Side by side pricing and context for Llama 3.2 3B (Together) and Llama 3.2 3B (Fireworks). Rates are curated catalog values with last verified dates on each model page.
Llama 3.2 3B (Together)
Tiny Llama on Together for cheap OpenAI-compatible routing. Compare Groq 3B Instant-class hosts when latency is the main constraint.
Input $0.060 / Output $0.060 per 1M
Context 128K · Approx
Llama 3.2 3B (Fireworks)
Tiny Llama on Fireworks for low-cost routing layers. Use when you want Fireworks hosting instead of Groq or Together for the same size class.
Input $0.100 / Output $0.100 per 1M
Context 128K · Approx
Quick take
- Llama 3.2 3B (Together) is cheaper on input in this catalog snapshot.
- Llama 3.2 3B (Together) is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | Llama 3.2 3B (Together) | Llama 3.2 3B (Fireworks) |
|---|---|---|
| Input / 1M | $0.060 | $0.100 |
| Output / 1M | $0.060 | $0.100 |
| Cached input / 1M | n/a | n/a |
| Context | 128K | 128K |
| Tokenizer | Approx | Approx |