Skip to content

Baseten new models #11767

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
AlexKer wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Baseten new models #11767

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c028c95
removed deprecated and added new models
AlexKer Feb 26, 2026
bf6816e
default model
AlexKer Feb 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
111 changes: 52 additions & 59 deletions packages/types/src/providers/baseten.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,25 @@ import type { ModelInfo } from "../model.js"
// https://baseten.co/products/model-apis/

export const basetenModels = {
"moonshotai/Kimi-K2-Thinking": {
maxTokens: 163_800,
contextWindow: 262_000,
"deepseek-ai/DeepSeek-V3-0324": {
maxTokens: 131_072,
contextWindow: 163_840,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
inputPrice: 0.77,
outputPrice: 0.77,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
},
"deepseek-ai/DeepSeek-V3.1": {
maxTokens: 131_072,
contextWindow: 163_840,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.5,
outputPrice: 1.5,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Kimi K2 Thinking - A model with enhanced reasoning capabilities from Kimi K2",
},
"zai-org/GLM-4.6": {
maxTokens: 200_000,
Expand All @@ -26,74 +34,72 @@ export const basetenModels = {
outputPrice: 2.2,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Frontier open model with advanced agentic, reasoning and coding capabilities",
},
"deepseek-ai/DeepSeek-R1": {
maxTokens: 131_072,
contextWindow: 163_840,
"zai-org/GLM-4.7": {
maxTokens: 200_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.55,
outputPrice: 5.95,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.2,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "DeepSeek's first-generation reasoning model",
},
"deepseek-ai/DeepSeek-R1-0528": {
maxTokens: 131_072,
contextWindow: 163_840,
"zai-org/GLM-5": {
maxTokens: 203_000,
contextWindow: 203_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 2.55,
outputPrice: 5.95,
supportsNativeTools: true,
inputPrice: 0.95,
outputPrice: 3.15,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "The latest revision of DeepSeek's first-generation reasoning model",
},
"deepseek-ai/DeepSeek-V3-0324": {
maxTokens: 131_072,
contextWindow: 163_840,
"moonshotai/Kimi-K2-Instruct-0905": {
maxTokens: 164_000,
contextWindow: 262_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.77,
outputPrice: 0.77,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Fast general-purpose LLM with enhanced reasoning capabilities",
},
"deepseek-ai/DeepSeek-V3.1": {
maxTokens: 131_072,
contextWindow: 163_840,
"moonshotai/Kimi-K2-Thinking": {
maxTokens: 164_000,
contextWindow: 262_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.5,
outputPrice: 1.5,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description:
"Extremely capable general-purpose LLM with hybrid reasoning capabilities and advanced tool calling",
},
"Qwen/Qwen3-235B-A22B-Instruct-2507": {
maxTokens: 262_144,
contextWindow: 262_144,
"moonshotai/Kimi-K2.5": {
maxTokens: 262_000,
contextWindow: 262_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.22,
outputPrice: 0.8,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 3.0,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Mixture-of-experts LLM with math and reasoning capabilities",
},
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
maxTokens: 262_144,
contextWindow: 262_144,
"MiniMaxAI/MiniMax-M2.5": {
maxTokens: 204_000,
contextWindow: 204_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.38,
outputPrice: 1.53,
supportsNativeTools: true,
inputPrice: 0.3,
outputPrice: 1.2,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Mixture-of-experts LLM with advanced coding and reasoning capabilities",
},
"openai/gpt-oss-120b": {
maxTokens: 128_072,
Expand All @@ -105,22 +111,9 @@ export const basetenModels = {
outputPrice: 0.5,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Extremely capable general-purpose LLM with strong, controllable reasoning capabilities",
},
"moonshotai/Kimi-K2-Instruct-0905": {
maxTokens: 168_000,
contextWindow: 262_000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "State of the art language model for agentic and coding tasks. September Update.",
},
} as const satisfies Record<string, ModelInfo>

export type BasetenModelId = keyof typeof basetenModels

export const basetenDefaultModelId = "zai-org/GLM-4.6" satisfies BasetenModelId
export const basetenDefaultModelId = "MiniMaxAI/MiniMax-M2.5" satisfies BasetenModelId