Fireworks AI
- Categories
- Inference hosts
- Owned by
- Fireworks AI, Inc. (private)
- HQ
- US
- Website
- https://fireworks.ai
- Pricing page
- https://docs.fireworks.ai/serverless/pricing
- Fee model
- per_token+per_second_gpu
- Fees
- Serverless per-token (Standard/Priority/Fast paths); unlisted models priced by size: <4B $0.10, 4-16B $0.20, >16B $0.90, MoE<=56B $0.50, MoE 56.1-176B $1.20 per 1M tokens; On-demand deployments per GPU-second (H100/H200 $8.00/h, B200 $13/h, B300 $15/h, GB300 $20/h; region-restricted 1.5x)
- Free tier
- $1 free credits
- OpenAI-compatible API
- yes
- Notes
- Batch inference billed at 50% of serverless. From 2026-09-01 US-only serverless models priced at 1.5x base.
- Sources
- https://docs.fireworks.ai/serverless/pricing https://fireworks.ai/pricing collected 2026-09-18
LLM prices (16 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 accounts/fireworks/models/deepseek-v4-flash-0731 |
$0.22 | $0.66 | $0.007 | — | ✓ src |
| DeepSeek V4 Flash Vision Exp accounts/fireworks/models/deepseek-v4-flash-vision-exp |
$0.22 | $0.66 | $0.007 | — | ✓ src |
| DeepSeek V4 Pro 0813 accounts/fireworks/models/deepseek-v4-pro-0813 |
$1.32 | $3.96 | $0.044 | — | ✓ src |
| DeepSeek V4.1 Flash accounts/fireworks/models/deepseek-v4p1-flash |
$0.22 | $0.66 | $0.007 | — | ✓ src |
| GLM-5.2 accounts/fireworks/models/glm-5p2 |
$1.40 | $4.40 | $0.14 | — | ✓ src |
| GLM-5.3 accounts/fireworks/models/glm-5p3 |
$1.40 | $4.40 | $0.26 | — | ✓ src |
| GLM-5.3 Flash accounts/fireworks/models/glm-5p3-flash |
$0.15 | $0.50 | $0.03 | — | ✓ src |
| gpt-oss-120b accounts/fireworks/models/gpt-oss-120b |
$0.15 | $0.60 | $0.015 | — | ✓ src |
| Kimi K2.6 accounts/fireworks/models/kimi-k2p6 |
$0.95 | $4 | $0.16 | — | ✓ src |
| Kimi K2.7 Code accounts/fireworks/models/kimi-k2p7-code |
$0.95 | $4 | $0.19 | — | ✓ src |
| Kimi K3 accounts/fireworks/models/kimi-k3 |
$3 | $15 | $0.30 | — | ✓ src |
| MiniMax M3 accounts/fireworks/models/minimax-m3 |
$0.30 | $1.20 | $0.06 | — | ✓ src |
| Muse Glimmer 30B accounts/fireworks/models/muse-glimmer-30b |
$0.35 | $1.50 | $0.04 | — | ✓ src |
| NVIDIA Nemotron 3 Ultra (Preview) accounts/fireworks/models/nemotron-3-ultra-nvfp4 |
$0.60 | $2.40 | $0.12 | — | ✓ src |
| NVIDIA Nemotron 3.5 Lightning 30B A3B accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b |
$0.05 | $0.20 | $0.01 | — | ✓ src |
| Qwen 3.8 Max accounts/fireworks/models/qwen3p8-max |
$2 | $6 | $0.25 | — | ✓ src |