Skip to content

[Feat] Add verified GPT-6 Astra support across providers #1506

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

Merged
navedmerchant merged 5 commits into from
Sep 4, 2026
Merged

[Feat] Add verified GPT-6 Astra support across providers #1506

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1533550
feat(api): add verified GPT-6 Astra support
taltas Sep 3, 2026
fd5a254
Merge branch 'main' into feature/gpt-6-astra-support-050bt7298qbsg
navedmerchant Sep 4, 2026
8cd0f44
test(api): cover Astra request guards
navedmerchant Sep 4, 2026
033812b
feat(api): add GPT-6 Astra to Codex
navedmerchant Sep 4, 2026
2ba7b68
feat(api): support Astra on verified gateways
navedmerchant Sep 4, 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
72 changes: 72 additions & 0 deletions packages/types/src/__tests__/openai-models.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
import { openAiNativeDefaultModelId, openAiNativeModels } from "../providers/openai.js"

describe("OpenAI native models", () => {
it("describes GPT-6 Astra without changing the provider default", () => {
expect(openAiNativeDefaultModelId).toBe("gpt-5.6-sol")
expect(openAiNativeModels["gpt-6-astra"]).toMatchObject({
maxTokens: 128_000,
contextWindow: 1_050_000,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["low", "medium", "high", "xhigh", "max"],
requiredReasoningEffort: true,
reasoningEffort: "medium",
supportsTemperature: false,
inputPrice: 10,
cacheWritesPrice: 12.5,
cacheReadsPrice: 1,
outputPrice: 50,
longContextPricing: {
thresholdTokens: 272_000,
inputPriceMultiplier: 2,
outputPriceMultiplier: 1.5,
cacheWritesPriceMultiplier: 2,
cacheReadsPriceMultiplier: 2,
appliesToServiceTiers: ["default", "flex", "priority"],
},
})

expect(openAiNativeModels["gpt-6-astra"].tiers).toEqual([
{
name: "flex",
contextWindow: 1_050_000,
inputPrice: 5,
outputPrice: 25,
cacheWritesPrice: 6.25,
cacheReadsPrice: 0.5,
},
{
name: "priority",
contextWindow: 1_050_000,
inputPrice: 20,
outputPrice: 100,
cacheWritesPrice: 25,
cacheReadsPrice: 2,
},
])
})

it("uses current GPT-5.6 base pricing and context metadata", () => {
expect(openAiNativeModels["gpt-5.6-sol"]).toMatchObject({
contextWindow: 1_050_000,
inputPrice: 4,
cacheWritesPrice: 5,
cacheReadsPrice: 0.4,
outputPrice: 20,
})
expect(openAiNativeModels["gpt-5.6-terra"]).toMatchObject({
contextWindow: 1_050_000,
inputPrice: 2,
cacheWritesPrice: 2.5,
cacheReadsPrice: 0.2,
outputPrice: 12,
})
expect(openAiNativeModels["gpt-5.6-luna"]).toMatchObject({
contextWindow: 1_050_000,
inputPrice: 0.2,
cacheWritesPrice: 0.25,
cacheReadsPrice: 0.02,
outputPrice: 1.2,
})
})
})
2 changes: 2 additions & 0 deletions packages/types/src/model.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,6 +127,8 @@ export const modelInfoSchema = z.object({
.optional(),
requiredReasoningEffort: z.boolean().optional(),
preserveReasoning: z.boolean().optional(),
// Some OpenAI-compatible gateways require a Responses-backed route for tool calls.
requiresResponsesApi: z.boolean().optional(),
supportedParameters: z.array(modelParametersSchema).optional(),
inputPrice: z.number().optional(),
outputPrice: z.number().optional(),
Expand Down
16 changes: 16 additions & 0 deletions packages/types/src/providers/openai-codex.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,22 @@ export const openAiCodexDefaultModelId: OpenAiCodexModelId = "gpt-5.6-sol"
* Costs are 0 as they are covered by the subscription.
*/
export const openAiCodexModels = {
"gpt-6-astra": {
maxTokens: 128000,
contextWindow: 872000,
includedTools: ["apply_patch"],
excludedTools: ["apply_diff", "write_to_file"],
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["low", "medium", "high", "xhigh", "max"],
requiredReasoningEffort: true,
reasoningEffort: "low",
inputPrice: 0,
outputPrice: 0,
supportsVerbosity: true,
supportsTemperature: false,
description: "GPT-6 Astra: OpenAI's most capable model for complex, demanding work via ChatGPT subscription",
},
"gpt-5.6-sol": {
maxTokens: 128000,
contextWindow: 372000,
Expand Down
140 changes: 120 additions & 20 deletions packages/types/src/providers/openai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,49 @@ export const OPENAI_API_PROTOCOL = "openai"
export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5.6-sol"

export const openAiNativeModels = {
"gpt-6-astra": {
maxTokens: 128000,
contextWindow: 1_050_000,
includedTools: ["apply_patch"],
excludedTools: ["apply_diff", "write_to_file"],
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["low", "medium", "high", "xhigh", "max"],
requiredReasoningEffort: true,
reasoningEffort: "medium",
inputPrice: 10.0,
outputPrice: 50.0,
cacheWritesPrice: 12.5,
cacheReadsPrice: 1.0,
longContextPricing: {
thresholdTokens: 272_000,
inputPriceMultiplier: 2,
outputPriceMultiplier: 1.5,
cacheWritesPriceMultiplier: 2,
cacheReadsPriceMultiplier: 2,
appliesToServiceTiers: ["default", "flex", "priority"],
},
supportsTemperature: false,
tiers: [
{
name: "flex",
contextWindow: 1_050_000,
inputPrice: 5.0,
outputPrice: 25.0,
cacheWritesPrice: 6.25,
cacheReadsPrice: 0.5,
},
{
name: "priority",
contextWindow: 1_050_000,
inputPrice: 20.0,
outputPrice: 100.0,
cacheWritesPrice: 25.0,
cacheReadsPrice: 2.0,
},
],
description: "GPT-6 Astra: OpenAI's most capable model for complex reasoning and end-to-end agentic work",
},
"gpt-5.6-sol": {
maxTokens: 128000,
contextWindow: 1_050_000,
Expand All @@ -26,21 +69,37 @@ export const openAiNativeModels = {
supportsPromptCache: true,
supportsReasoningEffort: ["none", "low", "medium", "high", "xhigh", "max"],
reasoningEffort: "medium",
inputPrice: 5.0,
outputPrice: 30.0,
cacheWritesPrice: 6.25,
cacheReadsPrice: 0.5,
inputPrice: 4.0,
outputPrice: 20.0,
cacheWritesPrice: 5.0,
cacheReadsPrice: 0.4,
longContextPricing: {
thresholdTokens: 272_000,
inputPriceMultiplier: 2,
outputPriceMultiplier: 1.5,
appliesToServiceTiers: ["default", "flex"],
cacheWritesPriceMultiplier: 2,
cacheReadsPriceMultiplier: 2,
appliesToServiceTiers: ["default", "flex", "priority"],
},
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 1_050_000, inputPrice: 2.5, outputPrice: 15.0, cacheReadsPrice: 0.25 },
{ name: "priority", contextWindow: 1_050_000, inputPrice: 12.5, outputPrice: 75.0, cacheReadsPrice: 1.25 },
{
name: "flex",
contextWindow: 1_050_000,
inputPrice: 2.0,
outputPrice: 10.0,
cacheWritesPrice: 2.5,
cacheReadsPrice: 0.2,
},
{
name: "priority",
contextWindow: 1_050_000,
inputPrice: 8.0,
outputPrice: 40.0,
cacheWritesPrice: 10.0,
cacheReadsPrice: 0.8,
},
],
description: "GPT-5.6 Sol: OpenAI's flagship model for frontier reasoning, coding, and agentic workflows",
},
Expand All @@ -53,40 +112,81 @@ export const openAiNativeModels = {
supportsPromptCache: true,
supportsReasoningEffort: ["none", "low", "medium", "high", "xhigh", "max"],
reasoningEffort: "medium",
inputPrice: 2.5,
outputPrice: 15.0,
cacheWritesPrice: 3.125,
cacheReadsPrice: 0.25,
inputPrice: 2.0,
outputPrice: 12.0,
cacheWritesPrice: 2.5,
cacheReadsPrice: 0.2,
longContextPricing: {
thresholdTokens: 272_000,
inputPriceMultiplier: 2,
outputPriceMultiplier: 1.5,
appliesToServiceTiers: ["default", "flex"],
cacheWritesPriceMultiplier: 2,
cacheReadsPriceMultiplier: 2,
appliesToServiceTiers: ["default", "flex", "priority"],
},
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 1_050_000, inputPrice: 1.25, outputPrice: 7.5, cacheReadsPrice: 0.125 },
{ name: "priority", contextWindow: 1_050_000, inputPrice: 6.25, outputPrice: 37.5, cacheReadsPrice: 0.625 },
{
name: "flex",
contextWindow: 1_050_000,
inputPrice: 1.0,
outputPrice: 6.0,
cacheWritesPrice: 1.25,
cacheReadsPrice: 0.1,
},
{
name: "priority",
contextWindow: 1_050_000,
inputPrice: 4.0,
outputPrice: 24.0,
cacheWritesPrice: 5.0,
cacheReadsPrice: 0.4,
},
],
description: "GPT-5.6 Terra: Balanced everyday model with GPT-5.5-competitive performance at 2x lower cost",
},
"gpt-5.6-luna": {
maxTokens: 128000,
contextWindow: 400000,
contextWindow: 1_050_000,
includedTools: ["apply_patch"],
excludedTools: ["apply_diff", "write_to_file"],
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["none", "low", "medium", "high", "xhigh", "max"],
reasoningEffort: "medium",
inputPrice: 1.0,
outputPrice: 6.0,
cacheWritesPrice: 1.25,
cacheReadsPrice: 0.1,
inputPrice: 0.2,
outputPrice: 1.2,
cacheWritesPrice: 0.25,
cacheReadsPrice: 0.02,
longContextPricing: {
thresholdTokens: 272_000,
inputPriceMultiplier: 2,
outputPriceMultiplier: 1.5,
cacheWritesPriceMultiplier: 2,
cacheReadsPriceMultiplier: 2,
appliesToServiceTiers: ["default", "flex", "priority"],
},
supportsVerbosity: true,
supportsTemperature: false,
tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.5, outputPrice: 3.0, cacheReadsPrice: 0.05 }],
tiers: [
{
name: "flex",
contextWindow: 1_050_000,
inputPrice: 0.1,
outputPrice: 0.6,
cacheWritesPrice: 0.125,
cacheReadsPrice: 0.01,
},
{
name: "priority",
contextWindow: 1_050_000,
inputPrice: 0.4,
outputPrice: 2.4,
cacheWritesPrice: 0.5,
cacheReadsPrice: 0.04,
},
],
description: "GPT-5.6 Luna: The fastest, most affordable member of the GPT-5.6 family",
},
"gpt-5.1-codex-max": {
Expand Down
Loading
Loading