Firesearch Nano: pricing, context window and benchmarks
Firesearch Nano is a mid-range model from Fireworks AI. It offers a 8,192-token context window, costs $2.49 per million input tokens and $11.16 per million output tokens, and averages 55.6 across the index's benchmark suite.
Pricing
Firesearch Nano costs $2.49 per million input tokens and $11.16 per million output tokens. A blended 3:1 input-to-output mix works out to about $4.66 per million tokens. Cached input is listed at $0.26 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.49 | per 1M tokens |
| Output | $11.16 | per 1M tokens |
| Cached input | $0.26 | per 1M tokens |
| Blended 3:1 | $4.66 | estimate per 1M tokens |
| 1M in + 1M out | $13.65 | 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 | 63.0 | 488 | 19th | |
| GPQA Diamond | 52.6 | 493 | 18th | |
| SWE-bench Verified | 40.0 | 521 | 13th | |
| HumanEval | 58.9 | 513 | 15th | |
| MATH-500 | 52.9 | 533 | 11th | |
| AIME 2025 | 45.7 | 492 | 18th | |
| LiveCodeBench | 41.5 | 529 | 12th | |
| IFEval | 66.5 | 509 | 15th | |
| TruthfulQA | 62.6 | 495 | 18th | |
| HellaSwag | 73.2 | 475 | 21th | |
| MMMU | 54.8 | 500 | 17th | |
| Arena Elo | 1229.9 | 526 | 12th |
What Firesearch Nano is good for
Firesearch Nano 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 $2.49 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.
Strengths
- Input price of $2.49 per million tokens is at or below the index median.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Context window of 8,192 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 |
|---|---|---|---|---|
| Embed 4 Mini | Cohere | 4096 | $2.48 | 55.8 |
| Firesearch Nano | Fireworks AI | 8192 | $2.49 | 55.6 |
| Llama 3 DeepInfra 7B | DeepInfra | 16384 | $0.95 | 55.6 |
| Llama 3 Hyperbolic 7B | Hyperbolic | 4096 | $0.94 | 55.6 |
| Llama 3 Novita 8B | Novita AI | 16384 | $0.99 | 55.5 |
| Seed-OSS 7B | ByteDance | 8192 | $0.85 | 55.5 |
FAQ
How much does Firesearch Nano cost?
Firesearch Nano is listed at $2.49 per million input tokens and $11.16 per million output tokens. Cached input is $0.26 per million tokens. A blended 3:1 input-to-output mix is about $4.66 per million tokens.
What is the context window of Firesearch Nano?
Firesearch Nano has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Firesearch Nano open weights?
No. Firesearch Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Firesearch Nano score on benchmarks?
Firesearch Nano averages 55.6 across the scored benchmarks in this index, ranking #511 of 600 models. Its strongest relative result is Arena Elo at 1229.9.
What is Firesearch Nano best for?
Firesearch Nano 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 $2.49 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.