Higgsfield
Soul image models and DoP video generation, alongside character-reference services and hosted creative workflows.
Twelve reviewed records: four attributed models and eight managed components. Marketing Studio Flare/Sunburst routes belong to existing OpenAI model records. Remaining model identities and deployment gaps are tracked separately.
Start with the job your model needs to do. Then narrow by capabilities, provider and price.
Compare every model with the same request.
Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.
12 models
| Compare | Model | Input tokensPublished limit* | Output tokensMaximum per response* | Input pricePer 1M tokens | Output pricePer 1M tokens | Cost per question1,000 input + 500 outputEstimated · uncached |
|---|---|---|---|---|---|---|
| Not collected | 720p, 1080poutput resolution | Usage pricing $0.0938 / image720p generated image · Higgsfield API$0.1875 / image1080p generated image · Higgsfield APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | 720p, 1080poutput resolution | Usage pricing $0.0032 / image720p generated image · Higgsfield API$0.0057 / image1080p generated image · Higgsfield APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | Not collected | Usage pricing $2.50 / requestSoul ID training request · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| Not collected | 720p, 1080poutput resolution | Usage pricing Provider introduction advertises from USD 0.0032/image; exact resolution/configuration tariff has not been established.Rates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | 3 or 5 seconds in the web interface.output duration | Usage pricing API introduction advertises DoP from USD 0.125/generation, without a matching mode, duration or resolution tariff in the reviewed sources.Rates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 10,000characters | Follows the prepared source; at most 30 seconds.output duration | Usage pricing $0.318 / source-video second480p standard editing · Higgsfield API$0.681 / source-video second720p standard editing · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| 10,000characters | Follows the prepared source; at most 30 seconds.output duration | Usage pricing $0.318 / source-video second480p standard editing · Higgsfield API$0.681 / source-video second720p standard editing · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| 10,000characters | Follows the prepared source; at most 30 seconds.output duration | Usage pricing $0.318 / source-video second480p approximate editing · Higgsfield API$0.681 / source-video second720p approximate editing · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| Not collected | Integer 4–30 seconds; default 5.output duration | Usage pricing $0.0214 / 1,000 video tokensWithout video references · Higgsfield API$0.01284 / 1,000 video tokensWith video references · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| 5,000characters | 1k, 2k, 4koutput resolution | Usage pricing $0.0138 / image1k low · 15% off · Higgsfield API$0.0162 / image1k low · standard · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| 4,000characters | Not collected | Usage pricing $0.05 / imageMedium-quality character sheet · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
| 8,000characters | 2koutput resolution | Usage pricing $5.00 / 1M text input tokensText input · Higgsfield API$10.00 / 1M text output tokensText output · Higgsfield APIRates & conditions ↗ | Task-based pricingPrice details ↗ | |||
* Media models show their native limits. A shared context window includes both input and output tokens.
Catalog coverage
Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.
See what is being reviewed