Llama 3 DeepInfra Instruct: pricing, context window and benchmarks
Llama 3 DeepInfra Instruct is a multimodal model from DeepInfra. It offers a 65,536-token context window, costs $3.84 per million input tokens and $20.22 per million output tokens, and averages 75.5 across the index's benchmark suite.
Pricing
Llama 3 DeepInfra Instruct costs $3.84 per million input tokens and $20.22 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.93 per million tokens. Cached input is listed at $0.49 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.84 | per 1M tokens |
| Output | $20.22 | per 1M tokens |
| Cached input | $0.49 | per 1M tokens |
| Blended 3:1 | $7.93 | estimate per 1M tokens |
| 1M in + 1M out | $24.06 | 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 | 75.5 | 317 | 47th | |
| GPQA Diamond | 71.7 | 226 | 62th | |
| SWE-bench Verified | 66.3 | 186 | 69th | |
| HumanEval | 81.4 | 201 | 67th | |
| MATH-500 | 77.6 | 263 | 56th | |
| AIME 2025 | 70.0 | 256 | 57th | |
| LiveCodeBench | 69.2 | 204 | 66th | |
| IFEval | 82.3 | 265 | 56th | |
| TruthfulQA | 76.3 | 299 | 50th | |
| HellaSwag | 86.1 | 212 | 65th | |
| MMMU | 74.2 | 179 | 70th | |
| Arena Elo | 1374.9 | 292 | 51th |
What Llama 3 DeepInfra Instruct is good for
Llama 3 DeepInfra Instruct is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.84 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.84 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3 Lambda | Lambda | 65536 | $3.90 | 75.6 |
| Llama 3 Novita Instruct | Novita AI | 32768 | $3.94 | 75.6 |
| Magistral Base | Mistral AI | 65536 | $3.86 | 75.6 |
| Reka Flash Reasoning | Reka AI | 32768 | $10.70 | 75.6 |
| Llama 3 DeepInfra Instruct | DeepInfra | 65536 | $3.84 | 75.5 |
| Yi-Lightning Chat | 01.AI | 32768 | $3.79 | 75.5 |
FAQ
How much does Llama 3 DeepInfra Instruct cost?
Llama 3 DeepInfra Instruct is listed at $3.84 per million input tokens and $20.22 per million output tokens. Cached input is $0.49 per million tokens. A blended 3:1 input-to-output mix is about $7.93 per million tokens.
What is the context window of Llama 3 DeepInfra Instruct?
Llama 3 DeepInfra Instruct has a context window of 65,536 tokens and can emit up to 16,384 output tokens per request in this index.
Is Llama 3 DeepInfra Instruct open weights?
Yes. Llama 3 DeepInfra Instruct is listed as an open-weight model under a open weights licence.
How does Llama 3 DeepInfra Instruct score on benchmarks?
Llama 3 DeepInfra Instruct averages 75.5 across the scored benchmarks in this index, ranking #238 of 600 models. Its strongest relative result is Arena Elo at 1374.9.
What is Llama 3 DeepInfra Instruct best for?
Llama 3 DeepInfra Instruct is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.84 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.