Every provider Seshat supports, with the models it knows, their context window and their capabilities.
This page is generated from the provider registry of the runtime. How to set keys and endpoints is in Configuration, and the code side in Providers and authentication.
Providers
Provider ID
Service
Authentication
Vision
Prompt cache
anthropic
Anthropic
api_key
Yes
Yes
openai
OpenAI
api_key
Yes
Yes
mistral
Mistral AI
api_key
Yes
No
gemini
Google Gemini
api_key
Yes
No
deepseek
DeepSeek
api_key
Yes
No
ollama
Ollama
none
No
No
openrouter
OpenRouter
api_key
Yes
No
codex
Codex
oauth
No
No
z-ai
Z.ai
api_key
Yes
Yes
minimax
MiniMax
api_key
Yes
Yes
opencode
OpenCode Zen
api_key
Yes
No
kimi
Kimi (Moonshot AI)
api_key
Yes
Yes
Models
Anthropic (anthropic)
Model ID
Context
Max output
Prompt cache
claude-sonnet-5-5
1M
128K
Yes
claude-haiku-5-5
1M
128K
Yes
Default large and small model shown. 14 models in all, read from the models.dev catalog.
OpenAI (openai)
Model ID
Context
Max output
Prompt cache
gpt-6.1-sol
1M
128K
Yes
gpt-6-luna
1M
128K
Yes
Default large and small model shown. 24 models in all, read from the models.dev catalog.
Mistral AI (mistral)
Model ID
Context
Max output
Prompt cache
mistral-large-2512
262K
8K
No
mistral-small-2603
262K
256K
No
Default large and small model shown. 17 models in all, read from the models.dev catalog.
Google Gemini (gemini)
Model ID
Context
Max output
Prompt cache
gemini-4-argon
1M
32K
No
gemini-3.5-flash-lite
1M
65K
No
Default large and small model shown. 18 models in all, read from the models.dev catalog.
DeepSeek (deepseek)
Model ID
Context
Max output
Prompt cache
deepseek-flash
1M
393K
No
deepseek-v4-pro
1M
393K
No
OpenRouter (openrouter)
Model ID
Context
Max output
Prompt cache
anthropic/claude-sonnet-5.5
1M
128K
No
anthropic/claude-haiku-5.5
1M
128K
No
Default large and small model shown. 311 models in all, read from the models.dev catalog.
Codex (codex)
Model ID
Context
Max output
Prompt cache
gpt-5.6-sol
200K
100K
No
gpt-5.6-terra
200K
100K
No
gpt-5.5
200K
100K
No
gpt-5.4
272K
32K
No
gpt-5.6-luna
200K
100K
No
gpt-5.4-mini
272K
16K
No
Z.ai (z-ai)
Model ID
Context
Max output
Prompt cache
glm-5.3
1M
131K
Yes
glm-5.3-flashx
1M
131K
Yes
Default large and small model shown. 18 models in all, read from the models.dev catalog.
MiniMax (minimax)
Model ID
Context
Max output
Prompt cache
MiniMax-M2.7-highspeed
204K
131K
Yes
MiniMax-M3
1M
512K
Yes
MiniMax-M2.7
204K
131K
Yes
MiniMax-M2.5-highspeed
204K
131K
Yes
MiniMax-M2.5
204K
131K
Yes
MiniMax-M2.1
204K
131K
Yes
MiniMax-M2
204K
131K
Yes
MiniMax-M3.1-Flash
1M
512K
Yes
OpenCode Zen (opencode)
Model ID
Context
Max output
Prompt cache
claude-sonnet-5-5
1M
128K
No
claude-haiku-5-5
1M
128K
No
Default large and small model shown. 84 models in all, read from the models.dev catalog.