deleted, expired, another workspace's, or out of the credential's reach. Batches and files are not offered in production yetNo
404not_found_errorroute_not_availableA route that is built and not offered on this gateway: uploads, files and batches in production, and POST /v1/messages/count_tokensNo
429rate_limit_errorrate_limit_exceededA rate limit; param is requests, tokens, uploads, batches (batches created per hour) or knowledge_search; Retry-AfterYes, after Retry-After
429rate_limit_errorconcurrency_limit_exceededToo many open batches; param is batches; Retry-AfterYes, after Retry-After
  • Status
    400
    Type
    invalid_request_error
    Code
    missing_required_parameter
    Situation
    A required field or header is absent; param names it
    Retry
    No
  • Status
    400
    Type
    invalid_request_error
    Code
    invalid_value
    Situation
    A value is out of range or malformed: stop with more than 16 entries, a prompt_cache_key over 512 characters, a string holding a lone surrogate escape, a router name with an empty or unknown suffix, both max_tokens names with different values
    Retry
    No
  • Status
    400
    Type
    invalid_request_error
    Code
    unsupported_value
    Situation
    n other than 1, stream_options without stream, a message role, part, item or tool type not accepted, a hosted tool that is not served
    Retry
    No
  • Status
    400
    Type
    invalid_request_error
    Code
    file_too_large, invalid_file_format, batch_not_offered
    Situation
    A batch input file over 200 MB; one that is not UTF-8 JSON Lines of objects, is empty, holds more than 50,000 lines, or names more than one model, one url or a router (the message names the first line at fault); a batch of a model sold without batch. Batches and files are not offered in production yet
    Retry
    No
  • Status
    403
    Type
    permission_error
    Code
    guardrail_unsupported
    Situation
    A content moderation guardrail applies to text it does not scan yet: a batch, or a task request with text; the guardrail named, uncharged
    Retry
    No
  • Status
    404
    Type
    not_found_error
    Code
    model_not_found
    Situation
    Unknown catalog id, alias, pinned id or dep_; another workspace's dep_; a name starting with hips-router that is not one of the four routers
    Retry
    No
  • Status
    404
    Type
    not_found_error
    Code
    upload_not_found, file_not_found, batch_not_found
    Situation
    An id in the path, or input_file_id, that is unknown, deleted, expired, another workspace's, or out of the credential's reach. Batches and files are not offered in production yet
    Retry
    No
  • Status
    404
    Type
    not_found_error
    Code
    route_not_available
    Situation
    A route that is built and not offered on this gateway: uploads, files and batches in production, and POST /v1/messages/count_tokens
    Retry
    No
  • Status
    429
    Type
    rate_limit_error
    Code
    rate_limit_exceeded
    Situation
    A rate limit; param is requests, tokens, uploads, batches (batches created per hour) or knowledge_search; Retry-After
    Retry
    Yes, after Retry-After
  • Status
    429
    Type
    rate_limit_error
    Code
    concurrency_limit_exceeded
    Situation
    Too many open batches; param is batches; Retry-After
    Retry
    Yes, after Retry-After

Related sheets

  • Batch jobs
  • Files
  • Webhooks
Previous sheetFiles
Next sheetWebhooks
Sheet
17 of 19
Detail
L
Updated
2026-11-11
Sign in to the Console

Product

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

Developer

  • Docs
  • Quickstart
  • 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

Compare

  • OpenRouter alternatives
  • Together AI alternatives
  • Groq alternatives
  • All comparisons

Company

  • About
  • Contact
  • Affiliate program
  • HIPS Payments

Legal

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

Support

  • Contact HIPS
  • Looking for payments support?

HIPS. AI inference for builders.

hips.com

Hyperscale Inference Processing Systems OÜ