Get Model | Mesh API Docs

{
  "id": "model_123abc456def",
  "name": "GPT-4 Turbo",
  "context_length": 8192,
  "is_free": false,
  "pricing": {
    "prompt_usd_per_1k": "0.03",
    "completion_usd_per_1k": "0.06",
    "pricing_unit": "tokens",
    "prompt_usd_per_1m": "30.00",
    "completion_usd_per_1m": "60.00",
    "image_output_usd_per_image": null,
    "request_usd": null,
    "long_context_input_usd_per_1m": "45.00",
    "long_context_output_usd_per_1m": "90.00",
    "cache_read_input_usd_per_1m": "5.00",
    "cache_write_input_usd_per_1m": "7.50",
    "cache_read_audio_input_usd_per_1m": null,
    "long_context_cache_read_input_usd_per_1m": "10.00",
    "long_context_cache_write_input_usd_per_1m": "12.00",
    "batch_input_usd_per_1m": "20.00",
    "batch_output_usd_per_1m": "25.00",
    "training_usd_per_1m": null,
    "fine_tuned_input_usd_per_1m": "35.00",
    "fine_tuned_output_usd_per_1m": "40.00",
    "audio_input_usd_per_1m": null,
    "audio_output_usd_per_1m": null,
    "transcription_usd_per_1m": null,
    "cached_audio_input_usd_per_1m": null,
    "cached_text_input_usd_per_1m": "3.00",
    "cache_hit_usd_per_1m": "2.50",
    "image_input_usd_per_image": null,
    "image_output_size": null,
    "effective_date": "2024-01-01",
    "deprecated_date": null,
    "notes": "Pricing subject to change based on usage tiers.",
    "source_url": "https://openai.com/pricing",
    "discount_pct": "10"
  },
  "supports_thinking": true,
  "supports_completions_api": true,
  "supports_responses_api": true,
  "model_type": "transformer",
  "input_modalities": [
    "text"
  ],
  "output_modalities": [
    "text"
  ],
  "provider": "OpenAI",
  "description": "GPT-4 Turbo is a faster, cheaper variant of GPT-4 optimized for chat and completions.",
  "supports_realtime": false,
  "supports_embeddings": true,
  "supports_tools": false,
  "supports_structured_output": true,
  "supports_system_prompt": true,
  "supports_batching": true,
  "context_window": 8192,
  "standard_context_threshold": 4096,
  "realtime_session_max_tokens": 2048,
  "realtime_max_concurrent_per_owner": 5,
  "is_composite": false,
  "composite_models": null
}

Return a single enabled model by its model ID with per-user discounted pricing.

Served from the same Redis cache as GET /v1/models — no additional DB queries when the cache is warm. Discounts are applied per-user and not cached.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

model_idstringRequired

Response

Successful Response

idstring

namestring

context_lengthinteger or null

is_freeboolean

pricingobject

supports_thinkingboolean

supports_completions_apiboolean

supports_responses_apiboolean

model_typestring

input_modalitieslist of strings

output_modalitieslist of strings

providerstring or null

descriptionstring or null

supports_realtimebooleanDefaults to false

supports_embeddingsbooleanDefaults to false

supports_toolsbooleanDefaults to false

supports_structured_outputbooleanDefaults to false

supports_system_promptbooleanDefaults to true

supports_batchingbooleanDefaults to false

context_windowinteger or null

standard_context_thresholdinteger or null

realtime_session_max_tokensinteger or null

realtime_max_concurrent_per_ownerinteger or null

is_compositebooleanDefaults to false

composite_modelslist of strings or null

Errors

422

Unprocessable Entity Error

$	curl https://api.meshapi.ai/v1/models/model_id \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json"