Fireworks · text · last verified 2026-10-26
Qwen 3.8 Max
Answer: As of 2026-10-26, Fireworks lists Qwen 3.8 Max at $2.00 input and $6.00 output per 1M tokens (cached input $0.250). Status: verified. Source: https://docs.fireworks.ai/serverless/pricing.
Key stats
- Input: $2.00 / 1M
- Output: $6.00 / 1M
- Cached in: $0.250
- Context: —
- Status: verified
- Last verified: 2026-10-26
- Source: official page
- Input
- $2.00 / 1M
- Output
- $6.00 / 1M
- Cached input
- $0.250
- Batch input / output
- — / —
- Other pricing
- —
- Context window
- —
- Free tier
- Not stated
Standard tier; Priority tier ~1.25x.
Cost per 1,000 tasks
- Support reply (3K/500)
- $9.00
- RAG answer (12K/700)
- $28.20
- Code review (40K/2K)
- $92.00
Cite this
Fireworks Qwen 3.8 Max rates from Ratecard (https://ratecardai.pages.dev/models/fireworks-qwen-3-8-max.html), checked 2026-10-26. License: CC BY 4.0. Please attribute "Ratecard" with a link to https://ratecardai.pages.dev/.
One email a week: what changed in AI API pricing, with sources. No spam; unsubscribe anytime.