mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-17 05:00:16 +00:00
Finalize OpenAI Codex compatibility (#737)
- align Codex Responses provider with Pi static instructions - simplify Codex request/stream handling and cleanup exports - keep legacy OpenCode Codex prompt for testing until Pi prompt is allowlisted
This commit is contained in:
Mario Zechner
GitHub
parent
3ed0d1bde7
commit
6484ae279d
17 changed files with 613 additions and 1779 deletions
|
|
@ -1723,24 +1723,6 @@ export const MODELS = {
|
|||
contextWindow: 128000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"oswe-vscode-prime": {
|
||||
id: "oswe-vscode-prime",
|
||||
name: "Raptor Mini (Preview)",
|
||||
api: "openai-responses",
|
||||
provider: "github-copilot",
|
||||
baseUrl: "https://api.individual.githubcopilot.com",
|
||||
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-responses">,
|
||||
},
|
||||
"google": {
|
||||
"gemini-1.5-flash": {
|
||||
|
|
@ -4434,23 +4416,6 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"allenai/olmo-3-7b-instruct": {
|
||||
id: "allenai/olmo-3-7b-instruct",
|
||||
name: "AllenAI: Olmo 3 7B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.09999999999999999,
|
||||
output: 0.19999999999999998,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 65536,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"allenai/olmo-3.1-32b-instruct": {
|
||||
id: "allenai/olmo-3.1-32b-instruct",
|
||||
name: "AllenAI: Olmo 3.1 32B Instruct",
|
||||
|
|
@ -5005,12 +4970,12 @@ export const MODELS = {
|
|||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.7,
|
||||
output: 2.4,
|
||||
output: 2.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 163840,
|
||||
contextWindow: 64000,
|
||||
maxTokens: 16000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek/deepseek-r1-0528": {
|
||||
id: "deepseek/deepseek-r1-0528",
|
||||
|
|
@ -5210,12 +5175,29 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.09999999999999999,
|
||||
output: 0.39999999999999997,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
cacheRead: 0.01,
|
||||
cacheWrite: 1,
|
||||
},
|
||||
contextWindow: 1048576,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"google/gemini-2.5-flash-preview-09-2025": {
|
||||
id: "google/gemini-2.5-flash-preview-09-2025",
|
||||
name: "Google: Gemini 2.5 Flash Preview 09-2025",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 2.5,
|
||||
cacheRead: 0.075,
|
||||
cacheWrite: 0.3833,
|
||||
},
|
||||
contextWindow: 1048576,
|
||||
maxTokens: 65535,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"google/gemini-2.5-pro": {
|
||||
id: "google/gemini-2.5-pro",
|
||||
name: "Google: Gemini 2.5 Pro",
|
||||
|
|
@ -5386,23 +5368,6 @@ export const MODELS = {
|
|||
contextWindow: 256000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3-70b-instruct": {
|
||||
id: "meta-llama/llama-3-70b-instruct",
|
||||
name: "Meta: Llama 3 70B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 0.39999999999999997,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8192,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3-8b-instruct": {
|
||||
id: "meta-llama/llama-3-8b-instruct",
|
||||
name: "Meta: Llama 3 8B Instruct",
|
||||
|
|
@ -5667,12 +5632,12 @@ export const MODELS = {
|
|||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.07,
|
||||
output: 0.28,
|
||||
input: 0.09999999999999999,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
contextWindow: 131072,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/ministral-14b-2512": {
|
||||
|
|
@ -5760,40 +5725,6 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-7b-instruct": {
|
||||
id: "mistralai/mistral-7b-instruct",
|
||||
name: "Mistral: Mistral 7B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.028,
|
||||
output: 0.054,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32768,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-7b-instruct:free": {
|
||||
id: "mistralai/mistral-7b-instruct:free",
|
||||
name: "Mistral: Mistral 7B Instruct (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32768,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-large": {
|
||||
id: "mistralai/mistral-large",
|
||||
name: "Mistral Large",
|
||||
|
|
@ -5911,7 +5842,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 16384,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-saba": {
|
||||
id: "mistralai/mistral-saba",
|
||||
|
|
@ -7290,108 +7221,6 @@ export const MODELS = {
|
|||
contextWindow: 32768,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-max": {
|
||||
id: "qwen/qwen-max",
|
||||
name: "Qwen: Qwen-Max ",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.5999999999999999,
|
||||
output: 6.3999999999999995,
|
||||
cacheRead: 0.64,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32768,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-plus": {
|
||||
id: "qwen/qwen-plus",
|
||||
name: "Qwen: Qwen-Plus",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 1.2,
|
||||
cacheRead: 0.16,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-plus-2025-07-28": {
|
||||
id: "qwen/qwen-plus-2025-07-28",
|
||||
name: "Qwen: Qwen Plus 0728",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-plus-2025-07-28:thinking": {
|
||||
id: "qwen/qwen-plus-2025-07-28:thinking",
|
||||
name: "Qwen: Qwen Plus 0728 (thinking)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-turbo": {
|
||||
id: "qwen/qwen-turbo",
|
||||
name: "Qwen: Qwen-Turbo",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.049999999999999996,
|
||||
output: 0.19999999999999998,
|
||||
cacheRead: 0.02,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-vl-max": {
|
||||
id: "qwen/qwen-vl-max",
|
||||
name: "Qwen: Qwen VL Max",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.7999999999999999,
|
||||
output: 3.1999999999999997,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-14b": {
|
||||
id: "qwen/qwen3-14b",
|
||||
name: "Qwen: Qwen3 14B",
|
||||
|
|
@ -7418,13 +7247,13 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.18,
|
||||
output: 0.54,
|
||||
input: 0.19999999999999998,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 40960,
|
||||
maxTokens: 40960,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-235b-a22b-2507": {
|
||||
id: "qwen/qwen3-235b-a22b-2507",
|
||||
|
|
@ -7596,40 +7425,6 @@ export const MODELS = {
|
|||
contextWindow: 160000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-coder-flash": {
|
||||
id: "qwen/qwen3-coder-flash",
|
||||
name: "Qwen: Qwen3 Coder Flash",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.5,
|
||||
cacheRead: 0.08,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-coder-plus": {
|
||||
id: "qwen/qwen3-coder-plus",
|
||||
name: "Qwen: Qwen3 Coder Plus",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 5,
|
||||
cacheRead: 0.09999999999999999,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-coder:exacto": {
|
||||
id: "qwen/qwen3-coder:exacto",
|
||||
name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
|
||||
|
|
@ -7664,23 +7459,6 @@ export const MODELS = {
|
|||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-max": {
|
||||
id: "qwen/qwen3-max",
|
||||
name: "Qwen: Qwen3 Max",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.2,
|
||||
output: 6,
|
||||
cacheRead: 0.24,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-next-80b-a3b-instruct": {
|
||||
id: "qwen/qwen3-next-80b-a3b-instruct",
|
||||
name: "Qwen: Qwen3 Next 80B A3B Instruct",
|
||||
|
|
@ -7698,6 +7476,23 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-next-80b-a3b-instruct:free": {
|
||||
id: "qwen/qwen3-next-80b-a3b-instruct:free",
|
||||
name: "Qwen: Qwen3 Next 80B A3B Instruct (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-next-80b-a3b-thinking": {
|
||||
id: "qwen/qwen3-next-80b-a3b-thinking",
|
||||
name: "Qwen: Qwen3 Next 80B A3B Thinking",
|
||||
|
|
@ -7800,23 +7595,6 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-vl-8b-thinking": {
|
||||
id: "qwen/qwen3-vl-8b-thinking",
|
||||
name: "Qwen: Qwen3 VL 8B Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.18,
|
||||
output: 2.0999999999999996,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwq-32b": {
|
||||
id: "qwen/qwq-32b",
|
||||
name: "Qwen: QwQ 32B",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue