Firesearch Turbo: pricing, context window and benchmarks
Firesearch Turbo is a mid-range model from Fireworks AI. It offers a 16,384-token context window, costs $7.58 per million input tokens and $33.44 per million output tokens, and averages 69.3 across the index's benchmark suite.
Pricing
Firesearch Turbo costs $7.58 per million input tokens and $33.44 per million output tokens. A blended 3:1 input-to-output mix works out to about $14.04 per million tokens. Cached input is listed at $1.03 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $7.58 | per 1M tokens |
| Output | $33.44 | per 1M tokens |
| Cached input | $1.03 | per 1M tokens |
| Blended 3:1 | $14.04 | estimate per 1M tokens |
| 1M in + 1M out | $41.02 | 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 | 74.2 | 347 | 42th | |
| GPQA Diamond | 64.4 | 372 | 38th | |
| SWE-bench Verified | 57.6 | 362 | 40th | |
| HumanEval | 73.6 | 366 | 39th | |
| MATH-500 | 74.9 | 326 | 46th | |
| AIME 2025 | 61.3 | 380 | 37th | |
| LiveCodeBench | 62.0 | 348 | 42th | |
| IFEval | 77.4 | 374 | 38th | |
| TruthfulQA | 72.6 | 374 | 38th | |
| HellaSwag | 79.8 | 380 | 37th | |
| MMMU | 64.0 | 389 | 35th | |
| Arena Elo | 1352.1 | 361 | 40th |
What Firesearch Turbo is good for
Firesearch Turbo 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 $7.58 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.
- 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 |
|---|---|---|---|---|
| Gemini 3 Flash Nano | Google DeepMind | 32768 | $7.56 | 69.4 |
| Firesearch Turbo | Fireworks AI | 16384 | $7.58 | 69.3 |
| Gemini 2.5 Pro Nano | Google DeepMind | 32768 | $7.28 | 69.2 |
| DBRX Base | Databricks | 32768 | $2.63 | 69.1 |
| Firesearch Reasoning | Fireworks AI | 32768 | $7.74 | 69.0 |
| Phi-3.5 Chat | Microsoft | 16384 | $2.64 | 69.0 |
FAQ
How much does Firesearch Turbo cost?
Firesearch Turbo is listed at $7.58 per million input tokens and $33.44 per million output tokens. Cached input is $1.03 per million tokens. A blended 3:1 input-to-output mix is about $14.04 per million tokens.
What is the context window of Firesearch Turbo?
Firesearch Turbo has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is Firesearch Turbo open weights?
No. Firesearch Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Firesearch Turbo score on benchmarks?
Firesearch Turbo averages 69.3 across the scored benchmarks in this index, ranking #369 of 600 models. Its strongest relative result is Arena Elo at 1352.1.
What is Firesearch Turbo best for?
Firesearch Turbo 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 $7.58 per million input tokens with a 16,384-token window, check its benchmark profile against the specific task before committing.