Supported platforms

Compare AI providers and models

Connect to 11 leading AI providers and choose from 96 models, from ChatGPT and Claude to Gemini, Grok, Kimi, and MiniMax. See what's available, compare options, and switch providers without rebuilding your product.

AI providers
11

Major platforms your team already knows: OpenAI, Anthropic, Google, xAI, Cohere, Mistral, DeepSeek, Qwen, Groq, Kimi, and MiniMax.

Models available
96

Every model listed here is ready to use in ModelRiver today, with no extra setup on your side.

One connection
1 setup

Your team integrates once. Change models or providers later without a full rebuild.

OpenAI

GPT-5.5/5.4, GPT-4.1/4o, Codex, and O-series reasoning models

28 models
Frontier, mini, codex, and reasoning tiers
gpt-5.5
Newest frontier GPT model for coding and professional work
$5 in
$30 out
gpt-5.5-pro
Highest-compute GPT-5.5 variant
$30 in
$180 out
gpt-5.4
Production workhorse GPT model for professional work
$2.50 in
$15 out
gpt-5.4-mini
Strong mini GPT model for coding and subagents
$0.75 in
$4.50 out
gpt-5.4-nano
Smallest current GPT-5.4 variant
$0.2 in
$1.25 out
gpt-5.2
Previous frontier GPT model with configurable reasoning
$1.75 in
$14 out
gpt-5.1
Flagship GPT model for coding and agentic tasks
$1.25 in
$10 out
gpt-5
Previous GPT-5 reasoning model
$1.25 in
$10 out
gpt-5.4-pro
Highest-precision GPT-5.4 variant
$30 in
$180 out
gpt-5.2-pro
Previous pro GPT model for professional work
$21 in
$168 out
gpt-5-pro
Higher-compute GPT-5 variant
$15 in
$120 out
gpt-5-mini
Faster, cost-efficient GPT-5 variant
$0.25 in
$2 out
gpt-5-nano
Fastest and cheapest GPT-5 variant
$0.05 in
$0.4 out
gpt-5.3-codex
Latest Codex model for agentic coding
$1.75 in
$14 out
gpt-5.2-codex
High-end Codex model for long-horizon coding
$1.75 in
$14 out
gpt-5.1-codex
Codex model based on GPT-5.1
$1.25 in
$10 out
gpt-5.1-codex-mini
Cheaper GPT-5.1 Codex mini variant
$0.25 in
$2 out
gpt-5-codex
Baseline GPT-5 Codex model
$1.25 in
$10 out
gpt-4.1
Strong non-reasoning model for instructions and tools
$2 in
$8 out
gpt-4.1-mini
Efficient GPT-4.1 variant
$0.4 in
$1.60 out
gpt-4.1-nano
Lightweight GPT-4.1 model
$0.1 in
$0.4 out
gpt-4o
Widely used multimodal flagship model
$2.50 in
$10 out
gpt-4o-mini
Low-cost multimodal small model
$0.15 in
$0.6 out
o3-pro
Higher-compute o3 reasoning model
$20 in
$80 out
o3
Powerful reasoning model across text, code, and vision
$2 in
$8 out
o4-mini
Fast, cost-efficient reasoning model
$1.10 in
$4.40 out
o3-mini
Small reasoning model alternative to o3
$1.10 in
$4.40 out
o1-pro
Higher-compute legacy reasoning model still available in API
$150 in
$600 out

Anthropic

Claude Fable 5, Opus 4.8/4.7/4.6, Sonnet 4.6, and Haiku 4.5

claude-fable-5
Most capable Claude model for long-horizon agentic work
$10 in
$50 out
claude-opus-4-8
Latest Claude Opus model for complex agents
$5 in
$25 out
claude-opus-4-7
Previous Claude Opus model for complex agents
$5 in
$25 out
claude-opus-4-6
Claude Opus 4.6 for complex agents
$5 in
$25 out
claude-sonnet-4-6
Latest Claude Sonnet model for balanced speed and intelligence
$3 in
$15 out
claude-opus-4-5-20251101
Claude Opus 4.5 - flagship model
$5 in
$25 out
claude-sonnet-4-5-20250929
Claude Sonnet 4.5 - best for coding & agents
$3 in
$15 out
claude-haiku-4-5-20251001
Claude Haiku 4.5 - low latency and cost-efficient current Haiku
$1 in
$5 out

Google

Gemini 3.1 Pro Preview and Gemini 2.5 Pro, Flash, Flash-Lite

gemini-3.1-pro-preview
Gemini 3.1 Pro Preview - latest multimodal reasoning model
$2 in
$12 out
gemini-2.5-pro
Gemini 2.5 Pro - high-capability multipurpose model
$1.25 in
$10 out
gemini-2.5-flash
Gemini 2.5 Flash - fast high-throughput model
$0.3 in
$2.50 out
gemini-2.5-flash-lite
Gemini 2.5 Flash-Lite - ultra cost-efficient model
$0.1 in
$0.4 out

xAI

Grok 4.3, Grok 4.20 reasoning/non-reasoning, and Grok Build

grok-4.3
Grok 4.3 - default text, coding, and chat model
$1.25 in
$2.50 out
grok-4.20-0309-reasoning
Grok 4.20 Reasoning - structured reasoning workflows
$1.25 in
$2.50 out
grok-4.20-0309-non-reasoning
Grok 4.20 Non-Reasoning - fast text without reasoning overhead
$1.25 in
$2.50 out
grok-4.20-multi-agent-0309
Grok 4.20 Multi-Agent - long-context multi-agent orchestration
$1.25 in
$2.50 out
grok-build-0.1
Grok Build - agentic coding and build workflows
$1 in
$2 out

Cohere

Command A+, Command A, and current Command R family models

command-a-plus-05-2026
Command A+ - latest enterprise RAG and agentic model (May 2026)
$2.50 in
$10 out
command-a-03-2025
Command A - advanced instruction-following model (March 2025)
$2.50 in
$10 out
command-a-reasoning-08-2025
Command A Reasoning - reasoning-capable Command A variant
$2.50 in
$10 out
command-a-translate-08-2025
Command A Translate - state-of-the-art translation model
$2.50 in
$10 out
command-a-vision-07-2025
Command A Vision - multimodal Command A model for image inputs
$2.50 in
$10 out
command-r-plus-08-2024
Command R+ - strong long-context agent model
$2.50 in
$10 out
command-r-08-2024
Command R - lower-cost long-context model
$0.15 in
$0.6 out
command-r7b-12-2024
Command R7B - fastest low-cost Command model
$0.0375 in
$0.15 out

Mistral AI

Mistral Large/Medium/Small, Devstral, Magistral, Ministral, and Codestral

mistral-large-latest
Mistral Large 3 - flagship general-purpose model
$0.5 in
$1.50 out
mistral-medium-latest
Mistral Medium 3.5 - frontier multimodal model for agents and coding
$1.50 in
$7.50 out
mistral-small-latest
Mistral Small 4 - fast and efficient multimodal model
$0.1 in
$0.3 out
devstral-medium-latest
Devstral 2 - agentic coding model
$0.4 in
$2 out
devstral-small-latest
Devstral Small 2 - lightweight coding agent model
$0.1 in
$0.3 out
magistral-medium-latest
Magistral Medium - multimodal reasoning model
$2 in
$5 out
magistral-small-latest
Magistral Small - lightweight reasoning model
$0.5 in
$1.50 out
ministral-14b-latest
Ministral 3 14B - compact text and vision model
$0.2 in
$0.2 out
ministral-8b-latest
Ministral 3 8B - efficient edge-capable model
$0.15 in
$0.15 out
ministral-3b-latest
Ministral 3 3B - smallest Ministral 3 model
$0.1 in
$0.1 out
codestral-latest
Codestral - specialized coding model
$0.3 in
$0.9 out

DeepSeek

DeepSeek V4 Pro and V4 Flash in chat and thinking modes

deepseek-v4-pro
DeepSeek V4 Pro - frontier coding and long-horizon agents
$0.435 in
$0.87 out
deepseek-v4-flash
DeepSeek V4 Flash - default chat and high-volume workloads
$0.14 in
$0.28 out
deepseek-chat
Legacy alias for V4 Flash non-thinking mode (deprecated July 2026)
$0.14 in
$0.28 out
deepseek-reasoner
Legacy alias for V4 Flash thinking mode (deprecated July 2026)
$0.14 in
$0.28 out

Qwen

Qwen 3.5 Plus/Flash, Qwen Max/Plus/Flash, and Coder (Alibaba Cloud)

qwen3.5-plus
Qwen 3.5 Plus - latest balanced production model
$0.4 in
$2.40 out
qwen3.5-flash
Qwen 3.5 Flash - fast 1M-context cost-efficient model
$0.1 in
$0.4 out
qwen3-max
Qwen3 Max - latest flagship Qwen model
$1.60 in
$6.40 out
qwen-max
Qwen-Max - flagship model, highest capability
$1.60 in
$6.40 out
qwen-plus
Qwen-Plus - balanced performance and cost
$0.4 in
$1.20 out
qwen-flash
Qwen-Flash - fast and cost-efficient flagship model
$0.05 in
$0.4 out
qwen3-coder-plus
Qwen3 Coder Plus - current coding and agent model
$1 in
$5 out

Groq

Ultra-fast LPU inference - Llama 3.1/3.3, GPT OSS

llama-3.1-8b-instant
Llama 3.1 8B - fast low-latency model
$0.05 in
$0.08 out
llama-3.3-70b-versatile
Llama 3.3 70B - versatile high-capability model
$0.59 in
$0.79 out
openai/gpt-oss-120b
GPT OSS 120B - open model with strong quality/cost balance
$0.15 in
$0.6 out
openai/gpt-oss-20b
GPT OSS 20B - very fast open model for lightweight workloads
$0.075 in
$0.3 out

Kimi

Kimi K2.7 Code, K2.6, K2.5, and Moonshot V1 models

kimi-k2.7-code
Kimi K2.7 Code - latest coding model with 256K context
$1 in
$2 out
kimi-k2.6
Kimi K2.6 - flagship multimodal agent and coding model (256K context)
$0.95 in
$4 out
kimi-k2.5
Kimi K2.5 - multimodal model with thinking and non-thinking modes (256K context)
$0.6 in
$3 out
moonshot-v1-8k
Moonshot V1 8K - short-text generation model (8K context)
$1 in
$2 out
moonshot-v1-32k
Moonshot V1 32K - long-text generation model (32K context)
$1 in
$2 out
moonshot-v1-128k
Moonshot V1 128K - very long-text generation model (128K context)
$1 in
$2 out
moonshot-v1-8k-vision-preview
Moonshot V1 8K Vision - image understanding model (8K context)
$1 in
$2 out
moonshot-v1-32k-vision-preview
Moonshot V1 32K Vision - image understanding model (32K context)
$1 in
$2 out
moonshot-v1-128k-vision-preview
Moonshot V1 128K Vision - image understanding model (128K context)
$1 in
$2 out

MiniMax

MiniMax M3 and M2-series coding/agent models

MiniMax-M3
MiniMax M3 - latest agentic reasoning and coding model (1M context)
$0.3 in
$1.20 out
MiniMax-M2.7
MiniMax M2.7 - flagship MoE coding and agent model (205K context)
$0.3 in
$1.20 out
MiniMax-M2.7-highspeed
MiniMax M2.7 Highspeed - same M2.7 quality with higher throughput
$0.6 in
$2.40 out
MiniMax-M2.5
MiniMax M2.5 - legacy flagship coding/agent model, still supported
$0.3 in
$1.20 out
MiniMax-M2.5-highspeed
MiniMax M2.5 Highspeed - legacy M2.5 with higher throughput
$0.6 in
$2.40 out
MiniMax-M2.1
MiniMax M2.1 - legacy multilingual coding model, still supported
$0.3 in
$1.20 out
MiniMax-M2.1-highspeed
MiniMax M2.1 Highspeed - legacy M2.1 with higher throughput
$0.6 in
$2.40 out
MiniMax-M2
MiniMax M2 - legacy agentic reasoning model, still supported
$0.3 in
$1.20 out

Build once, stay flexible as AI changes

Set up your AI workflows once, then move between providers, including Kimi and MiniMax, when pricing, performance, or strategy shifts, without starting from scratch.

Start free View docs