shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): add Together AI provider

Browse Source
This commit is contained in:
Mario Zechner
2026-05-08 16:44:18 +02:00
parent 9751057be9
commit 7adb8e7634
30 changed files with 714 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
packages/ai/src/env-api-keys.ts
View File

@@ -117,6 +117,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
"moonshotai-cn": "MOONSHOT_API_KEY",
huggingface: "HF_TOKEN",
fireworks: "FIREWORKS_API_KEY",
together: "TOGETHER_API_KEY",
opencode: "OPENCODE_API_KEY",
"opencode-go": "OPENCODE_API_KEY",
"kimi-coding": "KIMI_API_KEY",

364
packages/ai/src/models.generated.ts
View File

@@ -10188,23 +10188,6 @@ export const MODELS = {
contextWindow: 65536,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x7b-instruct": {
id: "mistralai/mixtral-8x7b-instruct",
name: "Mistral: Mixtral 8x7B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.54,
output: 0.54,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"mistralai/pixtral-large-2411": {
id: "mistralai/pixtral-large-2411",
name: "Mistral: Pixtral Large 2411",
@@ -10341,23 +10324,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 163840,
} satisfies Model<"openai-completions">,
"nvidia/llama-3.1-nemotron-70b-instruct": {
id: "nvidia/llama-3.1-nemotron-70b-instruct",
name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 1.2,
output: 1.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -12963,13 +12929,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.38,
output: 1.74,
cacheRead: 0,
input: 0.39999999999999997,
output: 1.75,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 4096,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.7-flash": {
id: "z-ai/glm-4.7-flash",
@@ -13193,6 +13159,328 @@ export const MODELS = {
maxTokens: 128000,
} satisfies Model<"openai-completions">,
},
"together": {
"MiniMaxAI/MiniMax-M2.5": {
id: "MiniMaxAI/MiniMax-M2.5",
name: "MiniMax-M2.5",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"MiniMaxAI/MiniMax-M2.7": {
id: "MiniMaxAI/MiniMax-M2.7",
name: "MiniMax-M2.7",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
name: "Qwen3 235B A22B Instruct 2507 FP8",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
name: "Qwen3 Coder 480B A35B Instruct",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 2,
output: 2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-Next-FP8": {
id: "Qwen/Qwen3-Coder-Next-FP8",
name: "Qwen3 Coder Next FP8",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.5,
output: 1.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.5-397B-A17B": {
id: "Qwen/Qwen3.5-397B-A17B",
name: "Qwen3.5 397B A17B",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.6,
output: 3.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 130000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.6-Plus": {
id: "Qwen/Qwen3.6-Plus",
name: "Qwen3.6 Plus",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.5,
output: 3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 500000,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3": {
id: "deepseek-ai/DeepSeek-V3",
name: "DeepSeek V3",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 1.25,
output: 1.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3-1": {
id: "deepseek-ai/DeepSeek-V3-1",
name: "DeepSeek V3.1",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.6,
output: 1.7,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V4-Pro": {
id: "deepseek-ai/DeepSeek-V4-Pro",
name: "DeepSeek V4 Pro",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null},
input: ["text"],
cost: {
input: 2.1,
output: 4.4,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 512000,
maxTokens: 384000,
} satisfies Model<"openai-completions">,
"essentialai/Rnj-1-Instruct": {
id: "essentialai/Rnj-1-Instruct",
name: "Rnj-1 Instruct",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"google/gemma-4-31B-it": {
id: "google/gemma-4-31B-it",
name: "Gemma 4 31B Instruct",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
name: "Llama 3.3 70B",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.88,
output: 0.88,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.5": {
id: "moonshotai/Kimi-K2.5",
name: "Kimi K2.5",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.5,
output: 2.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.6": {
id: "moonshotai/Kimi-K2.6",
name: "Kimi K2.6",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 1.2,
output: 4.5,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131000,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
name: "GPT OSS 120B",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null},
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5.1": {
id: "zai-org/GLM-5.1",
name: "GLM-5.1",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
},
"vercel-ai-gateway": {
"alibaba/qwen-3-14b": {
id: "alibaba/qwen-3-14b",

28
packages/ai/src/providers/openai-completions.ts
View File

@@ -575,6 +575,15 @@ function buildParams(
} else if (model.thinkingLevelMap?.off !== null) {
openRouterParams.reasoning = { effort: model.thinkingLevelMap?.off ?? "none" };
}
} else if (compat.thinkingFormat === "together" && model.reasoning) {
const togetherParams = params as Omit<typeof params, "reasoning_effort"> & {
reasoning?: { enabled: boolean };
reasoning_effort?: string;
};
togetherParams.reasoning = { enabled: !!options?.reasoningEffort };
if (options?.reasoningEffort && compat.supportsReasoningEffort) {
togetherParams.reasoning_effort = model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;
}
} else if (options?.reasoningEffort && model.reasoning && compat.supportsReasoningEffort) {
// OpenAI-style reasoning_effort
(params as any).reasoning_effort = model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;
@@ -1050,6 +1059,8 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
const baseUrl = model.baseUrl;
const isZai = provider === "zai" || baseUrl.includes("api.z.ai");
const isTogether =
provider === "together" || baseUrl.includes("api.together.ai") || baseUrl.includes("api.together.xyz");
const isMoonshot = provider === "moonshotai" || provider === "moonshotai-cn" || baseUrl.includes("api.moonshot.");
const isCloudflareWorkersAI = provider === "cloudflare-workers-ai" || baseUrl.includes("api.cloudflare.com");
const isCloudflareAiGateway = provider === "cloudflare-ai-gateway" || baseUrl.includes("gateway.ai.cloudflare.com");
@@ -1059,6 +1070,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
baseUrl.includes("cerebras.ai") ||
provider === "xai" ||
baseUrl.includes("api.x.ai") ||
isTogether ||
baseUrl.includes("chutes.ai") ||
baseUrl.includes("deepseek.com") ||
isZai ||
@@ -1068,7 +1080,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
isCloudflareWorkersAI ||
isCloudflareAiGateway;
const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway;
const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether;
const isGrok = provider === "xai" || baseUrl.includes("api.x.ai");
const isDeepSeek = provider === "deepseek" || baseUrl.includes("deepseek.com");
@@ -1077,7 +1089,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
return {
supportsStore: !isNonStandard,
supportsDeveloperRole: !isNonStandard,
supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isCloudflareAiGateway,
supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway,
supportsUsageInStreaming: true,
maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
requiresToolResultName: false,
@@ -1088,16 +1100,18 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
? "deepseek"
: isZai
? "zai"
: provider === "openrouter" || baseUrl.includes("openrouter.ai")
? "openrouter"
: "openai",
: isTogether
? "together"
: provider === "openrouter" || baseUrl.includes("openrouter.ai")
? "openrouter"
: "openai",
openRouterRouting: {},
vercelGatewayRouting: {},
zaiToolStream: false,
supportsStrictMode: !isMoonshot && !isCloudflareAiGateway,
supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway,
cacheControlFormat,
sendSessionAffinityHeaders: false,
supportsLongCacheRetention: !(isCloudflareWorkersAI || isCloudflareAiGateway),
supportsLongCacheRetention: !(isTogether || isCloudflareWorkersAI || isCloudflareAiGateway),
};
}

5
packages/ai/src/types.ts
View File

@@ -43,6 +43,7 @@ export type KnownProvider =
| "moonshotai-cn"
| "huggingface"
| "fireworks"
| "together"
| "opencode"
| "opencode-go"
| "kimi-coding"
@@ -380,8 +381,8 @@ export interface OpenAICompletionsCompat {
requiresThinkingAsText?: boolean;
/** Whether all replayed assistant messages must include an empty reasoning_content field when reasoning is enabled. Default: auto-detected from URL. */
requiresReasoningContentOnAssistantMessages?: boolean;
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, and "qwen-chat-template" uses chat_template_kwargs.enable_thinking. Default: "openai". */
thinkingFormat?: "openai" | "openrouter" | "deepseek" | "zai" | "qwen" | "qwen-chat-template";
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, and "qwen-chat-template" uses chat_template_kwargs.enable_thinking. Default: "openai". */
thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "zai" | "qwen" | "qwen-chat-template";
/** OpenRouter-specific routing preferences. Only used when baseUrl points to OpenRouter. */
openRouterRouting?: OpenRouterRouting;
/** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */

3
packages/ai/src/utils/overflow.ts
View File

@@ -15,6 +15,7 @@ import type { AssistantMessage } from "../types.js";
* - xAI: "This model's maximum prompt length is 131072 but the request contains 537812 tokens"
* - Groq: "Please reduce the length of the messages or completion"
* - OpenRouter: "This endpoint's maximum context length is X tokens. However, you requested about Y tokens"
* - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
* - llama.cpp: "the request exceeds the available context size, try increasing it"
* - LM Studio: "tokens to keep from the initial prompt is greater than the context length"
* - GitHub Copilot: "prompt token count of X exceeds the limit of Y"
@@ -37,6 +38,7 @@ const OVERFLOW_PATTERNS = [
/maximum prompt length is \d+/i, // xAI (Grok)
/reduce the length of the messages/i, // Groq
/maximum context length is \d+ tokens/i, // OpenRouter (all backends)
/input \(\d+ tokens\) is longer than the model'?s context length \(\d+ tokens\)/i, // Together AI
/exceeds the limit of \d+/i, // GitHub Copilot
/exceeds the available context size/i, // llama.cpp server
/greater than the context length/i, // LM Studio
@@ -86,6 +88,7 @@ const NON_OVERFLOW_PATTERNS = [
* - Cerebras: 400/413 status code (no body)
* - Mistral: "Prompt contains X tokens ... too large for model with Y maximum context length"
* - OpenRouter (all backends): "maximum context length is X tokens"
* - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
* - llama.cpp: "exceeds the available context size"
* - LM Studio: "greater than the context length"
* - Kimi For Coding: "exceeded model token limit: X (requested: Y)"