Fireworks AI
Fast, production-grade inference for leading open-source and open-weights models. Requesty routes to 5 Fireworks AI models starting at $0.30 per 1M input tokens with context windows up to 262K tokens. One API key, OpenAI-compatible SDK, no markup.
All Fireworks AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
kimi-k2.6 | 262K | 33K | $0.95 | $4.00 | 👁🧠🔧⚡ | — |
minimax-m2.5 | 197K | 25K | $0.30 | $1.20 | 🔧⚡ | — |
glm-5 | 203K | 25K | $1.00 | $3.20 | 🔧⚡ | — |
deepseek-v3.2 | 164K | 20K | $0.56 | $1.68 | 🔧⚡ | — |
kimi-k2.5 | 262K | 262K | $0.60 | $3.00 | 👁🧠🔧⚡ | — |
About Fireworks AI on Requesty
How many Fireworks AI models are available through Requesty?
Requesty routes to 5 Fireworks AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Fireworks AI model?
The cheapest Fireworks AI model starts at $0.30 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Fireworks AI pricing?
No. Requesty passes through exactly what Fireworks AI charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Fireworks AI models?
Fireworks AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Fireworks AI models hosted?
Fireworks AI models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Fireworks AI rows in the models explorer.