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. 09Code with HIPS
  7. 10Coding-tool setup
    1. AHIPS Code
    2. BClaude Code
    3. CCodex
    4. DOpenCode
    5. EKilo
    6. FPi
    7. GQwen Code
    8. HCrush
    9. ICline
    10. JPrime Agent
    11. KAider
    12. LGoose
    13. MHermes Agent
    14. NGrok Build
    15. ODeepSeek Harness
    16. POther coding tools and editor integrations
  8. 11Command line
    1. AInstall and update
    2. BSign in
    3. CStatus and models
    4. DCoding agents
  9. 12Console
    1. AAccount
    2. BWorkspaces
    3. CAPI keys
    4. DSettings
    5. EUsage
    6. FModels
    7. GPlayground
    8. HDeployments
  10. 13Billing
  11. 14Provider setup
    1. AWhen it works
    2. BCommands
    3. CSettings
    4. DProvider Console
    5. EEarnings
    6. FCrash reports
    7. GData centers
  12. 15Semantic routing
  13. 16Guardrails
  14. 17Knowledge

Reference

  1. 18API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DMessages
    5. ECount tokens
    6. FModels
    7. GPrices API
    8. HTasks
    9. IEmbeddings and rerank
    10. JImages
    11. KJobs
    12. LUploads
    13. MFiles
    14. NBatches
    15. OWebhooks
    16. PVector stores
    17. QDeployments
    18. RRequirements and headers
    19. SErrors
    20. TUsage
    21. UVersioning
  2. 19Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 20Changelog
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. 09Code with HIPS
  7. 10Coding-tool setup
    1. AHIPS Code
    2. BClaude Code
    3. CCodex
    4. DOpenCode
    5. EKilo
    6. FPi
    7. GQwen Code
    8. HCrush
    9. ICline
    10. JPrime Agent
    11. KAider
    12. LGoose
    13. MHermes Agent
    14. NGrok Build
    15. ODeepSeek Harness
    16. POther coding tools and editor integrations
  8. 11Command line
    1. AInstall and update
    2. BSign in
    3. CStatus and models
    4. DCoding agents
  9. 12Console
    1. AAccount
    2. BWorkspaces
    3. CAPI keys
    4. DSettings
    5. EUsage
    6. FModels
    7. GPlayground
    8. HDeployments
  10. 13Billing
  11. 14Provider setup
    1. AWhen it works
    2. BCommands
    3. CSettings
    4. DProvider Console
    5. EEarnings
    6. FCrash reports
    7. GData centers
  12. 15Semantic routing
  13. 16Guardrails
  14. 17Knowledge

Reference

  1. 18API reference
    1. AAuthentication
    2. BChat completions
    3. CResponses
    4. DMessages
    5. ECount tokens
    6. FModels
    7. GPrices API
    8. HTasks
    9. IEmbeddings and rerank
    10. JImages
    11. KJobs
    12. LUploads
    13. MFiles
    14. NBatches
    15. OWebhooks
    16. PVector stores
    17. QDeployments
    18. RRequirements and headers
    19. SErrors
    20. TUsage
    21. UVersioning
  2. 19Operating guidance
    1. ALimits
    2. BErrors
    3. CRetries and billing outcomes
    4. DIdempotency
    5. EStreaming
    6. FData handling
    7. GCompatibility matrix
  3. 20Changelog
18
  1. Docs/
  2. API reference/
  3. Prices API
(Detail G)
llms.txt

Prices API

On this sheet20 sections
  1. The routes
  2. Money and units
  3. A worked conversion
  4. Pools
  5. A pool in the model id
  6. How often it changes
  7. The catalog
  8. Price rows
  9. Which row is the price now
  10. The model fields that decide a price
  11. Plans
  12. Settings
  13. An answer, abridged
  14. One model
  15. The price history
  16. The price feeds per pool
  17. What a feed lists
  18. Each document
  19. The combined feed
  20. Errors

HIPS publishes its prices for machines to read. Three routes on https://hips.com answer the public catalog with every published rate, one model with its own rates, and the history of each rate: the same reads the Pricing page and each model's page are built from. Three price feeds on https://ai.hips.com list each pool's offers, one document per model, under the model id that runs it there (The price feeds per pool). Use them to show HIPS's prices in your own product, to estimate what a workload costs, or to follow a rate as it moves.

The routes

Route on https://hips.comAnswersKey
GET /api/modelsThe whole public catalog: every published model, every public price row in effect or announced, the plans and the public settingsNone
GET /api/models/{id}One published model and its own price rowsNone
GET /api/prices/historyHow each published on-demand rate has moved, per model, pool and kindNone
  • Route on https://hips.com
    GET /api/models
    Answers
    The whole public catalog: every published model, every public price row in effect or announced, the plans and the public settings
    Key
    None
  • Route on https://hips.com
    GET /api/models/{id}
    Answers
    One published model and its own price rows
    Key
    None
  • Route on https://hips.com
    GET /api/prices/history
    Answers
    How each published on-demand rate has moved, per model, pool and kind
    Key
    None

Each answers JSON in a data envelope, the same for every caller: no key, no cookie and no sign-in, and nothing about a workspace. The answers carry no cross-origin headers, so read them from your server, not from a browser page on another site. They are the catalog's rates, the same for every workspace; what one request was charged is in its own answer's x-hips-cost-micros (How a request is priced).

Money and units

Every amount is a whole number, amount_micros, in micro-dollars: millionths of a US dollar, 1,000,000 to the dollar. A row's unit says what one amount buys, and its kind what it prices.

KindUnitWhat one amount buys
language_inputper_million_tokensA million prompt tokens of a language model
language_input_cachedper_million_tokensA million prompt tokens billed as verified cache hits. HIPS keeps no prompt cache yet, so cached input is billed as input today: every prompt token is priced at language_input (Prompt caching)
language_outputper_million_tokensA million generated tokens
classificationper_thousand_classificationsA thousand classifications
task_secondper_secondA started second of a task model's compute
media_unitper_media_unitOne unit of the setting the row names in setting
always_on_hourlyper_allocated_hourAn hour of always-on capacity allocated
allocation_storageper_gigabyte_hourA gigabyte kept for an hour for a stopped allocation
storageper_gigabyte_monthA gigabyte stored for a month (Storage)
plan_feeper_monthA paid plan's monthly fee
plan_fee_annualper_yearA paid plan's yearly fee
plan_included_creditsper_periodThe credit a paid plan includes each monthly period, granted as a weekly pool (Weekly pool of included credit)
batch_discountbasis_pointsNot money: the batch discount in hundredths of a percent, 5,000 being 50%
mto_discountbasis_pointsNot money: a payment discount in hundredths of a percent
  • Kind
    language_input
    Unit
    per_million_tokens
    What one amount buys
    A million prompt tokens of a language model
  • Kind
    language_input_cached
    Unit
    per_million_tokens
    What one amount buys
    A million prompt tokens billed as verified cache hits. HIPS keeps no prompt cache yet, so cached input is billed as input today: every prompt token is priced at language_input (Prompt caching)
  • Kind
    language_output
    Unit
    per_million_tokens
    What one amount buys
    A million generated tokens
  • Kind
    classification
    Unit
    per_thousand_classifications
    What one amount buys
    A thousand classifications
  • Kind
    task_second
    Unit
    per_second
    What one amount buys
    A started second of a task model's compute
  • Kind
    media_unit
    Unit
    per_media_unit
    What one amount buys
    One unit of the setting the row names in setting
  • Kind
    always_on_hourly
    Unit
    per_allocated_hour
    What one amount buys
    An hour of always-on capacity allocated
  • Kind
    allocation_storage
    Unit
    per_gigabyte_hour
    What one amount buys
    A gigabyte kept for an hour for a stopped allocation
  • Kind
    storage
    Unit
    per_gigabyte_month
    What one amount buys
    A gigabyte stored for a month (Storage)
  • Kind
    plan_fee
    Unit
    per_month
    What one amount buys
    A paid plan's monthly fee
  • Kind
    plan_fee_annual
    Unit
    per_year
    What one amount buys
    A paid plan's yearly fee
  • Kind
    plan_included_credits
    Unit
    per_period
    What one amount buys
    The credit a paid plan includes each monthly period, granted as a weekly pool (Weekly pool of included credit)
  • Kind
    batch_discount
    Unit
    basis_points
    What one amount buys
    Not money: the batch discount in hundredths of a percent, 5,000 being 50%
  • Kind
    mto_discount
    Unit
    basis_points
    What one amount buys
    Not money: a payment discount in hundredths of a percent

A kind appears only where a row of it is published. Markups, commissions, provider payouts and floors are never in these answers.

A worked conversion

A language_input row with amount_micros 137200 and unit per_million_tokens:

  • Per million tokens: 137,200 / 1,000,000 = $0.1372.
  • Per token: 137,200 / 1,000,000 / 1,000,000 = $0.0000001372, that is amount_micros divided by 1,000,000,000,000.
  • For a prompt of 2,000 tokens: 2,000 x 137,200 / 1,000,000 = 274.4 micro-dollars, $0.0002744, at that rate.
  • A storage row of 100000 per_gigabyte_month is $0.10 per GB-month; a plan_fee row of 20000000 per_month is $20 a month.

Pools

A request runs in one of two pools, and each pool carries its own price rows for a model, named in these answers as on the inference API. A request chooses among three:

ChoiceValueWhere it runs
Auto (default)autoWherever HIPS has capacity for the model now, in the Certified or the Community pool, at that pool's rates; Auto has no price rows of its own
CertifiedcertifiedData-center supply operated by an approved provider
CommunitycommunityDevices their owners run
  • Choice
    Auto (default)
    Value
    auto
    Where it runs
    Wherever HIPS has capacity for the model now, in the Certified or the Community pool, at that pool's rates; Auto has no price rows of its own
  • Choice
    Certified
    Value
    certified
    Where it runs
    Data-center supply operated by an approved provider
  • Choice
    Community
    Value
    community
    Where it runs
    Devices their owners run
  • A request that names no pool takes its key's default pool, and Auto where the key sets none (Requirements and headers).
  • Under Auto, HIPS chooses among the pools the workspace and its guardrails allow that offer and price the model and have capacity for it now. Where both have, it weighs the request's expected charge in each pool against its expected time to the first token, the lower price winning a tie and then the Certified pool; where the first token cannot be estimated in a pool, the lower price decides. A workspace that keeps its requests out of the Community pool runs Auto in the Certified pool alone.
  • The request pays the rates of the pool it ran in, and the answer's x-hips-pool names that pool.
  • A model's price row whose pool is null applies in every pool the model is offered in.

A pool in the model id

On chat completions, Responses and Messages, a model id may carry its pool. A model id without a suffix uses Auto, as in the Playground and everywhere else in HIPS, or the key's default pool where the workspace set one.

Model idRuns
<model id>Under the key's default pool: Auto, unless the workspace set another
<model id>:autoAuto, whatever the key's default
<model id>:certifiedThe Certified pool alone, with no fallback, at its rates
<model id>:communityThe Community pool alone, with no fallback, at its rates
  • Model id
    <model id>
    Runs
    Under the key's default pool: Auto, unless the workspace set another
  • Model id
    <model id>:auto
    Runs
    Auto, whatever the key's default
  • Model id
    <model id>:certified
    Runs
    The Certified pool alone, with no fallback, at its rates
  • Model id
    <model id>:community
    Runs
    The Community pool alone, with no fallback, at its rates

A bare id, or :auto, is served wherever HIPS has capacity for the model, in the Certified or the Community pool, among the pools your workspace's settings allow. Where both have capacity, it takes the one where the request costs less, weighing the expected time to the first token where both pools can estimate it.

  • A suffix is the request that names the model without it, with x-hips-pool set to auto, certified or community, and for a pool x-hips-fallback: false (Requirements and headers). x-hips-pool naming anything else beside it, or x-hips-fallback: true beside :certified or :community, is a 400 requirement_conflict. A workspace that keeps its requests out of the Community pool refuses :community with the same code at model.
  • x-hips-model and the usage record name the model without the suffix; x-hips-pool names the pool the request ran in.
  • Only these three words are pool suffixes. Any other, or one on a router's name or a dep_ id, is read as the whole name: a 404 model_not_found, or the router's own 400. The task API, embeddings, rerank and a batch file's lines take no suffix: name the pool with x-hips-pool or hips.pool there.

How often it changes

  • revision counts the catalog's changes: it moves whenever HIPS changes a model, a pool, a price, a plan or a setting.
  • prices_updated_at is the latest moment a price row now in effect took effect. An announced price moves it when its moment comes, with no new revision; announcing one does not move it. It is null while no price is in effect.
  • published_at is when the catalog was last published. It moves on a regular cadence even when nothing changed, so it never tells you that anything did.
  • The site keeps its copy of the catalog for 60 seconds before reading it again, and answers Cache-Control: public, max-age=60; the price history answers what is left of its own 60 seconds. Reading more often than once a minute gains nothing: compare revision and prices_updated_at to tell whether anything changed.
  • There is no ETag: every request is answered in full. Every answer the catalog served carries x-hips-request-id; quote it when you write to support.

The catalog

GEThttps://hips.com/api/modelsserved

The whole public catalog in one answer: every published model with its pools, every public price row in effect or announced ahead, the plans a new subscriber may choose and the public settings.

cURL

00000000000000000000000000000000000000001curl -s https://hips.com/api/models
cURL sample

Parts list: The answer's data

  1. 01
    revisioninteger

    The catalog's revision (How often it changes).

  2. 02
    published_atRFC 3339 time

    When the catalog was last published.

  3. 03
    prices_updated_atRFC 3339 time or null

    The latest moment a price row now in effect took effect.

  4. 04
    modelsarray

    Every model in preview, live or deprecated; a draft or a retired model is never listed.

  5. 05
    pricesarray

    Every public price row in effect now and every one announced ahead, on demand and batch.

  6. 06
    plansarray

    The plans a new subscriber may choose, with their terms.

  7. 07
    stable_schedulesarray

    An empty list: no stable price is published in the catalog (Stable prices).

  8. 08
    settingsobject

    The public settings (Settings).

Price rows

Parts list: Each row of prices

  1. 01
    kindstring

    What the row prices (Money and units).

  2. 02
    modelstring or null

    The model's id, as the model's id and as a request's model; null on a row that is not a model's (a plan's, storage, a discount).

  3. 03
    poolstring or null

    certified or community (Pools); null on a model's row that applies in every pool it is offered in, and on every row that is not a model's.

  4. 04
    settingstring or null

    On a media_unit row, the model's setting the rate applies to; null on every other row.

  5. 05
    planstring or null

    On plan_fee, plan_fee_annual and plan_included_credits, the plan the row prices (pro, business); null on every other row.

  6. 06
    unitstring

    What one amount buys (Money and units).

  7. 07
    amount_microsinteger

    The amount in micro-dollars, or in basis points where unit is basis_points.

  8. 08
    batchboolean

    True on a batch row: the rate a batch line pays, derived from the on-demand row of the same model, pool, kind and setting at the batch discount, 50%, rounded down to the micro-dollar, and published beside it at the same effective_from.

  9. 09
    pricing_modestring

    market on every row of the catalog.

  10. 10
    effective_fromRFC 3339 time

    When the row took effect, or takes effect when scheduled is true.

  11. 11
    scheduledboolean

    True while effective_from is ahead: a change announced before it applies.

Which row is the price now

  • For one model, pool, kind and setting, the row with batch and scheduled both false is the on-demand rate in effect now, and the row with batch true and scheduled false beside it is the batch rate.
  • A row with scheduled true is an announced change. The row in effect stays listed beside it until its effective_from; from that moment the new row is in effect and the one it replaced is no longer listed.
  • A request's rate is the one in effect when it is accepted, and holds for every attempt and retry of it.
  • A model's batch rows are listed whether or not it is sold in batch: where its batch.offered is false, a batch for it is refused with 400 batch_not_offered.
  • A language_input_cached row is the rate a verified cache hit will be billed at. A pool bills it only where the model's prompt_cache flag for that pool is true; both flags read false today, since HIPS keeps no prompt cache yet, so every prompt token is billed at language_input.

Reading one rate, in dollars per unit:

00000000000000000000000000000000000000001import json2import os3import urllib.request4 5with urllib.request.urlopen("https://hips.com/api/models") as answer:6    catalog = json.load(answer)["data"]7 8 9def rate(model, pool, kind):10    """The on-demand rate in effect now, in dollars per unit, or None."""11    rows = [p for p in catalog["prices"]12            if p["model"] == model and p["kind"] == kind and not p["batch"] and not p["scheduled"]]13    row = next((p for p in rows if p["pool"] == pool), None) or next((p for p in rows if p["pool"] is None), None)14    return None if row is None else row["amount_micros"] / 1_000_00015 16 17# Dollars per million input tokens in the Certified pool.18print(rate(os.environ["HIPS_MODEL"], "certified", "language_input"))
Reads from the environmentHIPS_MODEL

The model fields that decide a price

Parts list: On each model

  1. 01
    idstring

    The model id a request names, and the model of its price rows.

  2. 02
    statuspreview, live or deprecated

    A deprecated model carries the day it retires in retires_at.

  3. 03
    typestring

    The model's type; a language model is priced per token.

  4. 04
    billingobject

    unit and kinds: the kinds the model is billed in, which its price rows carry. A language model's are language_input, language_input_cached and language_output.

  5. 05
    poolsarray

    Each pool row that serves the model now: pool, lane (shared, or always_on), engine (for example llamacpp or vllm) and precision, the precision that pool serves the model at on that engine: name as recorded (Q4_K_M, mxfp4, bf16) and level, one of fp32, bf16, fp16, fp8, int8, fp6, fp4 and int4, or null for a type with no such word. precision is left out where none is recorded. A pool's rates are the same on each of its engines. A model can carry price rows for a pool its pools does not list: they are that pool's rates once it serves the model, and no request runs there meanwhile.

  6. 06
    prices_publishedboolean

    True when at least one pool has a row in effect for every kind billing.kinds names. A model listed with false has no complete price yet.

  7. 07
    batchobject

    offered, whether a batch of the model is accepted, and reason_code, floors or other where batch was turned off for it, else null.

  8. 08
    prompt_cacheobject

    Per pool, certified and community: true where a cached prompt token is billed at language_input_cached. False in both pools today: cached input is billed as input.

  9. 09
    limitsobject

    The limits that are set, by name, context_tokens among them.

Each model also carries its names and description (name, family, size, variant, description), its task and modality, its dates (released_at, deprecated_at), its source on Hugging Face (hugging_face_id, hugging_face_revision, hugging_face_url), architecture, parameter_count, the current version and pinned_id, its versions and aliases, modalities, formats, license, tool_calls per pool, and agents, the coding agents tested with it (Models and task guides). None of them changes a price.

Plans

Parts list: Each plan

  1. 01
    planstring

    free, pro or business.

  2. 02
    termsobject or null

    The terms in effect for a new subscriber: models, the model ids the plan includes (null: every model), features, among router, guardrails, knowledge and deployments, and limits by name, empty while none is set.

  3. 03
    effective_fromRFC 3339 time or null

    When those terms took effect.

  4. 04
    scheduledarray

    Each change of terms announced ahead, with its effective_from and terms.

A plan's fees and its included credit are price rows naming it in plan: plan_fee per month, plan_fee_annual per year and plan_included_credits per monthly period. Free has no fee row. Billing explains the plans.

Settings

settings holds the catalog's public settings, each only once it is set: the free allowance (free_allowance_micros_monthly, free_allowance_plans, free_allowance_reset) and the holding benefit (holding_threshold_mto, holding_multiplier, holding_verification_cadence). holding_benefit_open is always there, false until the holding benefit opens.

An answer, abridged

Read from hips.com on 2026-11-13 and abridged, the model id left as a placeholder and prompt_cache as the catalog answers it now.

Abridged answer

00000000000000000000000000000000000000001{2  "data": {3    "revision": 131,4    "published_at": "2026-11-13T15:09:26.683968Z",5    "prices_updated_at": "2026-11-11T00:00:00Z",6    "models": [7      {8        "id": "<model id>",9        "type": "language",10        "status": "live",11        "billing": { "unit": "tokens", "kinds": ["language_input", "language_input_cached", "language_output"] },12        "pools": [13          { "pool": "certified", "lane": "shared", "engine": "llamacpp", "precision": { "name": "Q4_K_M", "level": "int4" } },14          { "pool": "community", "lane": "shared", "engine": "llamacpp", "precision": { "name": "Q4_K_M", "level": "int4" } }15        ],16        "batch": { "offered": false, "reason_code": null },17        "prompt_cache": { "certified": false, "community": false },18        "prices_published": true19      }20    ],21    "prices": [22      { "kind": "language_input", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 137200, "batch": false, "pricing_mode": "market", "effective_from": "2026-11-10T02:41:42.059458Z", "scheduled": false },23      { "kind": "language_input", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 68600, "batch": true, "pricing_mode": "market", "effective_from": "2026-11-10T02:41:42.059458Z", "scheduled": false },24      { "kind": "language_input_cached", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 13720, "batch": false, "pricing_mode": "market", "effective_from": "2026-11-10T02:41:42.059458Z", "scheduled": false },25      { "kind": "language_output", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 392000, "batch": false, "pricing_mode": "market", "effective_from": "2026-11-10T02:41:42.059458Z", "scheduled": false },26      { "kind": "plan_fee", "model": null, "pool": null, "setting": null, "plan": "pro", "unit": "per_month", "amount_micros": 20000000, "batch": false, "pricing_mode": "market", "effective_from": "2026-10-26T00:00:00Z", "scheduled": false },27      { "kind": "storage", "model": null, "pool": null, "setting": null, "plan": null, "unit": "per_gigabyte_month", "amount_micros": 100000, "batch": false, "pricing_mode": "market", "effective_from": "2026-10-27T00:00:00Z", "scheduled": false }28    ],29    "plans": [30      { "plan": "pro", "terms": { "models": null, "features": ["router", "guardrails", "knowledge"], "limits": {} }, "effective_from": "2026-11-11T00:00:00Z", "scheduled": [] }31    ],32    "stable_schedules": [],33    "settings": { "holding_benefit_open": false }34  }35}
Abridged answer sample

One model

GEThttps://hips.com/api/models/{id}served

One published model and its own price rows: the catalog's entry for that model, without the plans, the rows that are not a model's and the settings.

cURL

00000000000000000000000000000000000000001curl -s "https://hips.com/api/models/$HIPS_MODEL"
Reads from the environmentHIPS_MODEL

Parts list: The answer's data

  1. 01
    modelobject

    The model as the catalog lists it (The model fields that decide a price).

  2. 02
    pricesarray

    The rows whose model is this one, in effect and announced, on demand and batch, each as in the catalog.

  3. 03
    revisioninteger

    The catalog's revision.

  4. 04
    published_atRFC 3339 time

    When the catalog was last published.

{id} is a model's id as the catalog lists it, never a pinned id or an alias. An id the catalog does not list, a draft and a retired model answer 404 not_found.

Read from hips.com on 2026-11-13 and abridged, as the catalog's answer is.

Abridged answer

00000000000000000000000000000000000000001{2  "data": {3    "model": {4      "id": "<model id>",5      "status": "live",6      "billing": { "unit": "tokens", "kinds": ["language_input", "language_input_cached", "language_output"] },7      "batch": { "offered": true, "reason_code": null },8      "prompt_cache": { "certified": false, "community": false },9      "prices_published": true10    },11    "prices": [12      { "kind": "language_input", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 98000, "batch": false, "pricing_mode": "market", "effective_from": "2026-10-28T01:19:34.315366Z", "scheduled": false },13      { "kind": "language_input", "model": "<model id>", "pool": "certified", "setting": null, "plan": null, "unit": "per_million_tokens", "amount_micros": 49000, "batch": true, "pricing_mode": "market", "effective_from": "2026-10-28T01:19:34.315366Z", "scheduled": false }14    ],15    "revision": 131,16    "published_at": "2026-11-13T15:12:52.663259Z"17  }18}
Abridged answer sample

The price history

GEThttps://hips.com/api/prices/historyserved

How each published on-demand rate has moved since its model was listed: one series per model, pool, kind and setting, each rate with the moment it took effect.

00000000000000000000000000000000000000001curl -s https://hips.com/api/prices/history
Language

Parts list: The query

  1. 01
    modelOptional

    A model's id: that model's series alone, with every point.

  2. 02
    sinceOptional, with model

    The start of a UTC day, written YYYY-MM-DDT00:00:00Z and in no other form: each series then begins at the rate in effect at that moment.

Without model, each series carries its last 30 points; with it, every point, up to the newest 200 of a series. Any other parameter, a parameter given twice, a since in another form or without model, and a model outside the form of a model id (lowercase letters, digits, dots and hyphens) answer 400 invalid_request with the parameter in param; a model the catalog does not list answers 404 not_found.

Parts list: The answer's data

  1. 01
    revisioninteger

    The catalog's revision.

  2. 02
    prices_updated_atRFC 3339 time or null

    As in the catalog.

  3. 03
    seriesarray

    One series per model, pool, kind and setting.

Parts list: Each series

  1. 01
    model, pool, kind, setting, unit

    As on a price row; pool null on a series that applies in every pool the model is offered in.

  2. 02
    currentobject

    The rate in effect now: effective_from and amount_micros.

  3. 03
    previousobject or null

    The rate it replaced, or null for a first rate.

  4. 04
    change_bpsinteger or null

    The change from previous to current in basis points of previous, rounded toward zero: 40000 is a rise of 400%, -2500 a fall of 25%. Null without a previous rate, or from a rate of zero.

  5. 05
    pointsarray

    Each rate and the moment it took effect, oldest first. A rate that repeats the one before it is left out.

  • The series cover the on-demand rates of the kinds each model is billed in (language_input, language_input_cached, language_output, classification, and media_unit per setting) that took effect and were never canceled. A series begins when its model was listed: the rate in effect then is shown from that moment.
  • current, previous and change_bps are the series' own, whatever since or the cut to 30 points leaves in points.
  • Batch rows, announced rows, plans, storage and discounts have no history here; an announced change is in the catalog's prices with scheduled true.

Read from hips.com on 2026-11-13 and abridged, the model id left as a placeholder.

Abridged answer

00000000000000000000000000000000000000001{2  "data": {3    "revision": 131,4    "prices_updated_at": "2026-11-11T00:00:00Z",5    "series": [6      {7        "model": "<model id>",8        "pool": "certified",9        "kind": "language_input",10        "setting": null,11        "unit": "per_million_tokens",12        "current": { "effective_from": "2026-11-10T00:34:59.694295Z", "amount_micros": 196000 },13        "previous": { "effective_from": "2026-11-08T21:42:17.004751Z", "amount_micros": 39200 },14        "change_bps": 40000,15        "points": [16          { "effective_from": "2026-11-08T21:42:17.004751Z", "amount_micros": 39200 },17          { "effective_from": "2026-11-10T00:34:59.694295Z", "amount_micros": 196000 }18        ]19      }20    ]21  }22}
Abridged answer sample

The price feeds per pool

HIPS's machine-readable price feed: one document per model and pool, each with the model id that runs it in that pool, the pool's rates in force and what the pool serves for the model. Three feeds on https://ai.hips.com, the API's host, with no key:

GET/v1/feeds/certified/modelsserved

The Certified pool's offers, each under <model id>:certified, on https://ai.hips.com, with no key.

GET/v1/feeds/community/modelsserved

The Community pool's offers, each under <model id>:community, on https://ai.hips.com, with no key.

GET/v1/feeds/modelsserved

Both pools in one feed: a model's Certified offer at the default tier and its Community offer as service_tier: "flex" under the same id, on https://ai.hips.com, with no key.

cURL

00000000000000000000000000000000000000001curl -s --compressed https://ai.hips.com/v1/feeds/community/models
cURL sample
  • Each answers {"data": [...]}, one document per offer, read from the catalog the API prices and bills every request by: a feed never lists a rate a request is not charged at that moment.
  • Cache-Control: public, max-age=60 and an ETag; a matching If-None-Match answers 304 with no body. Sent with Accept-Encoding: gzip, the answer is gzipped, with its own ETag and Vary: accept-encoding. A feed is made again when the catalog changes or an announced price takes effect.

What a feed lists

  • A language model that is published and offered with its rates (status live), in each pool that serves it and has its own input and output rates in force there.
  • Never a model in preview, without a price in the pool, deprecated or retired, and never an announced price or a batch rate: the rates in force when the feed is made.

Each document

FieldWhat HIPS writes
schema_version2.4, the document format's version
idThe model id that runs the model in the feed's pool, <model id>:certified or <model id>:community (A pool in the model id)
nameThe model's display name and its pool, as (Certified pool) or (Community pool)
service_tierflex on the combined feed's Community offers; left out everywhere else (The combined feed)
hugging_face_idThe Hugging Face repository the model was added from, where the catalog shows it publicly
quantizationThe precision the pool serves the current version at, only where every kind of supply the pool serves it on states the same one: a GGUF's Q4_K_M is int4, Q8_0 int8, MXFP4 mxfp4, F16 fp16, BF16 bf16; left out wherever it is not recorded or differs
input_modalitiesText, with max_context_length (the model's context in tokens) and its price; and images: inline (base64) images of image/png, image/jpeg and image/gif, with image/webp where the Certified pool's own servers take them, where the pool takes images, else an empty sources
output_modalitiesText, with max_length (the model's output limit), streaming: true, supported_parameters and its price
  • Field
    schema_version
    What HIPS writes
    2.4, the document format's version
  • Field
    id
    What HIPS writes
    The model id that runs the model in the feed's pool, <model id>:certified or <model id>:community (A pool in the model id)
  • Field
    name
    What HIPS writes
    The model's display name and its pool, as (Certified pool) or (Community pool)
  • Field
    service_tier
    What HIPS writes
    flex on the combined feed's Community offers; left out everywhere else (The combined feed)
  • Field
    hugging_face_id
    What HIPS writes
    The Hugging Face repository the model was added from, where the catalog shows it publicly
  • Field
    quantization
    What HIPS writes
    The precision the pool serves the current version at, only where every kind of supply the pool serves it on states the same one: a GGUF's Q4_K_M is int4, Q8_0 int8, MXFP4 mxfp4, F16 fp16, BF16 bf16; left out wherever it is not recorded or differs
  • Field
    input_modalities
    What HIPS writes
    Text, with max_context_length (the model's context in tokens) and its price; and images: inline (base64) images of image/png, image/jpeg and image/gif, with image/webp where the Certified pool's own servers take them, where the pool takes images, else an empty sources
  • Field
    output_modalities
    What HIPS writes
    Text, with max_length (the model's output limit), streaming: true, supported_parameters and its price

prompt and completion are the pool's input and output rates in force. cached_prompt is listed only where the pool bills cached input, which no pool does yet (Prompt caching). Each cost_usd is the rate in US dollars per token as an exact decimal string: the catalog's amount_micros per million tokens divided by 1,000,000,000,000, nothing rounded (A worked conversion). A price HIPS does not bill is left out, never written as zero.

supported_parameters names the sampling parameters of chat completions, always, each with its usual range: max_tokens (up to the model's output limit), temperature, top_p, stop (16 at most), seed, presence_penalty and frequency_penalty. A feature's parameters are listed only where the pool serves it for the model: tools and tool_choice where its tool calls are validated or its template takes them, parallel_tool_calls, response_format for json_object, structured_outputs for json_schema, logprobs and top_logprobs, logit_bias, and reasoning.

Note

The format is strict: a document holds only the fields its schema names, and HIPS's tests hold every document to them, so a reader that refuses an unknown field never refuses one of these.

The combined feed

For a reader that takes a single feed, GET /v1/feeds/models holds both pools: each model's Certified offer at the default tier under <model id>:certified, and its Community offer under that same id with service_tier: "flex". A model offered in the Community pool alone is listed at the default tier under <model id>:community.

  • A chat completion that names a :certified id with service_tier: "flex" runs in the Community pool, exactly as the :community id does, at the Community pool's rates and under its terms: any caller that sends it gets the Community pool. service_tier is not passed to the model.
  • The answer says the tier it was served at: "service_tier": "flex" at the top level of the whole answer and of every streamed chunk.
  • Any other service_tier, or flex on any other model id, a batch file's lines included, is a 400 unsupported_parameter, as before.
  • A reader that shows a flex offer only while the default offer of its id is shown shows the combined feed's Community offer of a model only while its Certified offer is.

Abridged, its values left as placeholders:

One document

00000000000000000000000000000000000000001{2  "data": [3    {4      "schema_version": "2.4",5      "id": "<model id>:community",6      "name": "<display name> (Community pool)",7      "hugging_face_id": "<owner>/<name>",8      "quantization": "int4",9      "input_modalities": [10        {11          "type": "text",12          "supported_inputs": { "max_context_length": { "value": "<the model's context>", "unit": "token" } },13          "pricing": [{ "type": "prompt", "unit": "token", "cost_usd": "<rate in force, per token>" }]14        },15        { "type": "image", "supported_inputs": { "sources": { "type": "enum", "values": [] } } }16      ],17      "output_modalities": [18        {19          "type": "text",20          "max_length": { "value": "<the model's output limit>", "unit": "token" },21          "streaming": true,22          "supported_parameters": {23            "max_tokens": { "type": "integer", "min": 1, "max": "<the model's output limit>", "unit": "token" },24            "temperature": { "type": "range", "min": 0, "max": 2 },25            "top_p": { "type": "range", "min": 0, "max": 1 },26            "stop": { "type": "array", "max_items": 16 },27            "seed": { "type": "integer" },28            "presence_penalty": { "type": "range", "min": -2, "max": 2 },29            "frequency_penalty": { "type": "range", "min": -2, "max": 2 },30            "tools": { "type": "boolean" },31            "tool_choice": { "type": "boolean" }32          },33          "pricing": [{ "type": "completion", "unit": "token", "cost_usd": "<rate in force, per token>" }]34        }35      ]36    }37  ]38}
One document sample

Errors

An error answers {"error": {"code", "message", "param", "request_id"}} with Cache-Control: no-store, request_id present where the platform behind the site answered it.

StatusCodeWhenRetry
400invalid_requestThe price history's query is out of shape; param names the parameterNo: correct the query
404not_foundNo published model has this id: one model's route, or the history's modelNo
502unreadableThe catalog's answer could not be readYes, later
503not_connectedThe site is not connected to the catalogYes, later
AnotherThe platform's own codeA failure behind the site, passed through with its statusYes, later, for a 5xx
  • Status
    400
    Code
    invalid_request
    When
    The price history's query is out of shape; param names the parameter
    Retry
    No: correct the query
  • Status
    404
    Code
    not_found
    When
    No published model has this id: one model's route, or the history's model
    Retry
    No
  • Status
    502
    Code
    unreadable
    When
    The catalog's answer could not be read
    Retry
    Yes, later
  • Status
    503
    Code
    not_connected
    When
    The site is not connected to the catalog
    Retry
    Yes, later
  • Status
    Another
    Code
    The platform's own code
    When
    A failure behind the site, passed through with its status
    Retry
    Yes, later, for a 5xx

Related sheets

  • Billing
  • Models
  • Pricing
Previous sheetModels
Next sheetTasks
Sheet
18 of 20
Detail
G
Updated
2026-11-15
Sign in to the Console

On this sheet

  1. The routes
  2. Money and units
  3. A worked conversion
  4. Pools
  5. A pool in the model id
  6. How often it changes
  7. The catalog
  8. Price rows
  9. Which row is the price now
  10. The model fields that decide a price
  11. Plans
  12. Settings
  13. An answer, abridged
  14. One model
  15. The price history
  16. The price feeds per pool
  17. What a feed lists
  18. Each document
  19. The combined feed
  20. Errors

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