Model Catalogue

Model abilities

The complete declared capability set for every WebWright model: input and output modalities, limits, supported parameters, and Standard and Premium pricing. The same catalogue data powers the machine-readable feeds at /v1/models and /v1/provider/models.

WebWright: Wren R1

wren-r1
Declared, pending live verification

Wren R1 is WebWright's chat model on the Standard plan, served from us-east-1 with a 200K-token context window, streaming responses, tool calling, structured outputs and a reasoning mode.

Input modalities

Text

  • Context window: 200,000 tokens

Image

  • Sources: url, base64
  • Formats: image/png, image/jpeg, image/webp, image/gif
  • Maximum content size: 20 MiB (20,971,520 bytes)

File

  • Sources: url, base64
  • Formats: application/pdf, text/plain, text/csv
  • Maximum content size: 50 MiB (52,428,800 bytes)

Audio

  • Sources: url, base64
  • Formats: audio/wav, audio/mpeg
  • Maximum duration: 3600 seconds (1 hour)

Output modalities

Text

  • Maximum output: 200,000 tokens
  • Streaming: supported
Supported parameters
max_tokens
1 to 200,000 token
reasoning
Supported
stop
Up to 4 items
structured_outputs
Supported
temperature
0 to 2
tools
Supported
top_p
0 to 1

Pricing

Standard

Input (per 1M tokens)
$0.40
Cached input (per 1M tokens)
$0.10
Output (per 1M tokens)
$1.60
Audio input (per second)
$0.00002

Premium

Input (per 1M tokens)
$0.80
Cached input (per 1M tokens)
$0.20
Output (per 1M tokens)
$3.20
Audio input (per second)
Included

WebWright: Wren R1 (Priority)

wren-r1-fast
Declared, pending live verification

Wren R1 Priority is WebWright's Premium plan chat model, served from us-east-1 with a 200K-token context window and priority capacity.

Input modalities

Text

  • Context window: 200,000 tokens

Image

  • Sources: url, base64
  • Formats: image/png, image/jpeg, image/webp, image/gif
  • Maximum content size: 20 MiB (20,971,520 bytes)

File

  • Sources: url, base64
  • Formats: application/pdf, text/plain, text/csv
  • Maximum content size: 50 MiB (52,428,800 bytes)

Audio

  • Sources: url, base64
  • Formats: audio/wav, audio/mpeg
  • Maximum duration: 3600 seconds (1 hour)

Output modalities

Text

  • Maximum output: 200,000 tokens
  • Streaming: supported
Supported parameters
max_tokens
1 to 200,000 token
reasoning
Supported
stop
Up to 4 items
structured_outputs
Supported
temperature
0 to 2
tools
Supported
top_p
0 to 1

Pricing

Standard

Input (per 1M tokens)
$0.40
Cached input (per 1M tokens)
$0.10
Output (per 1M tokens)
$1.60
Audio input (per second)
$0.00002

Premium

Input (per 1M tokens)
$0.80
Cached input (per 1M tokens)
$0.20
Output (per 1M tokens)
$3.20
Audio input (per second)
Included

WebWright: Whisper Large v3 Turbo

whisper-large-v3-turbo
Declared, pending live verification

WebWright's speech-to-text model, served from us-east-1. Send an audio file and receive a transcript in json, text, srt, verbose_json or vtt.

Input modalities

Audio

  • Sources: url, base64
  • Formats: audio/wav, audio/mpeg
  • Maximum duration: 3600 seconds (1 hour)

Output modalities

Transcription

  • Streaming: not supported
Supported parameters
language
Accepted
prompt
Accepted
response_format
json, text, srt, verbose_json, vtt
temperature
0 to 1
timestamp_granularities
word, segment (up to 2)

Pricing

Standard

Audio input (per second)
$0.00002

Premium

Audio input (per second)
Included

Machine-readable feeds

Both feeds are public, static, and safe to cache. They read no database, no API key, and no user data.

See the API reference for authentication, chat completions, and transcription details.