LLM Gateway
Access 100+ AI models through one API. Switch providers instantly, automatic fallbacks, no vendor lock-in.
Your App
Opper Gateway
100+ AI models
OpenAI
Anthropic
xAI
Meta
Mistral
Qwen
DeepSeek
GLM
& more...
Trusted by leading companies
Challenge
Direct model integrations lock you into single providers with no failover, waste budget on expensive models for simple tasks, and can't adapt to regional compliance needs.
Hard-coded model providers make it impossible to switch when better models emerge or when you need regional compliance.
A single API outage or rate limit can bring your entire application down. No built-in redundancy means lost revenue.
Using expensive flagship models for simple tasks wastes budget. No easy way to route different workloads to cost-optimal models.
Data sovereignty requirements force complex infrastructure. Can't easily use EU-hosted models when needed for compliance.
The Opper Way
Build once, run anywhere with intelligent model routing
Switch between 100+ models with one line of code. Test OpenAI, Anthropic, Google, and others without rewriting your application. Deploy the best model for each task.
from opperai import Opper
client = Opper()
# switch models with one parameter
client.call(
"instructions": "You are a helpful assistant",
"input": messages,
"model": "openai/gpt5"
# or "claude-sonnet-4.5"
# or "gemini-2.5-pro"
)Configure backup models that activate instantly if your primary fails. Built-in retry logic and error handling keep your application running through outages and rate limits.
claude-sonnet-4.5claude-sonnet-4.5Route simple tasks to fast, cheap models and complex ones to premium models. Track spend per model and optimize your AI budget automatically.
gemini-2.5-flashgpt-5Access EU-hosted models from AWS, Azure, GCP, and providers like Berget AI for GDPR compliance. Switch regions as easily as switching models.
claude-sonnet-4.5claude-sonnet-4.5gpt-5gpt-5Access the latest AI models from leading providers with unified pricing per million tokens.
All prices are per 1M tokens • EU and US regions available • Prices subject to change, see docs for latest
| Provider | Model | Region | Input (1M tokens) | Output (1M tokens) |
|---|---|---|---|---|
| Anthropic | claude-sonnet-4.5Popular | US | $3 | $15 |
| Anthropic | claude-opus-4.1Popular | US | $15 | $75 |
| Anthropic | claude-sonnet-4 | US | $3 | $15 |
| Anthropic | claude-opus-4 | US | $15 | $75 |
| Anthropic | claude-haiku-4.5 | US | $1 | $5 |
| Anthropic | claude-3.7-sonnet | US | $3 | $15 |
| Anthropic | claude-3.7-sonnet-20250219 | US | $3 | $15 |
| Anthropic | claude-3.5-sonnet | US | $3 | $15 |
| Anthropic | claude-3.5-sonnet-20241022 | US | $3 | $15 |
| Anthropic | claude-3.5-sonnet-20240620 | US | $3 | $15 |
| Anthropic | claude-3.5-haiku | US | $0.8 | $4 |
| AWS | claude-sonnet-4.5-euPopular | EU | $3 | $15 |
| AWS | claude-sonnet-4-eu | EU | $3 | $15 |
| AWS | claude-sonnet-4 | US | $3 | $15 |
| AWS | claude-opus-4 | US | $15 | $75 |
| AWS | claude-haiku-4.5-eu | EU | $1 | $5 |
| AWS | claude-3.7-sonnet-eu | EU | $3 | $15 |
| AWS | claude-3.7-sonnet | US | $3 | $15 |
| AWS | claude-3.5-sonnet-eu | EU | $3 | $15 |
| AWS | claude-3-haiku-eu | EU | $0.25 | $1.25 |
| AWS | gpt-oss-120b-eu | EU | $0.15 | $0.6 |
| AWS | gpt-oss-20b-eu | EU | $0.07 | $0.3 |
| AWS | pixtral-large-2502-eu | EU | $2 | $6 |
| Amazon | titan-text-express-v1-eu | EU | $1.3 | $1.7 |
| Azure | gpt-5Popular | EU | $1.25 | $10 |
| Azure | gpt-5-mini | EU | $0.25 | $2 |
| Azure | gpt-5-nano | EU | $0.05 | $0.4 |
| Azure | gpt-4o-eu | EU | $2.75 | $11 |
| Azure | gpt4-eu | EU | $30 | $60 |
| Azure | gpt3-eu | EU | $0.5 | $1.5 |
| Azure | meta-llama-3.1-405b | US | $5.33 | $16 |
| Azure | meta-llama-3.1-70b-eu | EU | $2.68 | $3.54 |
| Azure | mistral-large-eu | EU | $0.2 | $0.6 |
| Berget | gpt-oss-120b | EU | $0.35 | $1.05 |
| Berget | llama-3.3-70b-instruct | EU | $1.05 | $1.05 |
| Berget | mistral-small-3.1-24b-instruct | EU | $0.35 | $0.35 |
| Berget | qwen3-32b | EU | $0.58 | $0.58 |
| Cerebras | gpt-oss-120b | US | $0.25 | $0.69 |
| Cerebras | llama-3.3-70b | US | $0.85 | $1.2 |
| Cerebras | llama-4-maverick-17b-128e-instruct | US | $0.2 | $0.6 |
| Cerebras | llama-4-scout-17b-16e-instruct | US | $0.65 | $0.85 |
| Cerebras | llama3.1-8b | US | $0.1 | $0.1 |
| Cerebras | qwen-3-235b-a22b-instruct-2507 | US | $0.6 | $1.2 |
| Cerebras | qwen-3-235b-a22b-thinking-2507 | US | $0.6 | $1.2 |
| Cerebras | qwen-3-32b | US | $0.4 | $0.8 |
| Cerebras | qwen-3-coder-480b | US | $2 | $2 |
| Fireworks | deepseek-v3.1 | US | $1.2 | $1.2 |
| Fireworks | deepseek-v3-0324 | US | $0.9 | $0.9 |
| Fireworks | glm-4p6 | US | $0.55 | $2.19 |
| Fireworks | glm-4.5 | US | $0.55 | $2.19 |
| Fireworks | qwen3-235b-a22b-thinking-2507 | US | $0.5 | $0.5 |
| Fireworks | qwen3-coder-480b-a35b-instruct | US | $0.45 | $1.8 |
gemini-2.5-proPopular | US | $1.25 | $10 | |
gemini-2.5-flashPopular | US | $0.3 | $2.5 | |
gemini-2.5-flash-lite | US | $0.1 | $0.4 | |
gemini-2.5-flash-lite-preview | US | $0.1 | $0.4 | |
gemini-flash-latest | US | $0.3 | $2.5 | |
gemini-flash-lite-latest | US | $0.1 | $0.4 | |
gemini-2.0-flash | US | $0.1 | $0.4 | |
gemini-2.0-flash-001 | US | $0.1 | $0.4 | |
gemini-2.0-flash-exp | US | $0 | $0 | |
gemini-2.0-flash-lite | US | $0.07 | $0.3 | |
gemini-2.0-flash-lite-eu | EU | $0.07 | $0.3 | |
gemini-2.0-flash-thinking-exp | US | $0 | $0 | |
gemini-2.0-flash-thinking-exp-01-21 | US | $0 | $0 | |
claude-3.7-sonnet | EU | $3 | $15 | |
claude-opus-4 | US | $15 | $75 | |
claude-sonnet-4 | EU | $3 | $15 | |
| Groq | deepseek-r1-distill-llama-70b | US | $0.75 | $0.99 |
| Groq | gemma2-9b-it | US | $0.2 | $0.2 |
| Groq | gpt-oss-120b | US | $0.15 | $0.75 |
| Groq | gpt-oss-20b | US | $0.1 | $0.5 |
| Groq | llama-3.1-8b-instant | US | $0.05 | $0.08 |
| Groq | llama-3.3-70b-versatile | US | $0.59 | $0.79 |
| Groq | llama-4-maverick-17b-128e-instruct | US | $0.2 | $0.6 |
| Groq | llama-4-scout-17b-16e-instruct | US | $0.11 | $0.34 |
| Groq | moonshotai/kimi-k2-instruct | US | $1 | $3 |
| Groq | moonshotai/kimi-k2-instruct-0905 | US | $1 | $3 |
| Mistral | codestral-2508-eu | EU | $0.3 | $0.9 |
| Mistral | devstral-medium-2507-eu | EU | $0.4 | $2 |
| Mistral | magistral-medium-2506-eu | EU | $2 | $5 |
| Mistral | magistral-medium-eu | EU | $2 | $5 |
| Mistral | magistral-small-2507-eu | EU | $0.5 | $1.5 |
| Mistral | mistral-large-2407-eu | EU | $3 | $9 |
| Mistral | mistral-large-2411-eu | EU | $0.2 | $0.6 |
| Mistral | mistral-large-eu | EU | $2 | $6 |
| Mistral | mistral-medium-2508-eu | EU | $0.4 | $2 |
| Mistral | mistral-medium-eu | EU | $0.4 | $2 |
| Mistral | mistral-small-2501-eu | EU | $0.1 | $0.3 |
| Mistral | mistral-small-eu | EU | $0.1 | $0.3 |
| Mistral | mistral-small-latest-eu | EU | $0.1 | $0.3 |
| Mistral | mistral-tiny-eu | EU | $0.25 | $0.25 |
| Mistral | pixtral-12b-2409-eu | EU | $0.15 | $0.15 |
| Mistral | pixtral-large-2411-eu | EU | $2 | $6 |
| Mistral | pixtral-large-latest-eu | EU | $2 | $6 |
| OpenAI | gpt-5Popular | US | $1.25 | $10 |
| OpenAI | gpt-5-mini | US | $0.25 | $1 |
| OpenAI | gpt-5-nano | US | $0.05 | $0.4 |
| OpenAI | gpt-4.5-preview | US | $75 | $150 |
| OpenAI | gpt-4.1 | US | $2 | $8 |
| OpenAI | gpt-4.1-mini | US | $0.4 | $1.6 |
| OpenAI | gpt-4.1-nano | US | $0.1 | $0.4 |
| OpenAI | gpt-4o | US | $2.5 | $10 |
| OpenAI | gpt-4o-2024-05-13 | US | $5 | $15 |
| OpenAI | gpt-4o-2024-08-06 | US | $2.5 | $10 |
| OpenAI | gpt-4o-audio-preview | US | $2.5 | $10 |
| OpenAI | gpt-4o-mini | US | $0.15 | $0.6 |
| OpenAI | gpt4-turbo | US | $10 | $30 |
| OpenAI | gpt3.5-turbo | US | $0.5 | $1.5 |
| OpenAI | o1 | US | $15 | $60 |
| OpenAI | o1-2024-12-17 | US | $15 | $60 |
| OpenAI | o1-mini | US | $1.1 | $4.4 |
| OpenAI | o1-mini-2024-09-12 | US | $3 | $12 |
| OpenAI | o1-pro | US | $150 | $600 |
| OpenAI | o3 | US | $2 | $8 |
| OpenAI | o3-mini | US | $1.1 | $4.4 |
| OpenAI | o3-mini-2025-01-31 | US | $1.1 | $4.4 |
| OpenAI | o4-mini | US | $1.1 | $4.4 |
| Perplexity | sonar | US | $1 | $1 |
| Perplexity | sonar-deep-research | US | $2 | $8 |
| Perplexity | sonar-pro | US | $3 | $15 |
| Perplexity | sonar-reasoning | US | $1 | $5 |
| Perplexity | sonar-reasoning-pro | US | $2 | $8 |
| xAI | grok-4 | US | $3 | $15 |
| xAI | grok-4-fast-reasoning | US | $0.2 | $0.5 |
| xAI | grok-4-fast-non-reasoning | US | $0.2 | $0.5 |
| xAI | grok-3 | US | $3 | $15 |
| xAI | grok-3-mini-beta | US | $0.3 | $0.5 |
| xAI | grok-2 | US | $2 | $10 |
| xAI | grok-2-vision | US | $2 | $10 |
| xAI | grok-code-fast-1 | US | $0.2 | $1.5 |
Bring your own API keys or add custom model deployments using the Opper CLI or API.
opper models create example/my-gpt4 azure/gpt4-production YOUR_API_KEYLooking for a specific model? View complete model list →
Case Study
GetTested uses Opper's LLM Gateway to translate biomarker data into personalized health recommendations at scale — serving 10,000+ customers monthly across 60 countries with reliable, fact-checked AI insights.