Price Per TokenPrice Per Token
Fireworks

Fireworks API Pricing (Updated 2026)

Compare pricing for all 10 Fireworks models. Prices shown per 1M tokens with historical trends.

Get our weekly newsletter on pricing changes, new releases, and tools.

No bots, no big tech influence — join the new community for AI devs
8 Ways to Use Fewer Tokens
Last updated: April 10, 2026 at 08:39 AM

Overview

10
Total Models
$0.18
Cheapest Input (per 1M)
131K
Max Context Length

Model Release Timeline

0 releases
No release date information available
Spacing represents time between releases

All Fireworks Models

Compare pricing for all 10 Fireworks models.

Model
Context
Input
Output
Coding
MMLU
GPQA
Cache Read
Cache Write
Actions
33K
$0.000
$0.000
-
-
Try
8K
$0.000
$0.000
29.5
69.6
41.6
-
-
Try
131K
$0.000
$0.000
-
-
Try
131K
$0.000
$0.000
-
-
Try
-
$0.000
$0.000
-
-
Try
-
$0.000
$0.000
-
-
Try
131K
$0.180
$0.180
-
-
Try
131K
$0.900
$0.900
$0.45
-
Try
131K
$0.900
$0.900
$0.45
-
Try
131K
$0.900
$0.900
$0.45
-
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts under 200k tokens.

Showing lowest price across all providers. Benchmarks from Artificial Analysis and HuggingFace Open LLM Leaderboard.

Cost vs. Quality

Compare Fireworks models by benchmark performance and cost.

X-axis:
Y-axis:
Loading chart...
Sarvam M
Fireworks Models

Community Ratings

Rate how well Fireworks models perform across popular AI coding tools.

Historical Pricing Trends

Price Changes Over Time

No historical pricing data available for this provider.

Try Fireworks Models

Cost Calculator

Estimate your costs for any Fireworks model based on expected token usage.

Open Cost Calculator

Try in Playground

Test Fireworks models directly in your browser.

Open Playground

Frequently Asked Questions

Currently, Marin 8B Instruct is the most affordable at $0.18 per 1M input tokens.
Count your input tokens (prompt) and expected output tokens (response). Use the formula: (input_tokens/1M × input_price) + (output_tokens/1M × output_price). Our pricing calculator can help automate this.
Fireworks pricing varies by model. Input costs range from $0.18 to $0.90 per 1M tokens. See the table above for specific model pricing.