Tickerr / Pricing / Fireworks AI
Fireworks AI pricing (2026)
High-speed inference platform for open-source and fine-tuned models, focused on production-grade latency and throughput.
6 modelsFrom $0.200/1M input tokensUpdated April 2026
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Llama 3.1 8B Instruct | $0.200 | $0.200 | 131K |
| Phi-3 Vision 128K | $0.200 | $0.200 | 128K |
| Mixtral 8x7B Instruct | $0.500 | $0.500 | 33K |
| Llama 3.3 70B Instruct | $0.900 | $0.900 | 131K |
| Qwen 2.5 72B Instruct | $0.900 | $0.900 | 33K |
| Llama 3.1 405B Instruct | $3.00 | $3.00 | 131K |
About Fireworks AI
High-speed inference platform for open-source and fine-tuned models, focused on production-grade latency and throughput. Prices shown are on-demand rates in USD per 1 million tokens and may vary by region. Check the official pricing page for the latest rates before production use.
Compare with other providers: All AI pricing · GPT-4o · Claude 3.5 Sonnet · Gemini