Skip to main content
GET
https://app.firmware.ai
/
api
/
v1
/
models
Models
curl --request GET \
  --url https://app.firmware.ai/api/v1/models \
  --header 'Authorization: Bearer <token>'
{
  "object": "<string>",
  "data": [
    {
      "id": "<string>",
      "object": "<string>",
      "created": 123,
      "owned_by": "<string>",
      "provider": "<string>",
      "created_at": "<string>",
      "provider_info": {},
      "...": "<any>"
    }
  ]
}
List available model IDs across all inference endpoints.

​
Chat models

Use these model IDs with chat completions and messages.
Model IDProviderContext
claude-opus-4-6Anthropic1M
claude-opus-4-5Anthropic200k
claude-sonnet-4-6Anthropic1M
claude-sonnet-4-5Anthropic200k
claude-sonnet-4Anthropic200k
claude-haiku-4-5Anthropic200k
claude-haiku-3-5Anthropic200k
gpt-5.2OpenAI400k
gpt-5-3-codexOpenAI400k
gpt-5OpenAI400k
gpt-5-miniOpenAI400k
gpt-5-nanoOpenAI400k
gpt-4oOpenAI128k
gpt-4o-miniOpenAI128k
gpt-4.1OpenAI1M
grok-4-1-fast-reasoningxAI2M
grok-4-1-fast-non-reasoningxAI2M
grok-code-fast-1xAI256k
gemini-3-1-pro-previewGoogle1M
gemini-3-pro-previewGoogle1M
gemini-3-flash-previewGoogle1M
gemini-2.5-proGoogle1M
gemini-2.5-flashGoogle1M
gemini-2.5-flash-liteGoogle1M
deepseek-v3-2Fireworks128k
deepseek-r1Bedrock128k
gpt-oss-120bBedrock128k
gpt-oss-20bBedrock128k
minimax-m2.5Fireworks AI192k
kimi-k2.5Fireworks AI262k
kimi-k2-thinkingBedrock262k
zai-glm-5Fireworks AI198k
zai-glm-4.7Bedrock128k
zai-glm-4.7-flashBedrock128k
f1Firmware128k
f1-flashFirmware1M
f1-proFirmware1M

​
Embedding models

Use these model IDs with embeddings.
Model IDProviderPrice per 1M tokens
text-embedding-3-smallOpenAI$0.02
text-embedding-3-largeOpenAI$0.13
text-embedding-ada-002OpenAI$0.10
text-embedding-004GoogleFree
voyage-4-largeVoyage AI$0.12
voyage-4Voyage AI$0.06
voyage-4-liteVoyage AI$0.02
voyage-context-3Voyage AI$0.18
voyage-code-3Voyage AI$0.18
voyage-finance-2Voyage AI$0.12
voyage-law-2Voyage AI$0.12
voyage-code-2Voyage AI$0.12

​
Rerank models

Use these model IDs with rerank.
Model IDProviderPrice per 1M tokens
rerank-2.5Voyage AI$0.05
rerank-2.5-liteVoyage AI$0.02

​
Audio transcription models

Use these model IDs with audio transcriptions.
Model IDProviderPrice
whisper-1OpenAI$0.006/min
elevenlabs-scribe-v2ElevenLabs$0.40/hr

​
Audio speech models

Use these model IDs with audio speech.
Model IDProviderPrice per 1M chars
elevenlabs-tts-multilingualElevenLabs$170.00
elevenlabs-tts-v3ElevenLabs$170.00

​
Image generation models

Use these model IDs with image generation.
Model IDProviderPrice
dall-e-3OpenAI0.04–0.04–0.12 per image
imagen-4Google$0.04 per image
imagen-4-ultraGoogle$0.06 per image
imagen-4-fastGoogle$0.02 per image
gemini-3-pro-image-previewGoogleToken-based
gemini-3-1-flash-image-previewGoogleToken-based
gemini-2.5-flash-imageGoogleToken-based

​
Call endpoint

Send a GET request with your Firmware API key.

​
Authenticate

Use an API key in the Authorization header. 
curl https://app.firmware.ai/api/v1/models \
  -H "Authorization: Bearer $FIRMWARE_API_KEY"

​
Understand response

Returns an OpenAI-compatible list object. Each entry is a supported model object.
​
object
string
Always list.
​
data
array
Array of model objects.

​
See example

Example response shape. Fields may vary by provider. 
{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-4o-mini",
      "object": "model",
      "created": 1735689600,
      "owned_by": "openai",
      "provider_info": {
        "status": "enabled"
      }
    }
  ]
}

​
Handle errors

401 means the API key is missing or invalid. 429 means you hit a usage or plan limit.