Firesearch Pro: pricing, context window and benchmarks
Firesearch Pro is a mid-range model from Fireworks AI. It offers a 32,768-token context window, costs $7.67 per million input tokens and $32.83 per million output tokens, and averages 70.4 across the index's benchmark suite.
Pricing
Firesearch Pro costs $7.67 per million input tokens and $32.83 per million output tokens. A blended 3:1 input-to-output mix works out to about $13.96 per million tokens. Cached input is listed at $0.86 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $7.67 | per 1M tokens |
| Output | $32.83 | per 1M tokens |
| Cached input | $0.86 | per 1M tokens |
| Blended 3:1 | $13.96 | estimate per 1M tokens |
| 1M in + 1M out | $40.50 | 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 | 72.6 | 370 | 38th | |
| GPQA Diamond | 68.4 | 305 | 49th | |
| SWE-bench Verified | 59.8 | 330 | 45th | |
| HumanEval | 75.3 | 338 | 44th | |
| MATH-500 | 70.2 | 384 | 36th | |
| AIME 2025 | 61.0 | 382 | 36th | |
| LiveCodeBench | 63.9 | 320 | 47th | |
| IFEval | 80.1 | 331 | 45th | |
| TruthfulQA | 72.8 | 371 | 38th | |
| HellaSwag | 81.2 | 362 | 40th | |
| MMMU | 68.7 | 330 | 45th | |
| Arena Elo | 1362.0 | 340 | 43th |
What Firesearch Pro is good for
Firesearch Pro 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 $7.67 per million input tokens with a 32,768-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.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Nova Pro Mini | Amazon | 16384 | $7.74 | 70.6 |
| GPT-4.1 Nano | OpenAI | 32768 | $7.42 | 70.5 |
| Firesearch Pro | Fireworks AI | 32768 | $7.67 | 70.4 |
| Llama 3 Novita Base | Novita AI | 8192 | $3.06 | 70.3 |
| Sonar Pro Mini | Perplexity | 8192 | $8.02 | 70.3 |
| Yi-Large Base | 01.AI | 16384 | $2.78 | 70.3 |
FAQ
How much does Firesearch Pro cost?
Firesearch Pro is listed at $7.67 per million input tokens and $32.83 per million output tokens. Cached input is $0.86 per million tokens. A blended 3:1 input-to-output mix is about $13.96 per million tokens.
What is the context window of Firesearch Pro?
Firesearch Pro has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is Firesearch Pro open weights?
No. Firesearch Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Firesearch Pro score on benchmarks?
Firesearch Pro averages 70.4 across the scored benchmarks in this index, ranking #358 of 600 models. Its strongest relative result is Arena Elo at 1362.0.
What is Firesearch Pro best for?
Firesearch Pro 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 $7.67 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.