Skip to content

Listings

All listings: Fireworks AI

Every listing for the models on page 8 of 13 of Fireworks AI, including each model's other versions and routes. Back to Fireworks AI

Sold by Fireworks AI

27 listings on this page sold by Fireworks AI.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
nomic-embed-text-v1
Newer version
Newer versionnomic-embed-text-v1.5We compared release dates and version names in our catalogue.
85.1
From 120 benchmarks. Plenty of data behind it.
Not enough data yet$0.008—8KNot enough data yetNot measured
Gemma 7B IT
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
84.5
From 75 benchmarks. Plenty of data behind it.
≈ 76 ±12
Coding IQ 75.7, 95% interval 64–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.208KNot enough data yetNot measured
Gte Base
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
83.7
From 109 benchmarks. Plenty of data behind it.
Not enough data yet$0.008—512Not enough data yetNot measured
Llama 3.2 1B Instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct
83.4
From 93 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.10131K
43.7
Poor value (43.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
82.7
From 130 benchmarks. Plenty of data behind it.
Not enough data yet$0.008—8KNot enough data yetNot measured
Llama 2 7b
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/llama-v2-7b
82.0
From 82 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.204KNot enough data yet
83.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.2 1B
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/llama-v3p2-1b
82.0
From 22 benchmarks. A fair amount of data behind it.
Not enough data yet$0.10$0.10131KNot enough data yetNot measured
code-llama-7b-instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
81.9
From 58 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20$0.2016KNot enough data yetNot measured
Gemma 2B IT
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
80.5
From 71 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.108KNot enough data yetNot measured
FLUX.1 [dev]
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
≈ 80
From 142 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.10$0.104KNot enough data yetNot measured
FLUX.1 [dev]
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8 · fp8
≈ 80
From 142 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet——4KNot enough data yetNot measured
Flux Kontext Max
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
78.3
From 173 benchmarks. A fair amount of data behind it.
Not enough data yet——4KNot enough data yetNot measured
Qwen2.5 0.5b Instruct
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct
78.2
From 36 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.1033KNot enough data yetNot measured
DeepSeek R1 Distill Qwen 1.5B
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b
75.6
From 50 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.10131KNot enough data yetNot measured
flux-1-dev-controlnet-union
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.001$0.0014KNot enough data yetNot measured
fireworks-ai-embedding-up-to-150m
Pricing tier
This is a separate pricing tier or billing meter that a provider lists under its own name, not a different model.
Not enough data yetNot enough data yet$0.008—Not published by the providerNot enough data yetNot measured
fireworks-ai-embedding-150m-to-350m
Pricing tier
This is a separate pricing tier or billing meter that a provider lists under its own name, not a different model.
Not enough data yetNot enough data yet$0.016—Not published by the providerNot enough data yetNot measured
Doesn’t apply to this modelDoesn’t apply to this model$0.042cache read $0.0084Doesn’t apply to this model262KDoesn’t apply to this modelDoesn’t apply to this model
Spot DeepSeek V4 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.07cache read $0.014$0.141MNot enough data yetNot measured
cogito-v1-preview-llama-3b
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.10$0.10131KNot enough data yetNot measured
deepseek-coder-1b-base
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.10$0.1016KNot enough data yetNot measured
ERNIE-4.5-21B-A3B-PT
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt
Not enough data yetNot enough data yet$0.10$0.10131KNot enough data yetNot measured
ERNIE-4.5-300B-A47B-PT
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt
Not enough data yetNot enough data yet$0.10$0.10131KNot enough data yetNot measured
fireworks-ai-up-to-4b
Pricing tier
This is a separate pricing tier or billing meter that a provider lists under its own name, not a different model.
Not enough data yetNot enough data yet$0.10$0.10Not published by the providerNot enough data yetNot measured
FLUX 1 Schnell
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.10$0.104KNot enough data yetNot measured
FLUX 1 Schnell
🇩🇪
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8 · fp8
Not enough data yetNot enough data yet——4KNot enough data yetNot measured
Llama 2 70b
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.1 70BWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/llama-v2-70b
Not enough data yetNot enough data yet$0.10$0.104KNot enough data yet
105.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works