Models

Start from any model.

30 models across 9 providers. Prices are USD per million tokens.

30 models
A
Anthropic / Claude Haiku 4.5 vision tools reasoning
anthropic/claude-haiku-4.5
Previous-generation Haiku.
200Kcontext
$1.00input / M
$5.00output / M
A
Anthropic / Claude Haiku 5.5 vision tools reasoning
anthropic/claude-haiku-5.5
Fast, low-cost Claude model.
1Mcontext
$0.10input / M
$0.50output / M
A
Anthropic / Claude Opus 4.5 vision tools reasoning
anthropic/claude-opus-4.5
Previous-generation Opus.
200Kcontext
$5.00input / M
$25.00output / M
A
Anthropic / Claude Opus 5.5 vision tools reasoning
anthropic/claude-opus-5.5
Anthropic's most capable model for complex, long-horizon work.
1Mcontext
$4.00input / M
$20.00output / M
A
Anthropic / Claude Sonnet 4.5 vision tools reasoning
anthropic/claude-sonnet-4.5
Previous-generation Sonnet, strong at coding.
200Kcontext
$3.00input / M
$15.00output / M
A
Anthropic / Claude Sonnet 5.5 vision tools reasoning
anthropic/claude-sonnet-5.5
Balanced intelligence and speed for production workloads.
1Mcontext
$2.00input / M
$10.00output / M
M
Mistral / Codestral tools
mistralai/codestral
Mistral's code model.
128Kcontext
$0.30input / M
$0.90output / M
DS
DeepSeek / DeepSeek Reasoner reasoning
deepseek/deepseek-reasoner
DeepSeek's reasoning model.
131Kcontext
$0.28input / M
$0.42output / M
DS
DeepSeek / DeepSeek V3 (Chat) tools
deepseek/deepseek-chat
DeepSeek's general chat model.
131Kcontext
$0.28input / M
$0.42output / M
G
Google / Gemini 2.5 Flash vision tools reasoning
google/gemini-2.5-flash
Fast hybrid-reasoning model with 1M context.
1Mcontext
$0.30input / M
$2.50output / M
G
Google / Gemini 2.5 Flash-Lite vision tools reasoning
google/gemini-2.5-flash-lite
Lowest-cost Gemini 2.5 model.
1Mcontext
$0.10input / M
$0.40output / M
G
Google / Gemini 2.5 Pro vision tools reasoning
google/gemini-2.5-pro
Google's reasoning model with 1M context.
1Mcontext
$1.25input / M
$10.00output / M
OA
OpenAI / GPT-4.1 vision tools
openai/gpt-4.1
Long-context (1M) non-reasoning model, strong at instruction following.
1Mcontext
$2.00input / M
$8.00output / M
OA
OpenAI / GPT-4.1 Mini vision tools
openai/gpt-4.1-mini
Cost-efficient GPT-4.1 with 1M context.
1Mcontext
$0.40input / M
$1.60output / M
OA
OpenAI / GPT-4o vision tools
openai/gpt-4o
Multimodal model with text and image input.
128Kcontext
$2.50input / M
$10.00output / M
OA
OpenAI / GPT-4o Mini vision tools
openai/gpt-4o-mini
Small, fast, cheap multimodal model.
128Kcontext
$0.15input / M
$0.60output / M
OA
OpenAI / GPT-5 vision tools reasoning
openai/gpt-5
General-purpose reasoning model with strong coding and tool use.
272Kcontext
$1.25input / M
$10.00output / M
OA
OpenAI / GPT-5 Mini vision tools reasoning
openai/gpt-5-mini
Faster, cheaper GPT-5 variant for well-defined tasks.
272Kcontext
$0.25input / M
$2.00output / M
OA
OpenAI / GPT-5 Nano vision tools reasoning
openai/gpt-5-nano
Smallest GPT-5 for classification, extraction and high volume.
272Kcontext
$0.05input / M
$0.40output / M
OA
OpenAI / GPT-5.5 vision tools reasoning
openai/gpt-5.5
OpenAI's flagship model for complex reasoning, coding and agentic work.
1.1Mcontext
$5.00input / M
$30.00output / M
Gq
Groq / gpt-oss-120b (Groq) tools reasoning
openai/gpt-oss-120b
OpenAI's open-weight 120B model on Groq's fast inference.
131Kcontext
$0.15input / M
$0.60output / M
x
xAI / Grok 4.5 vision tools reasoning
x-ai/grok-4.5
xAI's flagship Grok model.
500Kcontext
$2.00input / M
$6.00output / M
M
Meta / Llama 3.3 70B Instruct tools
meta-llama/llama-3.3-70b-instruct
Open-weight Llama 3.3 70B, served via Together AI.
131Kcontext
$1.04input / M
$1.04output / M
M
Mistral / Mistral Large vision tools
mistralai/mistral-large
Mistral's flagship model.
262Kcontext
$0.50input / M
$1.50output / M
M
Mistral / Mistral Small vision tools reasoning
mistralai/mistral-small
Efficient Mistral model.
262Kcontext
$0.15input / M
$0.60output / M
OA
OpenAI / o3 vision tools reasoning
openai/o3
Reasoning model for math, science and code.
200Kcontext
$2.00input / M
$8.00output / M
P
Perplexity / Sonar
perplexity/sonar
Web-grounded answers with citations.
128Kcontext
$1.00input / M
$1.00output / M
P
Perplexity / Sonar Pro
perplexity/sonar-pro
Advanced web-grounded search model.
200Kcontext
$3.00input / M
$15.00output / M
OA
OpenAI / Text Embedding 3 Large embeddings
openai/text-embedding-3-large
Higher-quality embeddings model (3072 dims).
8Kcontext
$0.13input / M
—output / M
OA
OpenAI / Text Embedding 3 Small embeddings
openai/text-embedding-3-small
Embeddings model (1536 dims).
8Kcontext
$0.02input / M
—output / M

No models match

Try removing a filter.