> ## 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 85 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: 'ByteDance/Seed-1.8',
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 |
| ------------------------------------------------- | ----------------- | ------------------ |
| Qwen/Qwen3.7-Max | \$2.50 | \$7.50 |
| deepseek-ai/DeepSeek-V4-Pro | \$1.30 | \$2.60 |
| Qwen/Qwen3-Max | \$1.20 | \$6.00 |
| Qwen/Qwen3-Max-Thinking | \$1.20 | \$6.00 |
| zai-org/GLM-5.1 | \$1.05 | \$3.50 |
| NousResearch/Hermes-3-Llama-3.1-405B | \$1.00 | \$1.00 |
| XiaomiMiMo/MiMo-V2.5-Pro | \$1.00 | \$3.00 |
| deepseek-ai/DeepSeek-R1-0528-Turbo | \$1.00 | \$3.00 |
| deepseek-ai/DeepSeek-V3-0324-Turbo | \$1.00 | \$3.00 |
| zai-org/GLM-5.2 | \$0.93 | \$3.00 |
| Sao10K/L3.1-70B-Euryale-v2.2 | \$0.85 | \$0.85 |
| moonshotai/Kimi-K2.6 | \$0.75 | \$3.50 |
| moonshotai/Kimi-K2.7-Code | \$0.74 | \$3.50 |
| NousResearch/Hermes-3-Llama-3.1-70B | \$0.70 | \$0.70 |
| zai-org/GLM-5 | \$0.60 | \$2.08 |
| ByteDance/Seed-2.0-code | \$0.50 | \$3.00 |
| ByteDance/Seed-2.0-pro | \$0.50 | \$3.00 |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | \$0.50 | \$2.20 |
| deepseek-ai/DeepSeek-R1-0528 | \$0.50 | \$2.15 |
| moonshotai/Kimi-K2.5 | \$0.45 | \$2.25 |
| Qwen/Qwen3.5-397B-A17B | \$0.45 | \$3.00 |
| zai-org/GLM-4.6 | \$0.43 | \$1.74 |
| MiniMaxAI/MiniMax-M2.7-Turbo | \$0.40 | \$2.00 |
| XiaomiMiMo/MiMo-V2.5 | \$0.40 | \$2.00 |
| zai-org/GLM-4.7 | \$0.40 | \$1.75 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct | \$0.40 | \$1.60 |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | \$0.40 | \$0.40 |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | \$0.40 | \$0.40 |
| 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 |
| Qwen/Qwen3.6-27B | \$0.32 | \$3.20 |
| deepseek-ai/DeepSeek-V3 | \$0.32 | \$0.89 |
| MiniMaxAI/MiniMax-M3 | \$0.30 | \$1.20 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | \$0.30 | \$1.00 |
| Qwen/Qwen3.5-122B-A10B | \$0.29 | \$2.40 |
| deepseek-ai/DeepSeek-V3.1-Terminus | \$0.27 | \$0.95 |
| deepseek-ai/DeepSeek-V3.2 | \$0.26 | \$0.38 |
| Qwen/Qwen3.5-27B | \$0.26 | \$2.60 |
| ByteDance/Seed-1.8 | \$0.25 | \$2.00 |
| MiniMaxAI/MiniMax-M2.7 | \$0.25 | \$1.00 |
| deepseek-ai/DeepSeek-V3-0324 | \$0.24 | \$0.90 |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | \$0.23 | \$2.30 |
| deepseek-ai/DeepSeek-V3.1 | \$0.21 | \$0.79 |
| nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | \$0.20 | \$0.80 |
| nvidia/Nemotron-Content-Safety-3.5 | \$0.20 | \$0.20 |
| Qwen/Qwen3-VL-235B-A22B-Instruct | \$0.20 | \$0.88 |
| stepfun-ai/Step-3.7-Flash | \$0.20 | \$1.15 |
| meta-llama/Llama-Guard-4-12B | \$0.18 | \$0.18 |
| openai/gpt-oss-120b-Turbo | \$0.15 | \$0.60 |
| Qwen/Qwen3-VL-30B-A3B-Instruct | \$0.15 | \$0.60 |
| Qwen/Qwen3.6-35B-A3B | \$0.15 | \$0.95 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | \$0.15 | \$0.60 |
| MiniMaxAI/MiniMax-M2.5 | \$0.15 | \$1.15 |
| deepreinforce-ai/Ornith-1.0-35B | \$0.14 | \$1.00 |
| Qwen/Qwen3.5-35B-A3B | \$0.14 | \$1.00 |
| tencent/Hy3 | \$0.14 | \$0.58 |
| google/gemma-4-31B-it | \$0.13 | \$0.38 |
| google/gemma-4-31B-it-turbo | \$0.12 | \$0.37 |
| Qwen/Qwen3-30B-A3B | \$0.12 | \$0.50 |
| Qwen/Qwen3-14B | \$0.12 | \$0.24 |
| ByteDance/Seed-2.0-mini | \$0.10 | \$0.40 |
| Qwen/Qwen3.5-9B | \$0.10 | \$0.15 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | \$0.10 | \$0.30 |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | \$0.10 | \$0.32 |
| deepseek-ai/DeepSeek-V4-Flash | \$0.09 | \$0.18 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | \$0.09 | \$1.10 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | \$0.09 | \$0.10 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | \$0.085 | \$0.40 |
| Qwen/Qwen3-32B | \$0.08 | \$0.28 |
| google/gemma-3-27b-it | \$0.08 | \$0.16 |
| mistralai/Mistral-Small-3.2-24B-Instruct-2506 | \$0.075 | \$0.20 |
| google/gemma-4-26B-A4B-it | \$0.07 | \$0.34 |
| microsoft/phi-4 | \$0.07 | \$0.14 |
| zai-org/GLM-4.7-Flash | \$0.06 | \$0.40 |
| mistralai/Mistral-Small-24B-Instruct-2501 | \$0.05 | \$0.08 |
| nvidia/Nemotron-3-Nano-30B-A3B | \$0.05 | \$0.20 |
| google/gemma-3-12b-it | \$0.05 | \$0.15 |
| google/gemma-3-4b-it | \$0.05 | \$0.10 |
| Sao10K/L3-8B-Lunaris-v1-Turbo | \$0.04 | \$0.05 |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | \$0.04 | \$0.16 |
| openai/gpt-oss-120b | \$0.037 | \$0.17 |
| openai/gpt-oss-20b | \$0.03 | \$0.14 |
| mistralai/Mistral-Nemo-Instruct-2407 | \$0.02 | \$0.04 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | \$0.02 | \$0.03 |
## Next Steps
Browse all supported AI providers
Learn how to construct proxy URLs and authenticate requests