> ## Documentation Index
> Fetch the complete documentation index at: https://lava.so/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# DeepInfra
> DeepInfra hosts open-source models on managed infrastructure with pay-per-token pricing and no minimum commitments.
DeepInfra offers 52 models through Lava's AI Gateway, supporting Chat Completions. Authentication uses `Authorization: Bearer`. See the [DeepInfra API docs](https://deepinfra.com/docs) for provider-specific parameters.
Supports both **managed** (Lava's API keys) and **unmanaged** (bring your own credentials) mode.
## Quick Start
```typescript theme={null}
const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fapi.deepinfra.com%2Fv1%2Fopenai%2Fchat%2Fcompletions', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${forwardToken}`,
},
body: JSON.stringify({
model: 'zai-org/GLM-5.2',
messages: [{ role: "user", content: "Hello!" }],
}),
});
```
## Chat Completions
**Target URL:** `https://api.deepinfra.com/v1/openai/chat/completions`
| | |
| ---------------- | ---------------------------------------- |
| **Content Type** | `application/json` |
| **Streaming** | Yes (set `stream: true` in request body) |
| Model | Input / 1M tokens | Output / 1M tokens |
| --------------------------------------------------- | ----------------- | ------------------ |
| zai-org/GLM-5.2 | \$1.40 | \$4.40 |
| deepseek-ai/DeepSeek-R1-Turbo | \$1.00 | \$3.00 |
| deepseek-ai/DeepSeek-R1-0528-Turbo | \$1.00 | \$3.00 |
| deepseek-ai/DeepSeek-V3-0324-Turbo | \$1.00 | \$3.00 |
| meta-llama/Meta-Llama-3.1-405B-Instruct | \$0.80 | \$0.80 |
| deepseek-ai/DeepSeek-R1 | \$0.70 | \$2.40 |
| deepseek-ai/DeepSeek-R1-0528 | \$0.50 | \$2.15 |
| deepseek-ai/DeepSeek-Prover-V2-671B | \$0.50 | \$2.18 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo | \$0.50 | \$0.50 |
| microsoft/WizardLM-2-8x22B | \$0.48 | \$0.48 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct | \$0.40 | \$1.60 |
| Gryphe/MythoMax-L2-13b | \$0.40 | \$0.40 |
| Qwen/Qwen2.5-72B-Instruct | \$0.36 | \$0.40 |
| meta-llama/Llama-3.2-11B-Vision-Instruct | \$0.345 | \$0.345 |
| deepseek-ai/DeepSeek-V3 | \$0.32 | \$0.89 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | \$0.30 | \$1.00 |
| meta-llama/Meta-Llama-3-70B-Instruct | \$0.30 | \$0.40 |
| MiniMaxAI/MiniMax-M2.5 | \$0.30 | \$1.20 |
| deepseek-ai/DeepSeek-V3.1-Terminus | \$0.27 | \$0.95 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | \$0.27 | \$0.27 |
| MiniMaxAI/MiniMax-M2.1 | \$0.27 | \$1.15 |
| MiniMaxAI/MiniMax-M2 | \$0.27 | \$1.15 |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | \$0.23 | \$2.30 |
| meta-llama/Llama-3.3-70B-Instruct | \$0.23 | \$0.40 |
| deepseek-ai/DeepSeek-V3.1 | \$0.21 | \$0.79 |
| deepseek-ai/DeepSeek-V3-0324 | \$0.20 | \$0.77 |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | \$0.20 | \$0.60 |
| meta-llama/Llama-Guard-4-12B | \$0.18 | \$0.18 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | \$0.15 | \$0.60 |
| Qwen/Qwen3-30B-A3B | \$0.12 | \$0.50 |
| Qwen/Qwen3-14B | \$0.12 | \$0.24 |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | \$0.10 | \$0.40 |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | \$0.10 | \$0.32 |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | \$0.10 | \$0.28 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | \$0.09 | \$1.10 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | \$0.09 | \$0.10 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | \$0.08 | \$0.30 |
| Qwen/Qwen3-32B | \$0.08 | \$0.28 |
| google/gemma-3-27b-it | \$0.08 | \$0.16 |
| microsoft/phi-4 | \$0.07 | \$0.14 |
| microsoft/phi-4-reasoning-plus | \$0.07 | \$0.35 |
| Qwen/Qwen2.5-Coder-32B-Instruct | \$0.06 | \$0.15 |
| google/gemma-3-12b-it | \$0.05 | \$0.10 |
| google/gemma-3-4b-it | \$0.05 | \$0.10 |
| microsoft/Phi-4-multimodal-instruct | \$0.05 | \$0.10 |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | \$0.04 | \$0.16 |
| Qwen/Qwen2.5-7B-Instruct | \$0.04 | \$0.10 |
| meta-llama/Meta-Llama-3.1-8B-Instruct | \$0.03 | \$0.05 |
| meta-llama/Meta-Llama-3-8B-Instruct | \$0.03 | \$0.06 |
| mistralai/Mistral-7B-Instruct-v0.3 | \$0.028 | \$0.054 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | \$0.02 | \$0.03 |
| meta-llama/Llama-3.2-1B-Instruct | \$0.005 | \$0.01 |
## Next Steps
Browse all supported AI providers
Learn how to construct proxy URLs and authenticate requests