Model catalog
These are the live specs Gate's Smart Router reads on every request — list price per million tokens, context window, capabilities and routing tier. Call any model by its native name; if a provider isn't connected yet, Gate transparently serves the nearest equivalent and stamps the substitution on your receipt.
Showing 22 of 22 models
qwen/qwen3-235b
$0.22
$ / 1M in
$0.88
$ / 1M out
262K
context
Also answers to: qwen3-235b, qwen-max, qwen2.5-72b, qwen-plus
Until Alibaba is connected, Gate serves this as google/gemini-3.7-flash and marks the receipt.
anthropic/claude-haiku-4.5
$1.00
$ / 1M in
$5.00
$ / 1M out
200K
context
Also answers to: claude-haiku-4.5, claude-3-5-haiku, claude-3-5-haiku-20241022, claude-3-haiku, +1 more
Until Anthropic is connected, Gate serves this as google/gemini-2.5-flash and marks the receipt.
anthropic/claude-sonnet-4.5
$3.00
$ / 1M in
$15.00
$ / 1M out
200K
context
Also answers to: claude-sonnet-4.5, claude-sonnet-4, claude-3-7-sonnet, claude-3-5-sonnet, +2 more
Until Anthropic is connected, Gate serves this as openai/gpt-5.6-sol and marks the receipt.
anthropic/claude-opus-4.1
$15.00
$ / 1M in
$75.00
$ / 1M out
200K
context
Also answers to: claude-opus-4.1, claude-opus-4, claude-3-opus, claude-opus
Until Anthropic is connected, Gate serves this as openai/gpt-5.6-sol and marks the receipt.
cohere/command-a
$2.50
$ / 1M in
$10.00
$ / 1M out
256K
context
Also answers to: command-a, command-r-plus, command-r, command
Until Cohere is connected, Gate serves this as google/gemini-2.5-pro and marks the receipt.
deepseek/deepseek-v3.2
$0.28
$ / 1M in
$0.42
$ / 1M out
128K
context
Also answers to: deepseek-chat, deepseek-v3, deepseek-v3.2, deepseek/deepseek-chat
Until DeepSeek is connected, Gate serves this as google/gemini-2.5-flash and marks the receipt.
deepseek/deepseek-r1
$0.55
$ / 1M in
$2.19
$ / 1M out
128K
context
Also answers to: deepseek-reasoner, deepseek-r1, deepseek/deepseek-r1
Until DeepSeek is connected, Gate serves this as google/gemini-2.5-pro and marks the receipt.
google/gemini-2.5-flash-lite
$0.10
$ / 1M in
$0.40
$ / 1M out
1M
context
Also answers to: gemini-2.5-flash-lite, gemini-flash-lite, gemini-1.5-flash-8b
google/gemini-2.5-flash
$0.30
$ / 1M in
$2.50
$ / 1M out
1M
context
Also answers to: gemini-2.5-flash, gemini-1.5-flash, gemini-flash, gemini-2.0-flash
google/gemini-3.7-flash
$0.30
$ / 1M in
$2.50
$ / 1M out
1M
context
Also answers to: gemini-3.7-flash, gemini-3.5-flash, gemini-3-flash, gemini-3.6-flash
google/gemini-2.5-pro
$1.25
$ / 1M in
$10.00
$ / 1M out
2M
context
Also answers to: gemini-2.5-pro, gemini-1.5-pro, gemini-pro, gemini-3.1-pro
meta/llama-3.3-70b
$0.23
$ / 1M in
$0.40
$ / 1M out
128K
context
Also answers to: llama-3.3-70b, llama-3.3-70b-instruct, meta-llama/llama-3.3-70b-instruct, llama-3.1-70b, +1 more
Until Meta is connected, Gate serves this as google/gemini-2.5-flash and marks the receipt.
meta/llama-3.1-8b
$0.02
$ / 1M in
$0.03
$ / 1M out
128K
context
Also answers to: llama-3.1-8b, llama-3.1-8b-instruct, llama3-8b
Until Meta is connected, Gate serves this as google/gemini-2.5-flash-lite and marks the receipt.
meta/llama-4-maverick
$0.27
$ / 1M in
$0.85
$ / 1M out
1M
context
Also answers to: llama-4-maverick, llama-4, llama-4-scout
Until Meta is connected, Gate serves this as google/gemini-3.7-flash and marks the receipt.
mistral/mistral-small-3.2
$0.10
$ / 1M in
$0.30
$ / 1M out
128K
context
Also answers to: mistral-small, mistral-small-latest, ministral-8b, open-mistral-nemo
Until Mistral is connected, Gate serves this as google/gemini-2.5-flash-lite and marks the receipt.
mistral/mistral-large-2
$2.00
$ / 1M in
$6.00
$ / 1M out
128K
context
Also answers to: mistral-large, mistral-large-latest, mistral-medium, codestral
Until Mistral is connected, Gate serves this as google/gemini-2.5-pro and marks the receipt.
openai/gpt-5-nano
$0.05
$ / 1M in
$0.40
$ / 1M out
400K
context
Also answers to: gpt-5-nano, gpt-4o-mini, gpt-4.1-nano, gpt-3.5-turbo, +1 more
openai/gpt-5-mini
$0.25
$ / 1M in
$2.00
$ / 1M out
400K
context
Also answers to: gpt-5-mini, gpt-4.1-mini, gpt-4o, chatgpt-4o-latest, +1 more
openai/gpt-5.5
$1.25
$ / 1M in
$10.00
$ / 1M out
400K
context
Also answers to: gpt-5.5, gpt-5, gpt-4.1, gpt-4-turbo, +2 more
openai/gpt-5.6-sol
$1.25
$ / 1M in
$10.00
$ / 1M out
400K
context
Also answers to: gpt-5.6-sol, gpt-5.6, gpt-5.4, gpt-5.2
xai/grok-4
$3.00
$ / 1M in
$15.00
$ / 1M out
256K
context
Also answers to: grok-4, grok-3, grok-beta, grok
Until xAI is connected, Gate serves this as openai/gpt-5.5 and marks the receipt.
xai/grok-4-fast
$0.20
$ / 1M in
$0.50
$ / 1M out
2M
context
Also answers to: grok-4-fast, grok-3-mini, grok-2-mini
Until xAI is connected, Gate serves this as google/gemini-2.5-flash and marks the receipt.
Set cost, latency and capability rules once — Gate picks the cheapest model that fits every prompt and shows the savings on your dashboard.
