ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge main into model-registry

Browse Source
This commit is contained in:
Mario Zechner
2026-06-22 14:00:18 +02:00
parent 019b022068 717a8f958a
commit abbd911693
220 changed files with 10488 additions and 4354 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/together.models.ts
+107 -109
View File
@@ -4,25 +4,6 @@
import type { Model } from "../types.ts";
export const TOGETHER_MODELS = {
"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,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"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",
@@ -42,28 +23,28 @@ export const TOGETHER_MODELS = {
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",
"MiniMaxAI/MiniMax-M3": {
id: "MiniMaxAI/MiniMax-M3",
name: "MiniMax-M3",
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"],
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.6,
cacheRead: 0,
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 524288,
maxTokens: 250000,
} 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",
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
name: "Qwen 2.5 7B Instruct Turbo",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
@@ -71,27 +52,26 @@ export const TOGETHER_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 2,
output: 2,
input: 0.3,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 32768,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-Next-FP8": {
id: "Qwen/Qwen3-Coder-Next-FP8",
name: "Qwen3 Coder Next FP8",
"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},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.5,
output: 1.2,
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
@@ -117,6 +97,25 @@ export const TOGETHER_MODELS = {
contextWindow: 262144,
maxTokens: 130000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.5-9B": {
id: "Qwen/Qwen3.5-9B",
name: "Qwen3.5 9B",
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: 0.17,
output: 0.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.6-Plus": {
id: "Qwen/Qwen3.6-Plus",
name: "Qwen3.6 Plus",
@@ -142,57 +141,18 @@ export const TOGETHER_MODELS = {
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},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 2.5,
output: 7.5,
input: 1.25,
output: 3.75,
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",
@@ -204,8 +164,8 @@ export const TOGETHER_MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null},
input: ["text"],
cost: {
input: 2.1,
output: 4.4,
input: 1.74,
output: 3.48,
cacheRead: 0.2,
cacheWrite: 0,
},
@@ -241,8 +201,8 @@ export const TOGETHER_MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.5,
input: 0.39,
output: 0.97,
cacheRead: 0,
cacheWrite: 0,
},
@@ -267,25 +227,6 @@ export const TOGETHER_MODELS = {
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",
@@ -305,6 +246,25 @@ export const TOGETHER_MODELS = {
contextWindow: 262144,
maxTokens: 131000,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.7-Code": {
id: "moonshotai/Kimi-K2.7-Code",
name: "Kimi K2.7 Code",
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: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b": {
id: "nvidia/nemotron-3-ultra-550b-a55b",
name: "Nemotron 3 Ultra 550B A55B",
@@ -343,6 +303,44 @@ export const TOGETHER_MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "GPT OSS 20B",
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: 0.05,
output: 0.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5": {
id: "zai-org/GLM-5",
name: "GLM-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"],
cost: {
input: 1,
output: 3.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5.1": {
id: "zai-org/GLM-5.1",
name: "GLM-5.1",