20 flagship models · 270+ total

Model Catalog

Every model routes through the Opsora gateway with automatic failover, load balancing, and usage tracking.

Coder

Code generation, completion, and review

qwen3-coder

Alibaba Qwen

Coder

Code generation & completion

Price$0.50 / 1M

deepseek-coder-v3

DeepSeek

Coder

Code generation & debugging

Price$0.14 / 1M

codestral-22b

Mistral AI

Coder

Code completion & review

Price$0.30 / 1M

starcoder2-15b

BigCode

Coder

Code completion across 600+ languages

Price$0.20 / 1M

codegemma-7b

Google

Coder

Code understanding & generation

Pricevaries

Ultra

Highest-capability reasoning and multimodal

nemotron-super

NVIDIA

Ultra

General reasoning & analysis

Price$0.80 / 1M

gemini-2.5-pro

Google

Ultra

Multimodal reasoning, 1M+ context

Price$1.25 / 1M

gpt-4o

OpenAI

Ultra

Multimodal general-purpose

Price$2.50 / 1M

claude-3.5-sonnet

Anthropic

Ultra

Reasoning, coding & analysis

Price$3.00 / 1M

deepseek-v3

DeepSeek

Ultra

Large-context reasoning

Price$0.27 / 1M

nemotron-ultra

NVIDIA

Ultra

High-capability open reasoning

Pricevaries

Fast

Low-latency, cost-effective inference

gemini-2.5-flash

Google

Fast

Fast multimodal inference

Price$0.075 / 1M

llama-3.3-8b

Meta

Fast

Lightweight general-purpose

Price$0.05 / 1M

mistral-nemo

Mistral AI

Fast

Efficient multilingual (128k)

Price$0.15 / 1M

phi-3.5-mini

Microsoft

Fast

Compact reasoning (128k)

Price$0.10 / 1M

qwen2.5-7b

Alibaba Qwen

Fast

Efficient multilingual & math

Price$0.06 / 1M

Open

Open-weight models you can self-host

granite-3.1-8b

IBM

Open

Enterprise open-weight

Pricevaries

llama-3.3-70b

Meta

Open

Large open-weight general

Price$0.59 / 1M

mistral-nemotron

Mistral / NVIDIA

Open

Open reasoning & code

Pricevaries

qwen2.5-coder-32b

Alibaba Qwen

Open

Open code generation

Pricevaries

All plans include access to every model. Pricing shown is per 1M tokens at the provider level.