Reka Flash: pricing, context window and benchmarks
Reka Flash is a multimodal model from Reka AI. It offers a 128,000-token context window, costs $9.95 per million input tokens and $36.78 per million output tokens, and averages 74.1 across the index's benchmark suite.
Pricing
Reka Flash costs $9.95 per million input tokens and $36.78 per million output tokens. A blended 3:1 input-to-output mix works out to about $16.66 per million tokens. Cached input is listed at $1.11 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $9.95 | per 1M tokens |
| Output | $36.78 | per 1M tokens |
| Cached input | $1.11 | per 1M tokens |
| Blended 3:1 | $16.66 | estimate per 1M tokens |
| 1M in + 1M out | $46.73 | 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 | 78.8 | 221 | 63th | |
| GPQA Diamond | 68.6 | 304 | 49th | |
| SWE-bench Verified | 65.5 | 206 | 66th | |
| HumanEval | 80.1 | 232 | 61th | |
| MATH-500 | 74.9 | 331 | 45th | |
| AIME 2025 | 67.1 | 312 | 48th | |
| LiveCodeBench | 67.6 | 236 | 61th | |
| IFEval | 81.1 | 309 | 49th | |
| TruthfulQA | 79.0 | 222 | 63th | |
| HellaSwag | 83.0 | 321 | 47th | |
| MMMU | 69.3 | 321 | 47th | |
| Arena Elo | 1369.0 | 322 | 46th |
What Reka Flash is good for
Reka Flash 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 $9.95 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.
Strengths
- Large 128,000-token context window for long documents and agent traces.
- 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 $9.95 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-Coder Base | DeepSeek | 32768 | $3.53 | 74.1 |
| GPT-5.1 Nano | OpenAI | 32768 | $9.56 | 74.1 |
| Gemma 3 Instruct | Google DeepMind | 128000 | $3.72 | 74.1 |
| Nova Lite Pro | Amazon | 200000 | $9.69 | 74.1 |
| QwQ Base | Alibaba Cloud | 65536 | $3.68 | 74.1 |
| Reka Flash | Reka AI | 128000 | $9.95 | 74.1 |
FAQ
How much does Reka Flash cost?
Reka Flash is listed at $9.95 per million input tokens and $36.78 per million output tokens. Cached input is $1.11 per million tokens. A blended 3:1 input-to-output mix is about $16.66 per million tokens.
What is the context window of Reka Flash?
Reka Flash has a context window of 128,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Reka Flash open weights?
No. Reka Flash is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Reka Flash score on benchmarks?
Reka Flash averages 74.1 across the scored benchmarks in this index, ranking #277 of 600 models. Its strongest relative result is Arena Elo at 1369.0.
What is Reka Flash best for?
Reka Flash 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 $9.95 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.