Skip to content

Listings

All listings: Fireworks AI

Every listing for the models on page 4 of 13 of Fireworks AI, including each model's other versions and routes. Back to Fireworks AI

Sold by Fireworks AI

25 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
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
GPT OSS 20b
πŸ‡ΊπŸ‡Έ
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.
111.3
From 251 benchmarks. Plenty of data behind it.
88Β Β±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.07cache read $0.04$0.30131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 2.5 VL 32B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, 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.
Newer version
Newer versionQwen3 VL 32B InstructWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct
111.3
From 25 benchmarks. A fair amount of data behind it.
Not enough data yet$0.90$0.90128K
47.9
Fair value (47.9). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3 8b Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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/ministral-3-8b-instruct-2512 Β· 2512
110.9
From 14 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20$0.20256KNot enough data yetNot measuredNot measured
Ministral 3 14B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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/ministral-3-14b-instruct-2512 Β· 2512
110.8
From 15 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20$0.20256KNot enough data yetNot measuredNot measured
Nemotron Nano 9b V2
πŸ‡ΊπŸ‡Έ
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/nvidia-nemotron-nano-9b-v2
110.6
From 19 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.20128K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3 Embedding 0.6B
πŸ‡¨πŸ‡³
Maker headquartered in CN, 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/qwen3-embedding-0p6b
110.5
From 192 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”33KNot enough data yetNot measuredNot measured
109.8
From 29 benchmarks. Plenty of data behind it.
Not enough data yet$0.90$0.9016K
53.1
Good value (53.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Llama 3.1 Nemotron 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct
109.8
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$0.90$0.90131K
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen2.5 14B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3 14BWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/qwen2p5-14b
109.5
From 58 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.20131KNot enough data yetNot measuredNot measured
Qwen2.5 Math 72B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct
109.5
From 21 benchmarks. A fair amount of data behind it.
Not enough data yet$0.90$0.904KNot enough data yetNot measuredNot measured
Qwen2.5 32B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct
109.0
From 108 benchmarks. Plenty of data behind it.
78Β Β±10stale
Coding IQ 77.8, 95% interval 67–88. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.90$0.9033KNot enough data yetNot measuredNot measured
Qwen2.5 72B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct
108.9
From 216 benchmarks. Plenty of data behind it.
80Β Β±22
Coding IQ 79.9, 95% interval 58–102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.90$0.9033K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen2.5 VL 72B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, 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.
qwen2p5-vl-72b-instruct
108.8
From 97 benchmarks. Plenty of data behind it.
Not enough data yet$0.90$0.90128K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3 4B Instruct 2507
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
108.8
From 91 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20$0.20262KNot enough data yetNot measuredNot measured
Gemma 3 27B IT
πŸ‡ΊπŸ‡Έ
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.
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.10131K
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
127.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
108.2
From 199 benchmarks. Plenty of data behind it.
β‰ˆ 77Β Β±11
Coding IQ 76.5, 95% interval 66–87. 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.
$0.90$0.908K
49.9
Fair value (49.9). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
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-v3p3-70b-instruct
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.90$0.90131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen2.5 32B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3 32BWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/qwen2p5-32b
108.0
From 28 benchmarks. A fair amount of data behind it.
Not enough data yet$0.90$0.90131KNot enough data yetNot measuredNot measured
qwen2.5-coder-14b-instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct
107.7
From 40 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.2033KNot enough data yetNot measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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.
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$1.20$1.2066KNot enough data yetNot measuredNot measured
Qwen2 72B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5 72B InstructWe compared release dates and version names in our catalogue.
107.3
From 265 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±11
Coding IQ 76.2, 95% interval 65–87. 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.
$0.90$0.9033K
34.3
Poor value (34.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
DeepSeek R1 Distill Qwen 32B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.1
From 40 benchmarks. Plenty of data behind it.
β‰ˆ 81Β Β±12stale
Coding IQ 80.5, 95% interval 68–93. 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. Its newest result is over a year old.
$0.90$0.90131KNot enough data yetNot measuredNot measured
DeepSeek R1 Distill Qwen 14B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.0
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.20131KNot enough data yetNot measuredNot measured
Llama 3.1 70B Instruct
πŸ‡ΊπŸ‡Έ
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.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct
106.8
From 168 benchmarks. Plenty of data behind it.
β‰ˆ 80Β Β±11
Coding IQ 80.3, 95% interval 69–91. 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.
$0.90$0.90131K
41.0
Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen 2.5 Coder 32B
πŸ‡¨πŸ‡³
Maker headquartered in CN, 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/qwen2p5-coder-32b
106.7
From 11 benchmarks. Plenty of data behind it.
Not enough data yet$0.90$0.9033KNot enough data yetNot measured
118.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

Run by Fireworks AI

2 listings on this page where Fireworks AI runs the model. Another provider sells these listings.

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
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
GPT OSS 20b
πŸ‡ΊπŸ‡Έ
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.
Β Hugging Face
111.3
From 251 benchmarks. Plenty of data behind it.
88Β Β±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.20131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
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.
Β Hugging Face
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.90$0.90131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

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

How this data works