Authorization: Bearer. See the Fireworks API docs for provider-specific parameters.
Supports both managed (Lava’s API keys) and unmanaged (bring your own credentials) mode.
Quick Start
Chat Completions
Target URL:https://api.fireworks.ai/inference/v1/chat/completions
| Content Type | application/json |
| Streaming | Yes (set stream: true in request body) |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| accounts/fireworks/models/mixtral-8x22b-instruct | $1.20 | $1.20 |
| accounts/fireworks/models/glm-5 | $1.00 | $3.20 |
| accounts/fireworks/models/kimi-k2p5-turbo | $0.99 | $4.94 |
| accounts/fireworks/models/llama-v3p3-70b-instruct | $0.90 | $0.90 |
| accounts/fireworks/models/kimi-k2-instruct | $0.60 | $2.50 |
| accounts/fireworks/models/kimi-k2-thinking | $0.60 | $2.50 |
| accounts/fireworks/models/kimi-k2p5 | $0.60 | $3.00 |
| accounts/fireworks/models/glm-4p7 | $0.60 | $2.20 |
| accounts/fireworks/models/deepseek-v3p1 | $0.56 | $1.68 |
| accounts/fireworks/models/deepseek-v3p2 | $0.56 | $1.68 |
| accounts/fireworks/models/minimax-m2p5 | $0.30 | $1.20 |
| accounts/fireworks/models/qwen3-vl-30b-a3b-thinking | $0.15 | $0.60 |
| accounts/fireworks/models/gpt-oss-120b | $0.15 | $0.60 |
| accounts/fireworks/models/gpt-oss-20b | $0.07 | $0.30 |
Next Steps
All Providers
Browse all supported AI providers
Forward Proxy
Learn how to construct proxy URLs and authenticate requests