Skip to content

Fireworks AI

Pricing page

431 listings across 305 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of serviceStatus page

On training

No AI Training on Your Data: We do not use your prompts, training data, or API inputs to train or improve our AI models without your explicit opt-in.

Source: Fireworks AI privacy policy

On keeping your data

Zero Data Retention: We do not log or store prompt or generation data for any open models without explicit user opt-in*.

Source: Fireworks AI privacy policy

Other statements

Specifically, we have servers for the Service in the US.

Source: Fireworks AI privacy policy

We take these statements from Fireworks AI's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Page 1 of 13. The lists below split this page's listings into those sold by Fireworks AI, run by Fireworks AI, or sent to Fireworks AI by a marketplace.

Sold by Fireworks AI

35 listings on this page sold by Fireworks AI.

Default order. 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
Kimi K3.1 Proaccounts/fireworks/models/kimi-k3p1-pro
$2.00cache read $0.20$10.001M
DeepSeek V4.1 Flash 1017accounts/fireworks/models/deepseek-v4p1-flash-1017
$0.30cache read $0.006$1.201M
Kimi K3
$3.00cache read $0.30$15.001M
Qwen3.8 Maxaccounts/fireworks/models/qwen3p8-2p4t-a95b
$2.00cache read $0.25$6.00262K
GLM 5.3accounts/fireworks/models/glm-5p3
$1.40cache read $0.26$4.401M
DeepSeek V4.1 Flashaccounts/fireworks/models/deepseek-v4p1-flash
$0.30cache read $0.006$1.201M
$1.32cache read $0.044$3.961M
$0.22cache read $0.007$0.661MNot measuredNot measured
$1.25cache read $0.15$4.251MNot measured
MiniMax M3.1 Flashaccounts/fireworks/models/minimax-m3p1-flash
$0.15cache read $0.015$0.601MNot measuredNot measured
DeepSeek Flashfireworks_ai/accounts/fireworks/routers/deepseek-flash-latest · latest
Not enough data yet$0.30cache read $0.006$1.201MNot enough data yetNot measuredNot measured
GLM 5.2accounts/fireworks/routers/glm-5p2-fast · fast
$2.10cache read $0.21$6.601M
GLM 5.3 Flashaccounts/fireworks/models/glm-5p3-flash
$0.15cache read $0.03$0.501M
Kimi K2.6kimi-k2p6
$0.95cache read $0.16$4.00262K
DeepSeek V4 Flash 0731
$0.22cache read $0.007$0.661M
Not enough data yet$0.10—41KNot enough data yetNot measuredNot measured
GLM 5.1glm-5p1
$1.40cache read $0.26$4.40203K
$1.74cache read $0.145$3.481M
Qwen3.7 Plusqwen3p7-plus
$0.40cache read $0.08$1.60262K
Qwen3.6 Plusqwen3p6-plus
$0.50cache read $0.10$3.00Not published by the provider
DeepSeek V4 Flash
$0.14cache read $0.028$0.281M
Kimi K2.5kimi-k2p5
$0.60cache read $0.10$3.00262K
Not enough data yet$0.35cache read $0.04$1.50131KNot measuredNot measured
Show all 35 listings

Showing 23 of 35: one listing for each model.

Run by Fireworks AI

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

Default order. 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
 Hugging Face$2.00$10.001M
 Hugging Face$0.30$1.201M
Kimi K3
 Hugging Face$3.00$15.001M
Qwen3.8 MaxQwen/Qwen3.8-2.4T-A95B
 Hugging Face$2.00$6.001M
GLM 5.3
 Hugging Face$0.70$2.201M
 Hugging Face$0.15$0.601M
 Eden AI$1.25cache read $0.15$4.251MNot measured
 Hugging Face$0.15$0.601MNot measuredNot measured
 Hugging Face$1.25$4.251MNot measured
 Hugging Face$0.15$0.501M
DeepSeek V4.1 Flash 0910deepseek/deepseek-v4.1-flash
 OpenRouterNot enough data yet$0.30cache read $0.006$1.201MNot enough data yetNot measuredNot measured
DeepSeek V4 Proaccounts/fireworks/models/deepseek-v4-pro-0813
 Llmgateway$1.32cache read $0.044$3.96Not published by the provider
DeepSeek V4 Flash
 Hugging Face$0.07$0.141M
Show all 56 listings

Showing 13 of 56: one listing for each model.

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

Around the web

  • Fireworks AI
    Fireworks is the fastest way to build, tune, and scale AI on open models. Ship …Fireworks is the fastest way to build, tune, and scale AI on open models. Ship production-ready AI in seconds on our globally distributed cloud infrastructure, ...Read more

    linkedin.com

  • Fireworks AI - Crunchbase Company Profile & Funding
    Fireworks AI is an advanced platform that enables users to build, tune, and scale AI …Fireworks AI is an advanced platform that enables users to build, tune, and scale AI applications using open-source models.

    crunchbase.com

  • Introducing Fireworks AI on Microsoft Foundry
    Fireworks AI is a market leader for high performance inference for open models. Its engine …Fireworks AI is a market leader for high performance inference for open models. Its engine already runs at internet scale processing over 13T ...

    azure.microsoft.com

  • Fireworks.ai: Lighting up gen AI through a more efficient ...
    Fireworks AI delivers one of the fastest and most efficient gen AI inference engine, replacing …Fireworks AI delivers one of the fastest and most efficient gen AI inference engine, replacing traditional single AI models

    cloud.google.com

  • An honest Fireworks AI review (2025): The good, the bad, ...
    Fireworks AI can deliver up to 4x higher throughput than standard open-source options while slashing …Fireworks AI can deliver up to 4x higher throughput than standard open-source options while slashing latency in half. Its main purpose is to ...

    eesel.ai

  • Fireworks AI 2026 Company Profile
    Developer of a generative artificial intelligence platform designed to build and run AI agents and …Developer of a generative artificial intelligence platform designed to build and run AI agents and applications. Fireworks AI has raised $1.83B.

    pitchbook.com

How this data works