Fireworks AI vs OpenRouter: LLM API pricing compared
Updated 2026-11-10 · listed A to Z, not ranked
Fireworks AI hosts open models behind a serverless API billed per token, with dedicated GPU deployments also available.
OpenRouter is a single OpenAI-compatible API for hundreds of language models from many providers. Its pricing has two parts: the model’s own token price, and OpenRouter’s fee, which is charged when you buy credits rather than on each request.
Listed A to Z, from fireworks.ai and openrouter.ai. Every figure below is quoted from those pages.
- Main price table
- NVIDIA Nemotron 3.5 Lightning 30B A3B, OpenAI GPT OSS 120B, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiniMax M3, Nemotron 3 Ultra, GLM 5.3, Qwen 3.8 Max, Kimi K3
- Free option
- None in the published plan table
- Published prices
- Fireworks AI serverless pricing per 1M tokens from $0.05 input; Batch 50% off, Spot 30% off Standard. Kimi, Qwen, GLM, DeepSeek rates.
- Main price table
- Standard (pay as you go), Business (pay as you go), Enterprise
- Free option
- Standard (pay as you go): 5.5% on credit purchases
- Published prices
- Model tokens at provider list price, a 5.5% (Standard) or 8% (Business) fee on credit purchases, BYOK and USDC.
How we checked: Prices quoted from each official pricing page: Fireworks AI checked Nov 10, 2026, OpenRouter checked Nov 10, 2026. Taxes, usage overages and promotions can change what you pay; confirm with each provider before you buy.
How they compare
- Main price table. Fireworks AI lists 9 entries (NVIDIA Nemotron 3.5 Lightning 30B A3B, OpenAI GPT OSS 120B, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiniMax M3, Nemotron 3 Ultra, GLM 5.3, Qwen 3.8 Max, Kimi K3); OpenRouter lists 3 (Standard (pay as you go), Business (pay as you go), Enterprise).
- Free option. Fireworks AI: none in the published plan table. OpenRouter: Standard (pay as you go): 5.5% on credit purchases.
- How prices are quoted. Fireworks AI: “Serverless, Standard tier (per 1M tokens)”. OpenRouter: “Plans and fees”.
Fireworks AI plans and prices
| Model | Input | Cached input | Output |
|---|---|---|---|
| NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 | $0.01 | $0.20 |
| OpenAI GPT OSS 120B | $0.15 | $0.015 | $0.60 |
| GLM 5.3 Flash | $0.15 | $0.03 | $0.50 |
| DeepSeek V4.1 Flash | $0.30 | $0.006 | $1.20 |
| MiniMax M3 | $0.30 | $0.06 | $1.20 |
| Nemotron 3 Ultra | $0.60 | $0.12 | $2.40 |
| GLM 5.3 | $1.40 | $0.26 | $4.40 |
| Qwen 3.8 Max | $2.00 | $0.25 | $6.00 |
| Kimi K3 | $3.00 | $0.30 | $15.00 |
Batch is 50% off and Spot is 30% off these Standard rates. Priority costs more; for example Kimi K3 Priority is $3.75 input, $0.375 cached and $18.75 output.
From fireworks.ai, checked Nov 10, 2026. Full breakdown: Fireworks AI pricing.
OpenRouter plans and prices
| Plan | Fee | How you pay | Notable limits |
|---|---|---|---|
| Standard (pay as you go) | 5.5% on credit purchases | Credit and debit cards, AliPay, crypto (USDC) | Rate limits pass through from the providers; 5 workspaces |
| Business (pay as you go) | 8% on credit purchases | Credit and debit cards, AliPay, crypto (USDC) | Adds EU and US in-region routing, advanced notifications, 1,000 workspaces |
| Enterprise | Set by contract; fee discounts available | Invoicing and purchase orders | SSO/SAML, contractual SLAs, dedicated support |
| Plan | Included BYOK usage | Above the allowance |
|---|---|---|
| Standard and Business | $25,000 of list-price inference per month with no OpenRouter fee | 5% of what the same request would cost at list price on OpenRouter, deducted from credits |
| Enterprise | Custom | Custom |
With BYOK, the model provider bills you for inference directly.
From openrouter.ai, checked Nov 10, 2026. Full breakdown: OpenRouter pricing.
FAQ
How much does Fireworks AI cost?
Fireworks AI serverless pricing per 1M tokens from $0.05 input; Batch 50% off, Spot 30% off Standard. Kimi, Qwen, GLM, DeepSeek rates. (checked Nov 10, 2026).
How much does OpenRouter cost?
Model tokens at provider list price, a 5.5% (Standard) or 8% (Business) fee on credit purchases, BYOK and USDC. (checked Nov 10, 2026).
Do Fireworks AI and OpenRouter have a free option?
Fireworks AI: none in the published plan table. OpenRouter: Standard (pay as you go): 5.5% on credit purchases.
Which is better, Fireworks AI or OpenRouter?
We do not pick a winner. The two price and package their products differently; the tables above quote each official pricing page so you can match a plan to your own usage.
Where do these prices come from?
Each vendor's own pricing page: fireworks.ai (checked Nov 10, 2026) and openrouter.ai (checked Nov 10, 2026). Prices change; confirm on the vendor's page before you buy.
Sources (official pages, read 2026-11-10)
Spot something out of date? Email hello@youraitools.co and we’ll fix it.