Skip to content
ModelCap

Inference provider

Fireworks: AI models and API pricing

Every tracked model Fireworks serves through OpenRouter, with Fireworks's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.

Snapshot as of 19 November 2026

Fireworks serves 11 tracked models through 20 endpoints as of 19 November 2026; the highest-ranked is Kimi K3.1 Pro (ModelCap Index #11); mean measured uptime is 99.50%.

Models served
11
On the ModelCap Index
8
Cheapest output price
$0.20/1M

Language models on Fireworks (11)

Ranked models first, in ModelCap Index order. Prices are the lowest Fireworks lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Fireworks, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3.1 ProMoonshot AI#1180.0$2.00$10.001M—100.0%1
2Kimi K3Moonshot AI#1779.0$3.00$15.001M—100.0%3
3GLM 5.3Z.ai#1978.5$0.98$3.081M—100.0%3
4Muse Spark OpenMeta#2178.4$1.25$4.251M—100.0%1
5GLM 5.3 FlashZ.ai#2676.4$0.15$0.501M—100.0%2Open weights
6MiniMax M3.1 FlashMiniMax#3374.1$0.15$0.601M—100.0%1
7DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.21$0.841M—100.0%3Open weights
8Nemotron 3.5 LightningNVIDIA#21934.9$0.05$0.20262K—100.0%1
9Ember-1Fireworks—$3.00$15.001M—100.0%1
10DeepSeek V4 Flash 0423DeepSeek—$0.105$0.211M—90.91%1Open weights
11DeepSeek V4.1 FlashDeepSeek—$0.21$0.841M—100.0%3Open weights

Fireworks on ModelCap: common questions

How many AI models does Fireworks serve?

11 tracked models as of 19 November 2026: 11 language models (8 with a public ModelCap Index position), across 20 live endpoints observed through OpenRouter.

What is the best model available on Fireworks?

Kimi K3.1 Pro from Moonshot AI is the highest-ranked language model Fireworks serves, at ModelCap Index position #11 and $10.00 per 1M output tokens on Fireworks. The table lists every model in Index order.

What is the cheapest model on Fireworks?

Nemotron 3.5 Lightning at $0.20 per 1M output tokens ($0.05 per 1M input), the lowest positive language-token price Fireworks lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Fireworks model has the largest context window?

Kimi K3.1 Pro, served with a 1M-token context window on Fireworks. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Fireworks?

Mean measured uptime across Fireworks endpoints is 99.50% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Fireworks prices come from?

From the OpenRouter catalogue entry for each Fireworks endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Fireworks exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further