@@ -21,31 +21,6 @@ export const opencodeGoDefaultModelInfo: ModelInfo = {
2121
2222export const OPENCODE_GO_DEFAULT_TEMPERATURE = 0
2323
24- /**
25- * Limits for Go models that do not yet have a full native configuration below.
26- *
27- * The Go `/v1/models` endpoint currently returns only model IDs, so these
28- * values prevent newly listed models from inheriting the generic 200k context
29- * window. Keep this table aligned with the endpoint and models.dev metadata.
30- */
31- export const opencodeGoModelLimits : Record < string , Pick < ModelInfo , "contextWindow" | "maxTokens" > > = {
32- "kimi-k2.7-code" : { contextWindow : 262_144 , maxTokens : 262_144 } ,
33- "longcat-2.0" : { contextWindow : 1_000_000 , maxTokens : 131_072 } ,
34- "glm-5.3-flash" : { contextWindow : 1_000_000 , maxTokens : 131_072 } ,
35- "deepseek-v4-flash-vision-exp" : { contextWindow : 1_000_000 , maxTokens : 384_000 } ,
36- "qwen3.8-flash" : { contextWindow : 1_000_000 , maxTokens : 131_072 } ,
37- "qwen3.5-plus" : { contextWindow : 262_144 , maxTokens : 65_536 } ,
38- "mimo-v2-pro" : { contextWindow : 1_048_576 , maxTokens : 128_000 } ,
39- "mimo-v2-omni" : { contextWindow : 262_144 , maxTokens : 128_000 } ,
40- "hy4-preview" : { contextWindow : 1_024_000 , maxTokens : 64_000 } ,
41- hy3 : { contextWindow : 256_000 , maxTokens : 64_000 } ,
42- "hy3-preview" : { contextWindow : 256_000 , maxTokens : 64_000 } ,
43- "gpt-5.6-luna" : { contextWindow : 1_050_000 , maxTokens : 128_000 } ,
44- "grok-4.5" : { contextWindow : 500_000 , maxTokens : 500_000 } ,
45- "grok-4.6" : { contextWindow : 500_000 , maxTokens : 500_000 } ,
46- "muse-spark-1.2-contributor" : { contextWindow : 1_048_576 , maxTokens : 131_072 } ,
47- }
48-
4924/**
5025 * Native per-model configuration for the Opencode Go plan.
5126 *
@@ -127,6 +102,21 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
127102 description :
128103 "GLM-5.3 is Zhipu's flagship coding and agent model with a 1M context window, 128k max output, and always-on reasoning with configurable effort (Low/High/Max). Available via the Opencode Go plan." ,
129104 } ,
105+ "glm-5.3-flash" : {
106+ maxTokens : 131_072 ,
107+ contextWindow : 1_000_000 ,
108+ supportsImages : true ,
109+ supportsPromptCache : true ,
110+ supportsMaxTokens : true ,
111+ supportsReasoningEffort : [ "low" , "high" , "max" ] ,
112+ reasoningEffort : "max" ,
113+ preserveReasoning : true ,
114+ inputPrice : 0.075 ,
115+ outputPrice : 0.25 ,
116+ cacheReadsPrice : 0.015 ,
117+ description :
118+ "GLM-5.3 Flash is Zhipu's fast multimodal coding and agent model with a 1M context window and configurable reasoning effort. Available via the Opencode Go plan." ,
119+ } ,
130120 "glm-5.2" : {
131121 maxTokens : 131_072 ,
132122 contextWindow : 1_000_000 ,
@@ -188,6 +178,36 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
188178 description :
189179 "Kimi K2.6 is Moonshot AI's native multimodal agentic MoE model with a 256k context window, built for long-horizon coding and tool use. Available via the Opencode Go plan." ,
190180 } ,
181+ "kimi-k2.7-code" : {
182+ maxTokens : 262_144 ,
183+ contextWindow : 262_144 ,
184+ supportsImages : true ,
185+ supportsPromptCache : true ,
186+ supportsMaxTokens : true ,
187+ preserveReasoning : true ,
188+ defaultTemperature : 1.0 ,
189+ inputPrice : 0.95 ,
190+ outputPrice : 4.0 ,
191+ cacheReadsPrice : 0.19 ,
192+ description :
193+ "Kimi K2.7 Code is Moonshot AI's coding model for long-context programming tasks, with multimodal input and a 256k context window. Available via the Opencode Go plan." ,
194+ } ,
195+
196+ // --- Meituan LongCat ---
197+ "longcat-2.0" : {
198+ maxTokens : 131_072 ,
199+ contextWindow : 1_000_000 ,
200+ supportsImages : false ,
201+ supportsPromptCache : true ,
202+ supportsMaxTokens : true ,
203+ supportsReasoningBinary : true ,
204+ preserveReasoning : true ,
205+ inputPrice : 0.3 ,
206+ outputPrice : 1.2 ,
207+ cacheReadsPrice : 0.006 ,
208+ description :
209+ "LongCat 2.0 is Meituan's long-context reasoning and coding model with a 1M context window. Available via the Opencode Go plan." ,
210+ } ,
191211
192212 // --- Xiaomi MiMo ---
193213 "mimo-v2.5" : {
@@ -226,6 +246,36 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
226246 description :
227247 "MiMo V2.5 Pro - Xiaomi's flagship reasoning model with 1M context, deep thinking, and tool calling. Available via the Opencode Go plan." ,
228248 } ,
249+ "mimo-v2-pro" : {
250+ maxTokens : 128_000 ,
251+ contextWindow : 1_048_576 ,
252+ supportsImages : false ,
253+ supportsPromptCache : false ,
254+ preserveReasoning : true ,
255+ inputPrice : 1.0 ,
256+ outputPrice : 3.0 ,
257+ cacheReadsPrice : 0.2 ,
258+ longContextPricing : {
259+ thresholdTokens : 256_000 ,
260+ inputPriceMultiplier : 2 ,
261+ outputPriceMultiplier : 2 ,
262+ cacheReadsPriceMultiplier : 2 ,
263+ } ,
264+ description :
265+ "MiMo V2 Pro is Xiaomi's text reasoning and coding model with a 1M context window. Available via the Opencode Go plan." ,
266+ } ,
267+ "mimo-v2-omni" : {
268+ maxTokens : 128_000 ,
269+ contextWindow : 262_144 ,
270+ supportsImages : true ,
271+ supportsPromptCache : false ,
272+ preserveReasoning : true ,
273+ inputPrice : 0.4 ,
274+ outputPrice : 2.0 ,
275+ cacheReadsPrice : 0.08 ,
276+ description :
277+ "MiMo V2 Omni is Xiaomi's multimodal reasoning model with a 256k context window. Available via the Opencode Go plan." ,
278+ } ,
229279
230280 // --- MiniMax ---
231281 "minimax-m2.5" : {
@@ -280,6 +330,21 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
280330 } ,
281331
282332 // --- Alibaba Qwen ---
333+ "qwen3.5-plus" : {
334+ maxTokens : 65_536 ,
335+ contextWindow : 262_144 ,
336+ supportsImages : true ,
337+ supportsPromptCache : true ,
338+ supportsReasoningBudget : true ,
339+ supportsReasoningBinary : true ,
340+ preserveReasoning : true ,
341+ inputPrice : 0.2 ,
342+ outputPrice : 1.2 ,
343+ cacheReadsPrice : 0.02 ,
344+ cacheWritesPrice : 0.25 ,
345+ description :
346+ "Qwen3.5 Plus is Alibaba's multimodal reasoning model with a 256k context window. Available via the Opencode Go plan." ,
347+ } ,
283348 "qwen3.6-plus" : {
284349 maxTokens : 65_536 ,
285350 contextWindow : 1_000_000 ,
@@ -346,6 +411,22 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
346411 description :
347412 "Qwen3.8 Max - Alibaba's flagship multimodal reasoning model with a 1M context window, 128k max output, and long-horizon coding and agentic capabilities. Available via the Opencode Go plan." ,
348413 } ,
414+ "qwen3.8-flash" : {
415+ maxTokens : 131_072 ,
416+ contextWindow : 1_000_000 ,
417+ supportsImages : true ,
418+ supportsPromptCache : true ,
419+ supportsMaxTokens : true ,
420+ supportsReasoningBudget : true ,
421+ supportsReasoningBinary : true ,
422+ preserveReasoning : true ,
423+ inputPrice : 0.15 ,
424+ outputPrice : 0.47 ,
425+ cacheReadsPrice : 0.016 ,
426+ cacheWritesPrice : 0.2 ,
427+ description :
428+ "Qwen3.8 Flash is Alibaba's fast multimodal reasoning model with a 1M context window. Available via the Opencode Go plan." ,
429+ } ,
349430
350431 // --- DeepSeek ---
351432 "deepseek-v4-pro" : {
@@ -384,6 +465,70 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
384465 description :
385466 "DeepSeek-V4-Flash is DeepSeek's fast, cost-efficient V4 model supporting thinking and non-thinking modes. Available via the Opencode Go plan." ,
386467 } ,
468+ "deepseek-v4-flash-vision-exp" : {
469+ maxTokens : 384_000 ,
470+ contextWindow : 1_000_000 ,
471+ supportsImages : true ,
472+ supportsPromptCache : true ,
473+ supportsMaxTokens : true ,
474+ supportsReasoningEffort : [ "disable" , "low" , "high" , "max" ] ,
475+ reasoningEffort : "high" ,
476+ preserveReasoning : true ,
477+ inputPrice : 0.22 ,
478+ outputPrice : 0.66 ,
479+ cacheReadsPrice : 0.007 ,
480+ description :
481+ "DeepSeek V4 Flash Vision Experimental is a fast multimodal reasoning model with a 1M context window. Available via the Opencode Go plan." ,
482+ } ,
483+
484+ // --- Tencent Hunyuan ---
485+ "hy4-preview" : {
486+ maxTokens : 64_000 ,
487+ contextWindow : 1_024_000 ,
488+ supportsImages : false ,
489+ supportsPromptCache : true ,
490+ supportsMaxTokens : true ,
491+ supportsReasoningEffort : [ "disable" , "high" ] ,
492+ reasoningEffort : "high" ,
493+ preserveReasoning : true ,
494+ inputPrice : 0.834 ,
495+ outputPrice : 2.501 ,
496+ cacheReadsPrice : 0.042 ,
497+ description :
498+ "Hunyuan 4 Preview is Tencent's long-context reasoning and coding model with a 1M context window. Available via the Opencode Go plan." ,
499+ } ,
500+ hy3 : {
501+ maxTokens : 64_000 ,
502+ contextWindow : 256_000 ,
503+ supportsImages : false ,
504+ supportsPromptCache : true ,
505+ supportsMaxTokens : true ,
506+ supportsReasoningEffort : [ "disable" , "low" , "high" ] ,
507+ reasoningEffort : "high" ,
508+ preserveReasoning : true ,
509+ inputPrice : 0.0175 ,
510+ outputPrice : 0.0725 ,
511+ cacheReadsPrice : 0.004375 ,
512+ description :
513+ "Hunyuan 3 is Tencent's reasoning and coding model with a 256k context window. Available via the Opencode Go plan." ,
514+ } ,
515+ "hy3-preview" : {
516+ // The live endpoint still lists this historical alias; it shares HY3's limits and pricing.
517+ maxTokens : 64_000 ,
518+ contextWindow : 256_000 ,
519+ supportsImages : false ,
520+ supportsPromptCache : true ,
521+ supportsMaxTokens : true ,
522+ supportsReasoningEffort : [ "disable" , "low" , "high" ] ,
523+ reasoningEffort : "high" ,
524+ preserveReasoning : true ,
525+ inputPrice : 0.0175 ,
526+ outputPrice : 0.0725 ,
527+ cacheReadsPrice : 0.004375 ,
528+ description :
529+ "Hunyuan 3 Preview is Tencent's preview reasoning and coding model with a 256k context window. Available via the Opencode Go plan." ,
530+ } ,
531+
387532 // --- OpenAI Responses ---
388533 // Luna is curated here because the Go gateway's model catalogue does not
389534 // currently provide its capability metadata. These values intentionally
@@ -393,6 +538,7 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
393538 contextWindow : 1_050_000 ,
394539 supportsImages : true ,
395540 supportsPromptCache : true ,
541+ supportsMaxTokens : true ,
396542 supportsReasoningEffort : [ "none" , "low" , "medium" , "high" , "xhigh" , "max" ] ,
397543 reasoningEffort : "medium" ,
398544 inputPrice : 0.2 ,
@@ -406,7 +552,62 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
406552 cacheWritesPriceMultiplier : 2 ,
407553 cacheReadsPriceMultiplier : 2 ,
408554 } ,
409- description : "GPT-5.6 Luna via the OpenCode Go Responses API." ,
555+ description :
556+ "GPT-5.6 Luna is OpenAI's fast reasoning model with a 1M context window. Available via the Opencode Go plan." ,
557+ } ,
558+ "grok-4.5" : {
559+ maxTokens : 500_000 ,
560+ contextWindow : 500_000 ,
561+ supportsImages : true ,
562+ supportsPromptCache : true ,
563+ supportsMaxTokens : true ,
564+ supportsReasoningEffort : [ "low" , "medium" , "high" ] ,
565+ reasoningEffort : "high" ,
566+ inputPrice : 2.0 ,
567+ outputPrice : 6.0 ,
568+ cacheReadsPrice : 0.3 ,
569+ longContextPricing : {
570+ thresholdTokens : 200_000 ,
571+ inputPriceMultiplier : 2 ,
572+ outputPriceMultiplier : 2 ,
573+ cacheReadsPriceMultiplier : 2 ,
574+ } ,
575+ description :
576+ "Grok 4.5 is xAI's multimodal reasoning and agent model with a 500k context window. Available via the Opencode Go plan." ,
577+ } ,
578+ "grok-4.6" : {
579+ maxTokens : 500_000 ,
580+ contextWindow : 500_000 ,
581+ supportsImages : true ,
582+ supportsPromptCache : true ,
583+ supportsMaxTokens : true ,
584+ supportsReasoningEffort : [ "low" , "medium" , "high" , "xhigh" ] ,
585+ reasoningEffort : "high" ,
586+ inputPrice : 2.0 ,
587+ outputPrice : 6.0 ,
588+ cacheReadsPrice : 0.5 ,
589+ longContextPricing : {
590+ thresholdTokens : 200_000 ,
591+ inputPriceMultiplier : 2 ,
592+ outputPriceMultiplier : 2 ,
593+ cacheReadsPriceMultiplier : 2 ,
594+ } ,
595+ description :
596+ "Grok 4.6 is xAI's multimodal reasoning and agent model with a 500k context window. Available via the Opencode Go plan." ,
597+ } ,
598+ "muse-spark-1.2-contributor" : {
599+ maxTokens : 131_072 ,
600+ contextWindow : 1_048_576 ,
601+ supportsImages : true ,
602+ supportsPromptCache : true ,
603+ supportsMaxTokens : true ,
604+ supportsReasoningEffort : [ "minimal" , "low" , "medium" , "high" , "xhigh" ] ,
605+ reasoningEffort : "medium" ,
606+ inputPrice : 0.1 ,
607+ outputPrice : 0.2 ,
608+ cacheReadsPrice : 0.002 ,
609+ description :
610+ "Muse Spark 1.2 Contributor is Meta's multimodal coding model with a 1M context window. Available via the Opencode Go plan." ,
410611 } ,
411612}
412613
@@ -429,6 +630,7 @@ export const opencodeGoModels: Record<string, ModelInfo> = {
429630export const OPENCODE_GO_ANTHROPIC_FORMAT_MODELS = new Set < string > ( [
430631 // --- Alibaba Qwen ---
431632 "qwen3.8-max" ,
633+ "qwen3.8-flash" ,
432634 "qwen3.7-max" ,
433635 "qwen3.7-plus" ,
434636 "qwen3.6-plus" ,
@@ -488,11 +690,3 @@ export function isOpencodeGoResponsesFormatModel(modelId: string): boolean {
488690export function getOpencodeGoModelInfo ( modelId : string ) : ModelInfo | undefined {
489691 return opencodeGoModels [ modelId ]
490692}
491-
492- /** Returns explicit model limits when Go omits them from `/v1/models`. */
493- export function getOpencodeGoModelLimits ( modelId : string ) : Pick < ModelInfo , "contextWindow" | "maxTokens" > | undefined {
494- const native = getOpencodeGoModelInfo ( modelId )
495- return native
496- ? { contextWindow : native . contextWindow , maxTokens : native . maxTokens }
497- : opencodeGoModelLimits [ modelId ]
498- }
0 commit comments