Firefunction: pricing, context window and benchmarks
Firefunction is a mid-range model from Fireworks AI. It offers a 16,384-token context window, costs $8.16 per million input tokens and $41.40 per million output tokens, and averages 72.3 across the index's benchmark suite.
Pricing
Firefunction costs $8.16 per million input tokens and $41.40 per million output tokens. A blended 3:1 input-to-output mix works out to about $16.47 per million tokens. Cached input is listed at $1.14 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.16 | per 1M tokens |
| Output | $41.40 | per 1M tokens |
| Cached input | $1.14 | per 1M tokens |
| Blended 3:1 | $16.47 | estimate per 1M tokens |
| 1M in + 1M out | $49.56 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 76.0 | 306 | 49th | |
| GPQA Diamond | 69.2 | 288 | 52th | |
| SWE-bench Verified | 60.6 | 314 | 48th | |
| HumanEval | 75.1 | 342 | 43th | |
| MATH-500 | 76.7 | 288 | 52th | |
| AIME 2025 | 69.0 | 281 | 53th | |
| LiveCodeBench | 61.4 | 357 | 41th | |
| IFEval | 78.8 | 359 | 40th | |
| TruthfulQA | 73.6 | 362 | 40th | |
| HellaSwag | 84.0 | 281 | 53th | |
| MMMU | 70.8 | 277 | 54th | |
| Arena Elo | 1356.8 | 349 | 42th |
What Firefunction is good for
Firefunction is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $8.16 per million input tokens with a 16,384-token window, check its benchmark profile against the specific task before committing.
Strengths
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $8.16 per million tokens.
- Context window of 16,384 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Doubao 1.5 Pro Mini | ByteDance | 32768 | $8.30 | 72.3 |
| Firefunction | Fireworks AI | 16384 | $8.16 | 72.3 |
| Fusion Pro | OpenRouter | 65536 | $8.69 | 72.2 |
| Llama 3 Modal Base | Modal | 16384 | $3.21 | 72.2 |
| Llama 3.1 Base | Meta AI | 32768 | $3.39 | 72.2 |
| Seed-OSS Base | ByteDance | 16384 | $3.14 | 72.2 |
FAQ
How much does Firefunction cost?
Firefunction is listed at $8.16 per million input tokens and $41.40 per million output tokens. Cached input is $1.14 per million tokens. A blended 3:1 input-to-output mix is about $16.47 per million tokens.
What is the context window of Firefunction?
Firefunction has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is Firefunction open weights?
No. Firefunction is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Firefunction score on benchmarks?
Firefunction averages 72.3 across the scored benchmarks in this index, ranking #320 of 600 models. Its strongest relative result is Arena Elo at 1356.8.
What is Firefunction best for?
Firefunction is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $8.16 per million input tokens with a 16,384-token window, check its benchmark profile against the specific task before committing.