Skip to content

Navigation

Filters

Filters

Input Modalities
Output Modalities
Prompt pricing
LowestAny
Series
Providers

Fireworks

Models from Fireworks

Compare in Chat

10 models

SortNewest
Fireworks

accounts/fireworks/models/deepseek-v4p1-flash

Available

fireworks/deepseek-v4p1-flash

$0.300/M input

$1.20/M output

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/models/deepseek-v4p1-flash-1017

Pricing unavailable

fireworks/deepseek-v4p1-flash-1017

Pricing unavailable

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/models/qwen3-embedding-8b

Pricing unavailable

fireworks/qwen3-embedding-8b

Pricing unavailable

by FireworksRelease date unknownEmbeddings
Fireworks

accounts/fireworks/models/qwen3-reranker-8b

Pricing unavailable

fireworks/qwen3-reranker-8b

Pricing unavailable

by FireworksRelease date unknownEmbeddings
Fireworks

accounts/fireworks/models/qwen3p8-2p4t-a95b

Available

fireworks/qwen3p8-2p4t-a95b

$2.00/M input

$6.00/M output

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/models/qwen3p8-max

Available

fireworks/qwen3p8-max

$2.00/M input

$6.00/M output

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot

Pricing unavailable

fireworks/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot

Pricing unavailable

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/routers/deepseek-v4p1-flash-spot

Pricing unavailable

fireworks/accounts/fireworks/routers/deepseek-v4p1-flash-spot

Pricing unavailable

by FireworksRelease date unknownText
Fireworks

accounts/fireworks/routers/spot-deepseek-v4-flash

Pricing unavailable

fireworks/accounts/fireworks/routers/spot-deepseek-v4-flash

Pricing unavailable

by FireworksRelease date unknownText
Fireworks

Fireworks: Ember-1

Available

fireworks/ember-1

$3.00/M input

$15.00/M output

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

by FireworksRelease date unknownVision