Llama 3 DeepInfra Chat: pricing, context window and benchmarks
Llama 3 DeepInfra Chat is a multimodal model from DeepInfra. It offers a 200,000-token context window, costs $3.74 per million input tokens and $15.32 per million output tokens, and averages 75.0 across the index's benchmark suite.
Pricing
Llama 3 DeepInfra Chat costs $3.74 per million input tokens and $15.32 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.63 per million tokens. Cached input is listed at $0.42 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.74 | per 1M tokens |
| Output | $15.32 | per 1M tokens |
| Cached input | $0.42 | per 1M tokens |
| Blended 3:1 | $6.63 | estimate per 1M tokens |
| 1M in + 1M out | $19.06 | 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 | 76.8 | 281 | 53th | |
| GPQA Diamond | 69.0 | 295 | 51th | |
| SWE-bench Verified | 65.5 | 204 | 66th | |
| HumanEval | 77.3 | 304 | 49th | |
| MATH-500 | 80.6 | 198 | 67th | |
| AIME 2025 | 72.5 | 209 | 65th | |
| LiveCodeBench | 67.8 | 230 | 62th | |
| IFEval | 81.4 | 291 | 52th | |
| TruthfulQA | 78.3 | 244 | 59th | |
| HellaSwag | 83.6 | 299 | 50th | |
| MMMU | 72.1 | 240 | 60th | |
| Arena Elo | 1376.4 | 286 | 52th |
What Llama 3 DeepInfra Chat is good for
Llama 3 DeepInfra Chat 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 $3.74 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Input price of $3.74 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 |
|---|---|---|---|---|
| Codestral Instruct | Mistral AI | 65536 | $4.01 | 75.1 |
| Llama 3 Hyperbolic Chat | Hyperbolic | 200000 | $3.64 | 75.1 |
| Llama 3 Replicate Instruct | Replicate | 128000 | $3.71 | 75.1 |
| Mistral Small 3 Instruct | Mistral AI | 32768 | $3.97 | 75.1 |
| Llama 3 DeepInfra Chat | DeepInfra | 200000 | $3.74 | 75.0 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
FAQ
How much does Llama 3 DeepInfra Chat cost?
Llama 3 DeepInfra Chat is listed at $3.74 per million input tokens and $15.32 per million output tokens. Cached input is $0.42 per million tokens. A blended 3:1 input-to-output mix is about $6.63 per million tokens.
What is the context window of Llama 3 DeepInfra Chat?
Llama 3 DeepInfra Chat has a context window of 200,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Llama 3 DeepInfra Chat open weights?
Yes. Llama 3 DeepInfra Chat is listed as an open-weight model under a open weights licence.
How does Llama 3 DeepInfra Chat score on benchmarks?
Llama 3 DeepInfra Chat averages 75.0 across the scored benchmarks in this index, ranking #253 of 600 models. Its strongest relative result is Arena Elo at 1376.4.
What is Llama 3 DeepInfra Chat best for?
Llama 3 DeepInfra Chat 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 $3.74 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.