DeepInfra model pricing
As of October 10, 2026, 128 DeepInfra models are available through LiteLLM. The most recently added are Gemma 4 31B IT Turbo, Gemma 4 31B IT Ultra, Gemma 4 E4B IT. Prices below are DeepInfra's list prices.
DeepInfra models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| Gemma 4 31B IT Turbo | $0.09 / $0.34 per 1M tokens | 256K | 1 | Aug 2026 | |
| Gemma 4 31B IT Ultra | $0.27 / $0.76 per 1M tokens | 128K | 1 | Aug 2026 | |
| Gemma 4 E4B IT | $0.02 / $0.10 per 1M tokens | 128K | 1 | Aug 2026 | |
| GPT OSS 120B Turbo | OpenAI | $0.15 / $0.60 per 1M tokens | 128K | 1 | Aug 2026 |
| GPT OSS 120B Ultra | OpenAI | $0.20 / $0.95 per 1M tokens | 128K | 1 | Aug 2026 |
| Hy3 | – | $0.14 / $0.58 per 1M tokens | 256K | 3 | Aug 2026 |
| Ling 3.0 Flash | – | $0.06 / $0.18 per 1M tokens | 128K | 2 | Aug 2026 |
| MiniMax M2.7 Turbo | MiniMax | $0.38 / $1.70 per 1M tokens | 192K | 1 | Aug 2026 |
| Nemotron 3 Nano 30B A3B | NVIDIA | $0.05 / $0.20 per 1M tokens | 256K | 2 | Aug 2026 |
| Nemotron Content Safety 3.5 | NVIDIA | $0.20 / $0.20 per 1M tokens | 128K | 1 | Aug 2026 |
| Nvidia Nemotron 3 Super 120B A12B | NVIDIA | $0.085 / $0.40 per 1M tokens | 256K | 1 | Aug 2026 |
| Nvidia Nemotron 3 Ultra 550B A55B | NVIDIA | $0.50 / $2.20 per 1M tokens | 256K | 3 | Aug 2026 |
| Qwen3 Max Thinking | Alibaba | $1.20 / $6 per 1M tokens | 256K | 1 | Aug 2026 |
| Qwen3.8 27B | Alibaba | $0.40 / $3 per 1M tokens | 256K | 5 | Aug 2026 |
| Seed 1.8 | ByteDance | $0.25 / $2 per 1M tokens | 256K | 1 | Aug 2026 |
| Seed 2.0 Code | ByteDance | $0.50 / $3 per 1M tokens | 256K | 1 | Aug 2026 |
| Seed 2.0 Mini | ByteDance | $0.10 / $0.40 per 1M tokens | 256K | 1 | Aug 2026 |
| Seed 2.0 Pro | ByteDance | $0.50 / $3 per 1M tokens | 256K | 1 | Aug 2026 |
| Step 3.7 Flash | – | $0.20 / $1.15 per 1M tokens | 256K | 3 | Aug 2026 |
| Inkling | – | $0.95 / $4.05 per 1M tokens | 512K | 4 | Aug 2026 |
| Inkling Small | – | $0.45 / $1.20 per 1M tokens | 512K | 2 | Aug 2026 |
| Qwen3.5 9B | Alibaba | $0.10 / $0.15 per 1M tokens | 256K | 2 | Aug 2026 |
| Qwen3.8 2.4t A95B | Alibaba | $2 / $6 per 1M tokens | 256K | 3 | Aug 2026 |
| Muse Glimmer 30B | – | $0.30 / $1.20 per 1M tokens | 128K | 3 | Aug 2026 |
| Gemini 3.1 Pro | $2 / $12 per 1M tokens | 1M | 2 | Aug 2026 | |
| Kimi K3 | Moonshot AI | $2.85 / $14.25 per 1M tokens | 1M | 13 | Aug 2026 |
| Gemini 3.7 Flash | $0.75 / $3.75 per 1M tokens | 1M | 7 | Aug 2026 | |
| Nvidia Nemotron 3.5 Lightning | NVIDIA | $0.08 / $0.20 per 1M tokens | 256K | 1 | Aug 2026 |
| Qwen3.8 Max | Alibaba | $1.65 / $4.951 per 1M tokens | 256K | 8 | Aug 2026 |
| Qwen3.7 Max | Alibaba | $2.50 / $7.50 per 1M tokens | 256K | 6 | Jul 2026 |
| Claude Opus 5 | Anthropic | $5 / $25 per 1M tokens | 1M | 9 | Jul 2026 |
| Claude Sonnet 5 | Anthropic | $2 / $10 per 1M tokens | 1M | 9 | Jun 2026 |
| Claude Fable 5 | Anthropic | $10 / $50 per 1M tokens | 1M | 9 | Jun 2026 |
| Claude Opus 4.8 | Anthropic | $5 / $25 per 1M tokens | 1M | 8 | Jun 2026 |
| DeepSeek V4 Flash | DeepSeek | $0.08 / $0.18 per 1M tokens | 1M | 22 | Jun 2026 |
| DeepSeek V4 Pro | DeepSeek | $1.30 / $2.60 per 1M tokens | 1M | 17 | Jun 2026 |
| Gemma 4 26B A4B IT | $0.07 / $0.34 per 1M tokens | 256K | 8 | Jun 2026 | |
| Gemma 4 31B IT | $0.13 / $0.38 per 1M tokens | 256K | 11 | Jun 2026 | |
| GLM 5.2 | Z.ai | $0.75 / $2.40 per 1M tokens | 1M | 19 | Jun 2026 |
| Kimi K2.7 Code | Moonshot AI | $0.68 / $3.40 per 1M tokens | 256K | 14 | Jun 2026 |
| MiniMax M3 | MiniMax | $0.28 / $1.10 per 1M tokens | 512K | 9 | Jun 2026 |
| Qwen3.6 27B | Alibaba | $0.32 / $3.20 per 1M tokens | 256K | 6 | Jun 2026 |
| Qwen3.6 35B A3B | Alibaba | $0.10 / $0.95 per 1M tokens | 256K | 8 | Jun 2026 |
| Gemini 3.1 Flash Lite | $0.25 / $1.50 per 1M tokens | 1M | 5 | May 2026 | |
| Gemini 3.5 Flash | $1.50 / $9 per 1M tokens | 1M | 5 | May 2026 | |
| GLM 5.1 | Z.ai | $1.05 / $3.50 per 1M tokens | 198K | 10 | May 2026 |
| Mimo V2.5 | Xiaomi | $0.40 / $2 per 1M tokens | 256K | 2 | May 2026 |
| Mimo V2.5 Pro | Xiaomi | $1 / $3 per 1M tokens | 1M | 2 | May 2026 |
| MiniMax M2.7 | MiniMax | $0.25 / $1 per 1M tokens | 192K | 7 | May 2026 |
| Claude Opus 4.7 | Anthropic | $5 / $25 per 1M tokens | 1M | 7 | Apr 2026 |
| Kimi K2.6 | Moonshot AI | $0.75 / $3.50 per 1M tokens | 256K | 13 | Apr 2026 |
| Qwen3.5 122B A10B | Alibaba | $0.29 / $2.40 per 1M tokens | 256K | 4 | Mar 2026 |
| Qwen3.5 27B | Alibaba | $0.26 / $2.60 per 1M tokens | 256K | 2 | Mar 2026 |
| Qwen3.5 35B A3B | Alibaba | $0.14 / $1 per 1M tokens | 256K | 3 | Mar 2026 |
| Qwen3.5 397B A17B | Alibaba | $0.45 / $3 per 1M tokens | 256K | 7 | Mar 2026 |
| Claude Sonnet 4.6 | Anthropic | $3 / $15 per 1M tokens | 1M | 8 | Feb 2026 |
| GLM 4.7 Flash | Z.ai | $0.06 / $0.40 per 1M tokens | 198K | 5 | Feb 2026 |
| GLM 5 | Z.ai | $0.60 / $2.08 per 1M tokens | 198K | 7 | Feb 2026 |
| Kimi K2.5 | Moonshot AI | $0.45 / $2.25 per 1M tokens | 256K | 8 | Feb 2026 |
| GLM 4.7 | Z.ai | $0.40 / $1.75 per 1M tokens | 198K | 9 | Jan 2026 |
| Qwen3 Max | Alibaba | $1.20 / $6 per 1M tokens | 256K | 5 | Jan 2026 |
| DeepSeek V3.2 | DeepSeek | $0.26 / $0.38 per 1M tokens | 160K | 10 | Dec 2025 |
| Qwen3 VL 235B A22B Instruct | Alibaba | $0.20 / $0.88 per 1M tokens | 256K | 8 | Dec 2025 |
| Qwen3 VL 30B A3B Instruct | Alibaba | $0.15 / $0.60 per 1M tokens | 256K | 3 | Dec 2025 |
| Claude Haiku 4.5 | Anthropic | $1 / $5 per 1M tokens | 200K | 12 | Oct 2025 |
| DeepSeek V3.1 Terminus | DeepSeek | $0.27 / $1 per 1M tokens | 160K | 3 | Oct 2025 |
| GLM 4.6 | Z.ai | $0.50 / $2 per 1M tokens | 198K | 7 | Oct 2025 |
| Llama 3.3 Nemotron Super 49B V1.5 | Meta | $0.10 / $0.40 per 1M tokens | 128K | 1 | Oct 2025 |
| Nvidia Nemotron Nano 9B V2 | NVIDIA | $0.04 / $0.16 per 1M tokens | 128K | 3 | Oct 2025 |
| Qwen3 Next 80B A3B Instruct | Alibaba | $0.09 / $1.10 per 1M tokens | 256K | 10 | Sep 2025 |
| Qwen3 Next 80B A3B Thinking | Alibaba | $0.14 / $1.40 per 1M tokens | 256K | 9 | Sep 2025 |
| DeepSeek R1 0528 Turbo | DeepSeek | $1 / $3 per 1M tokens | 32K | 1 | Aug 2025 |
| DeepSeek R1 Turbo | DeepSeek | $1 / $3 per 1M tokens | 40K | 2 | Aug 2025 |
| DeepSeek V3.1 | DeepSeek | $0.25 / $0.95 per 1M tokens | 160K | 12 | Aug 2025 |
| GPT OSS 120B | OpenAI | $0.037 / $0.17 per 1M tokens | 128K | 22 | Aug 2025 |
| GPT OSS 20B | OpenAI | $0.03 / $0.14 per 1M tokens | 128K | 14 | Aug 2025 |
| L3 8B Lunaris V1 Turbo | – | $0.04 / $0.05 per 1M tokens | 8K | 1 | Aug 2025 |
| L3.1 70B Euryale V2.2 | – | $0.85 / $0.85 per 1M tokens | 128K | 1 | Aug 2025 |
| L3.3 70B Euryale V2.3 | – | $0.65 / $0.75 per 1M tokens | 128K | 1 | Aug 2025 |
| Mistral Nemo Instruct | Mistral AI | $0.019 / $0.03 per 1M tokens | 128K | 5 | Aug 2025 |
| Olmocr 7B | – | $0.27 / $1.50 per 1M tokens | 16K | 1 | Aug 2025 |
| Qwen3 235B A22B Instruct 2507 | Alibaba | $0.09 / $0.55 per 1M tokens | 256K | 8 | Aug 2025 |
| Qwen3 Coder 480B A35B Instruct | Alibaba | $0.40 / $1.60 per 1M tokens | 256K | 7 | Aug 2025 |
| Qwen3 Coder 480B A35B Instruct Turbo | Alibaba | $0.30 / $1 per 1M tokens | 256K | 1 | Aug 2025 |
| Gemma 3 12B IT | $0.05 / $0.15 per 1M tokens | 128K | 4 | Jul 2025 | |
| Gemma 3 4B IT | $0.05 / $0.10 per 1M tokens | 128K | 3 | Jul 2025 | |
| GLM 4.5 | Z.ai | $0.40 / $1.60 per 1M tokens | 128K | 5 | Jul 2025 |
| Hermes 3 Llama 3.1 405B | – | $1 / $1 per 1M tokens | 128K | 2 | Jul 2025 |
| Hermes 3 Llama 3.1 70B | – | $0.70 / $0.70 per 1M tokens | 128K | 2 | Jul 2025 |
| Kimi K2 Instruct | Moonshot AI | $0.50 / $2 per 1M tokens | 128K | 6 | Jul 2025 |
| Llama 3.1 Nemotron 70B Instruct | Meta | $0.60 / $0.60 per 1M tokens | 128K | 2 | Jul 2025 |
| Llama Guard 4 12B | Meta | $0.18 / $0.18 per 1M tokens | 160K | 1 | Jul 2025 |
| Qwen2.5 7B Instruct | Alibaba | $0.04 / $0.10 per 1M tokens | 32K | 3 | Jul 2025 |
| Qwen2.5 VL 32B Instruct | Alibaba | $0.20 / $0.60 per 1M tokens | 128K | 2 | Jul 2025 |
| Qwen3 14B | Alibaba | $0.12 / $0.24 per 1M tokens | 40K | 4 | Jul 2025 |
| Qwen3 235B A22B | Alibaba | $0.18 / $0.54 per 1M tokens | 40K | 5 | Jul 2025 |
| Qwen3 235B A22B Thinking 2507 | Alibaba | $0.30 / $2.90 per 1M tokens | 256K | 3 | Jul 2025 |
| Qwen3 30B A3B | Alibaba | $0.12 / $0.50 per 1M tokens | 40K | 9 | Jul 2025 |
| Claude 4 Opus | Anthropic | $16.50 / $82.50 per 1M tokens | 200K | 3 | Jun 2025 |
| Claude 4 Sonnet | Anthropic | $3.30 / $16.50 per 1M tokens | 200K | 5 | Jun 2025 |
| Gemini 2.5 Flash | $0.30 / $2.50 per 1M tokens | 1M | 8 | Jun 2025 | |
| Gemini 2.5 Pro | $1.25 / $10 per 1M tokens | 1M | 7 | Jun 2025 | |
| Mistral Small 3.2 24B Instruct | Mistral AI | $0.075 / $0.20 per 1M tokens | 128K | 3 | Jun 2025 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | $0.27 / $0.27 per 1M tokens | 128K | 5 | May 2025 |
| Llama Guard 3 8B | Meta | $0.055 / $0.055 per 1M tokens | 128K | 5 | May 2025 |
| Qwen3 32B | Alibaba | $0.08 / $0.28 per 1M tokens | 40K | 11 | May 2025 |
| QwQ 32B | Alibaba | $0.15 / $0.40 per 1M tokens | 128K | 7 | May 2025 |
| Llama 4 Maverick 17B 128e Instruct | Meta | $0.20 / $0.80 per 1M tokens | 1M | 9 | Apr 2025 |
| Llama 4 Scout 17B 16e Instruct | Meta | $0.10 / $0.30 per 1M tokens | 320K | 10 | Apr 2025 |
| Mistral Small 24B Instruct | Mistral AI | $0.05 / $0.08 per 1M tokens | 32K | 3 | Apr 2025 |
| Gemma 3 27B IT | $0.08 / $0.16 per 1M tokens | 128K | 6 | Mar 2025 | |
| Claude 3.7 Sonnet | Anthropic | $3.30 / $16.50 per 1M tokens | 200K | 7 | Feb 2025 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | $0.20 / $0.60 per 1M tokens | 128K | 9 | Feb 2025 |
| Phi 4 | Microsoft | $0.07 / $0.14 per 1M tokens | 16K | 2 | Feb 2025 |
| DeepSeek R1 | DeepSeek | $0.50 / $2.15 per 1M tokens | 160K | 16 | Jan 2025 |
| DeepSeek V3 | DeepSeek | $0.24 / $0.90 per 1M tokens | 160K | 15 | Jan 2025 |
| Llama 3.3 70B Instruct Turbo | Meta | $0.10 / $0.32 per 1M tokens | 128K | 2 | Jan 2025 |
| Llama 3.1 70B Instruct Turbo | Meta | $0.40 / $0.40 per 1M tokens | 128K | 2 | Dec 2024 |
| Llama 3.1 8B Instruct Turbo | Meta | $0.02 / $0.04 per 1M tokens | 128K | 2 | Dec 2024 |
| Llama 3.3 70B Instruct | Meta | $0.23 / $0.40 per 1M tokens | 128K | 18 | Dec 2024 |
| Qwen2.5 72B Instruct | Alibaba | $0.36 / $0.40 per 1M tokens | 32K | 6 | Dec 2024 |
| Llama3.2 11B Vision Instruct | Meta | $0.049 / $0.049 per 1M tokens | 128K | 5 | Nov 2024 |
| Llama3.2 3B Instruct | Meta | $0.02 / $0.02 per 1M tokens | 128K | 8 | Oct 2024 |
| Llama 3.1 70B Instruct | Meta | $0.40 / $0.40 per 1M tokens | 128K | 11 | Jul 2024 |
| Llama 3.1 8B Instruct | Meta | $0.03 / $0.05 per 1M tokens | 128K | 13 | Jul 2024 |
| WizardLM 2 8x22B | Microsoft | $0.48 / $0.48 per 1M tokens | 64K | 2 | May 2024 |
| Mixtral 8x7B Instruct V0.1 | Mistral AI | $0.40 / $0.40 per 1M tokens | 32K | 6 | Jan 2024 |
| Mythomax L2 13B | – | $0.40 / $0.40 per 1M tokens | 4K | 3 | – |
