FastInfra vs Together AI at a glance
Together AI is known for hosted open models and GPU clusters. FastInfra combines hosted open and frontier models — Claude, GPT and Gemini alongside Llama, Qwen, DeepSeek and GLM — behind one OpenAI-compatible key, plus per-minute GPU pods, cloud VPS and dedicated bare metal on the same wallet.
| Capability | FastInfra |
|---|---|
| OpenAI-compatible API | Yes — change base_url and key |
| Open-weight and frontier models on one key | Yes — 714 models |
| Automatic lowest-cost routing and failover | Yes |
| GPU pods billed per minute | Yes — H100 from $3.12/hour |
| Cloud VPS and dedicated servers | Yes |
| Free-tier models | Yes — 12 models at $0 |
Live prices for popular models
| Model | Input $/1M | Output $/1M | Routes |
|---|---|---|---|
Claude Opus 5anthropic/claude-opus-5 | $5.4 | $27 | 1 |
Claude Sonnet 5anthropic/claude-sonnet-5 | $2.16 | $10.8 | 1 |
Claude Haiku 5.5anthropic/claude-haiku-5.5 | $0.108 | $0.54 | 1 |
Claude Fable 5.1anthropic/claude-fable-5.1 | $10.8 | $54 | 1 |
GPT-5.5openai/gpt-5.5 | $5.4 | $32.4 | 1 |
GPT-6 Solopenai/gpt-6-sol | $2.16 | $10.8 | 1 |
GPT-OSS 120Bgpt-oss-120b | $0.0302 | $0.1102 | 5 |
Gemini 3.8 Flashgoogle/gemini-3.8-flash | $0.81 | $4.05 | 1 |
DeepSeek V4 Prodeepseek/deepseek-v4-pro | $1.728 | $3.456 | 2 |
DeepSeek V4 Flashdeepseek/deepseek-v4-flash | $0.0983 | $0.1966 | 2 |
Qwen3.6 27Bqwen/qwen3.6-27b | $0.486 | $2.916 | 2 |
Kimi K3moonshotai/kimi-k3 | $0.2074 | $16.2 | 3 |
Grok 4.7x-ai/grok-4.7 | $2.16 | $6.48 | 1 |
GLM 5.3glm-5.3 | $0.0864 | $3.888 | 4 |
Llama 4 Maverickmeta-llama/llama-4-maverick | $0.2025 | $0.7047 | 1 |
Live GPU prices
When you need your own weights, fine-tunes or sustained throughput, rent a GPU by the minute from the same account.
| GPU | VRAM | Secure cloud $/hr | Community cloud $/hr | Max GPUs per pod |
|---|---|---|---|---|
| B300 | 288 GB | $9.71 | $7.50 | 8 |
| MI300X | 192 GB | $2.58 | — | 8 |
| B200 | 180 GB | $8.63 | $6.46 | 8 |
| H200 NVL | 143 GB | $4.09 | — | 8 |
| H200 SXM | 141 GB | $5.71 | $3.88 | 8 |
| RTX PRO 6000 | 96 GB | $2.69 | $1.83 | 9 |
| RTX PRO 6000 MaxQ | 96 GB | — | $1.77 | 2 |
| RTX PRO 6000 WK | 96 GB | $2.80 | $1.83 | 8 |
| H100 NVL | 94 GB | $3.45 | $2.80 | 10 |
| A100 PCIe | 80 GB | $1.93 | $1.29 | 8 |
| A100 SXM | 80 GB | $1.93 | $1.50 | 8 |
| H100 PCIe | 80 GB | $3.12 | $2.15 | 8 |
| H100 SXM | 80 GB | $4.31 | $2.91 | 8 |
| A40 | 48 GB | $0.64 | — | 10 |
| L40 | 48 GB | $0.89 | $0.75 | 10 |
| L40S | 48 GB | $1.18 | $0.85 | 8 |
| PRO 6000 MIG 48GB | 48 GB | $1.39 | — | 16 |
| RTX 6000 Ada | 48 GB | $1.07 | $0.80 | 8 |
| RTX A6000 | 48 GB | $0.64 | $0.36 | 10 |
| RTX PRO 5000 | 48 GB | $1.04 | $0.89 | 8 |
| A100 SXM 40GB | 40 GB | — | $1.08 | 2 |
| RTX 5000 Ada | 32 GB | — | $0.53 | 4 |
| RTX 5090 | 32 GB | $1.29 | $0.75 | 8 |
| RTX PRO 4500 | 32 GB | $0.78 | — | 8 |
| RTX PRO 4500 SE | 32 GB | $0.78 | — | 8 |
| L4 | 24 GB | $0.64 | — | 9 |
| PRO 6000 MIG 24GB | 24 GB | $0.75 | — | 32 |
| RTX 3090 | 24 GB | $0.54 | $0.24 | 8 |
| RTX 3090 Ti | 24 GB | — | $0.29 | 4 |
| RTX 4090 | 24 GB | $0.96 | $0.37 | 8 |
| RTX A5000 | 24 GB | $0.29 | $0.17 | 10 |
| RTX PRO 4000 | 24 GB | $0.62 | — | 4 |
| RTX 4000 Ada | 20 GB | $0.30 | $0.22 | 8 |
| RTX 4000 Ada SFF | 20 GB | — | $0.20 | 7 |
| RTX A4500 | 20 GB | $0.27 | $0.21 | 4 |
| RTX 2000 Ada | 16 GB | $0.26 | — | 8 |
| RTX 4080 | 16 GB | — | $0.29 | 2 |
| RTX 4080 SUPER | 16 GB | — | $0.30 | 4 |
| RTX 5080 | 16 GB | — | $0.42 | 8 |
| RTX A4000 | 16 GB | $0.27 | $0.18 | 8 |
| Tesla V100 | 16 GB | — | $0.21 | 8 |
| V100 SXM2 | 16 GB | — | $0.25 | 8 |
| RTX 3080 Ti | 12 GB | — | $0.20 | 4 |
| RTX 4070 Ti | 12 GB | — | $0.21 | 5 |
| RTX 3080 | 10 GB | — | $0.18 | 2 |
| RTX 3070 | 8 GB | — | $0.14 | 6 |
| RTX A2000 | 6 GB | — | $0.13 | 4 |
Migrate in five minutes
from openai import OpenAI
client = OpenAI(base_url="https://api.fastinfra.ai/v1", api_key="YOUR_FASTINFRA_KEY")
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Summarise this ticket in one line."}],
)
print(resp.choices[0].message.content)Open-weight model IDs use the publisher/model format (for example meta-llama/llama-4-maverick or qwen/qwen3.6-27b); GET /models returns the full list.