OpenCode Go
A platform providing API access services for large models, offering developers low-cost model invocation channels through discounted pricing strategies.
Core Facts
Muse Spark can be used as a backend via OpenCode Go.
The default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.
Timeline (last 90 days)
OpenCode Go kept and pinned the base URL https://opencode.ai/inference/go/v1 because models.dev migrated the provider-level URL to an OpenAI-only path; without pinning, requests would hit an incompatible endpoint.
OpenCode Go no longer lists MiniMax M2.7.
The default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.
The Cline recommendation list adds Gemini 4 Argon and removes Grok 4.7; the free list replaces Step 5 Preview with Nemotron 3.5 Super VL; OpenCode Go no longer lists MiniMax M2.7.
OpenCode added Gemini 4 Argon to OpenCode Go on October 14, launching a promotion of '$60 of usage for $10 before November 30'.
In v4.1.24, OpenCode Go switched to the new inference endpoint https://opencode.ai/inference/go/v1.
v3.0.71's model catalog adds three providers: AI/ML API, LowRouter and Prime Inference; the v0 provider is streamlined to provide only the default model `v0-1.5-md`; OpenCode Go migrates to the new endpoint `https://opencode.ai/inference/go/v1`; and Step 5 Preview is added to the Cline free list.
Muse Spark can be used as a backend via OpenCode Go.
In the test, the cache hit rates for Ollama and OpenCode Go were 97.2% and 99.5%, respectively.
OpenCode's Go plan is priced at $10/month, half the price of Ollama's legacy plan.
19 more timeline events
All Facts (14)
Muse Spark can be used as a backend via OpenCode Go.
85%Partially VerifiedThe default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.
75%UnverifiedOpenCode Go no longer lists MiniMax M2.7.
70%UnverifiedOpenCode Go kept and pinned the base URL https://opencode.ai/inference/go/v1 because models.dev migrated the provider-level URL to an OpenAI-only path; without pinning, requests would hit an incompatible endpoint.
50%UnverifiedThe Cline recommendation list adds Gemini 4 Argon and removes Grok 4.7; the free list replaces Step 5 Preview with Nemotron 3.5 Super VL; OpenCode Go no longer lists MiniMax M2.7.
50%UnverifiedOpenCode added Gemini 4 Argon to OpenCode Go on October 14, launching a promotion of '$60 of usage for $10 before November 30'.
50%UnverifiedIn v4.1.24, OpenCode Go switched to the new inference endpoint https://opencode.ai/inference/go/v1.
50%Unverifiedv3.0.71's model catalog adds three providers: AI/ML API, LowRouter and Prime Inference; the v0 provider is streamlined to provide only the default model `v0-1.5-md`; OpenCode Go migrates to the new endpoint `https://opencode.ai/inference/go/v1`; and Step 5 Preview is added to the Cline free list.
50%UnverifiedOpenCode Go's monthly quota is only about 38% higher than its weekly quota (42% higher for tokens), exhibiting a week-strong, month-weak structure where using the monthly quota at a weekly pace will quickly hit the ceiling.
50%UnverifiedResolving the 502 error requires changing the BaseURL from the local address to OpenCode Go's official service address, because the new version must use Response mode and cannot respond through local routing
50%UnverifiedThis fix causes the OpenCode provider to add the x-opencode-session header to every request, generating a non-empty temporary ID as a fallback for standalone requests.
50%UnverifiedThe OpenCode Go backend requires that every model request must carry the x-opencode-session request header.
50%UnverifiedOpenCode Go, Codex CLI, Aider, and Continue can all be regarded as Harness implementations under different design philosophies.
50%UnverifiedZed merged PR #63702 in its nightly build, fixing a missing session header issue when integrating with OpenCode Go.
50%