Llama 3 DeepInfra 7B: pricing, context window and benchmarks
Llama 3 DeepInfra 7B is a small open-weight model from DeepInfra. It offers a 16,384-token context window, costs $0.95 per million input tokens and $3.71 per million output tokens, and averages 55.6 across the index's benchmark suite.
Pricing
Llama 3 DeepInfra 7B costs $0.95 per million input tokens and $3.71 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.64 per million tokens. Cached input is listed at $0.14 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.95 | per 1M tokens |
| Output | $3.71 | per 1M tokens |
| Cached input | $0.14 | per 1M tokens |
| Blended 3:1 | $1.64 | estimate per 1M tokens |
| 1M in + 1M out | $4.66 | 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 | 63.6 | 482 | 20th | |
| GPQA Diamond | 54.1 | 479 | 20th | |
| SWE-bench Verified | 38.7 | 531 | 12th | |
| HumanEval | 57.1 | 530 | 12th | |
| MATH-500 | 55.1 | 519 | 14th | |
| AIME 2025 | 43.7 | 514 | 14th | |
| LiveCodeBench | 45.8 | 488 | 19th | |
| IFEval | 66.4 | 513 | 15th | |
| TruthfulQA | 63.6 | 480 | 20th | |
| HellaSwag | 71.0 | 520 | 13th | |
| MMMU | 53.0 | 519 | 14th | |
| Arena Elo | 1233.6 | 522 | 13th |
What Llama 3 DeepInfra 7B is good for
Llama 3 DeepInfra 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.95 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.95 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- 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.
- Less reliable on open-ended reasoning and complex multi-step instructions.
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 Llama 3 DeepInfra 7B cost?
Llama 3 DeepInfra 7B is listed at $0.95 per million input tokens and $3.71 per million output tokens. Cached input is $0.14 per million tokens. A blended 3:1 input-to-output mix is about $1.64 per million tokens.
What is the context window of Llama 3 DeepInfra 7B?
Llama 3 DeepInfra 7B has a context window of 16,384 tokens and can emit up to 8,192 output tokens per request in this index.
Is Llama 3 DeepInfra 7B open weights?
Yes. Llama 3 DeepInfra 7B is listed as an open-weight model under a open weights licence.
How does Llama 3 DeepInfra 7B score on benchmarks?
Llama 3 DeepInfra 7B averages 55.6 across the scored benchmarks in this index, ranking #512 of 600 models. Its strongest relative result is Arena Elo at 1233.6.
What is Llama 3 DeepInfra 7B best for?
Llama 3 DeepInfra 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.95 per million input tokens it can handle a large share of production traffic.