opencode: Model updates - #58743
Merged
Merged
Conversation
cla-bot
Bot
added
the
cla-signed
benbrandt
approved these changes
Jun 6, 2026
benbrandt
enabled auto-merge
June 6, 2026 20:21
alan-codes-things
pushed a commit
to alan-codes-things/zed
that referenced
this pull request
Jun 7, 2026
OpenCode models updates (delayed since I was super-busy the past 2 weeks and nobody else opened up a PR): **Free**: - added MiniMax M3 Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/minimax-m3-free.toml) and [docs](https://opencode.ai/docs/zen/). Seeing how MiniMax M2.5 was a long-term Free model, I am also assuming the same will be true for M3 🤷 Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Nemotron 3 Ultra Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/nemotron-3-ultra-free.toml) and [docs](https://opencode.ai/docs/zen/), with 3 reasoning levels discovered manually from the OpenCode CLI. Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test, both on `low` and `high` reasoning levels - removed Nemotron 3 Super Free as per [models.dev](anomalyco/models.dev@72fc81a) **Go**: - added MiniMax M3 as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/minimax-m3.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Qwen 3.7 Plus as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/qwen3.7-plus.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - updated token counts for Qwen 3.6 Plus as per anomalyco/models.dev@350704d - removed Qwen 3.5 Plus as per [models.dev](anomalyco/models.dev@c7af5ba) (but not from Zen where [it is still valid](https://github.com/anomalyco/models.dev/blob/e524b01b9a8f593838f9d36469f0c5087ae2cf34/providers/opencode/models/qwen3.5-plus.toml)) **Zen**: - added DeepSeek V4 Flash as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/deepseek-v4-flash.toml) and [docs](https://opencode.ai/docs/zen/). Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one - added MiniMax M2.7 which was mistakenly marked as Go-only. Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one ------ Self-Review Checklist: - [x] I've reviewed my own diff for quality, security, and reliability - [x] Unsafe blocks (if any) have justifying comments - [x] The content is consistent with the [UI/UX checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist) - [ ] Tests cover the new/changed behavior - [x] Performance impact has been considered and is acceptable Release Notes: - Agent: Updated OpenCode models (added MiniMax M3, Qwen 3.7 Plus, DeepSeek V4 Flash, MiniMax M3 Free, and Nemotron 3 Ultra Free; removed Nemotron 3 Super Free, Qwen 3.5 Plus; updated MiniMax M2.7, MiniMax M2.5, Qwen 3.6 Plus)
TomPlanche
pushed a commit
to TomPlanche/zed
that referenced
this pull request
Jun 8, 2026
OpenCode models updates (delayed since I was super-busy the past 2 weeks and nobody else opened up a PR): **Free**: - added MiniMax M3 Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/minimax-m3-free.toml) and [docs](https://opencode.ai/docs/zen/). Seeing how MiniMax M2.5 was a long-term Free model, I am also assuming the same will be true for M3 🤷 Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Nemotron 3 Ultra Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/nemotron-3-ultra-free.toml) and [docs](https://opencode.ai/docs/zen/), with 3 reasoning levels discovered manually from the OpenCode CLI. Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test, both on `low` and `high` reasoning levels - removed Nemotron 3 Super Free as per [models.dev](anomalyco/models.dev@72fc81a) **Go**: - added MiniMax M3 as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/minimax-m3.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Qwen 3.7 Plus as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/qwen3.7-plus.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - updated token counts for Qwen 3.6 Plus as per anomalyco/models.dev@350704d - removed Qwen 3.5 Plus as per [models.dev](anomalyco/models.dev@c7af5ba) (but not from Zen where [it is still valid](https://github.com/anomalyco/models.dev/blob/e524b01b9a8f593838f9d36469f0c5087ae2cf34/providers/opencode/models/qwen3.5-plus.toml)) **Zen**: - added DeepSeek V4 Flash as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/deepseek-v4-flash.toml) and [docs](https://opencode.ai/docs/zen/). Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one - added MiniMax M2.7 which was mistakenly marked as Go-only. Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one ------ Self-Review Checklist: - [x] I've reviewed my own diff for quality, security, and reliability - [x] Unsafe blocks (if any) have justifying comments - [x] The content is consistent with the [UI/UX checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist) - [ ] Tests cover the new/changed behavior - [x] Performance impact has been considered and is acceptable Release Notes: - Agent: Updated OpenCode models (added MiniMax M3, Qwen 3.7 Plus, DeepSeek V4 Flash, MiniMax M3 Free, and Nemotron 3 Ultra Free; removed Nemotron 3 Super Free, Qwen 3.5 Plus; updated MiniMax M2.7, MiniMax M2.5, Qwen 3.6 Plus)
This was referenced Jun 18, 2026
Closed
5 tasks
This was referenced Jul 8, 2026
jonx
pushed a commit
to jonx/zed-aros
that referenced
this pull request
Jul 17, 2026
OpenCode models updates (delayed since I was super-busy the past 2 weeks and nobody else opened up a PR): **Free**: - added MiniMax M3 Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/minimax-m3-free.toml) and [docs](https://opencode.ai/docs/zen/). Seeing how MiniMax M2.5 was a long-term Free model, I am also assuming the same will be true for M3 🤷 Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Nemotron 3 Ultra Free as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/nemotron-3-ultra-free.toml) and [docs](https://opencode.ai/docs/zen/), with 3 reasoning levels discovered manually from the OpenCode CLI. Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test, both on `low` and `high` reasoning levels - removed Nemotron 3 Super Free as per [models.dev](anomalyco/models.dev@72fc81a) **Go**: - added MiniMax M3 as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/minimax-m3.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - added Qwen 3.7 Plus as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode-go/models/qwen3.7-plus.toml). Tested and confirmed working with a simple "_rename this variable for me. add a function. delete the function_" test - updated token counts for Qwen 3.6 Plus as per anomalyco/models.dev@350704d - removed Qwen 3.5 Plus as per [models.dev](anomalyco/models.dev@c7af5ba) (but not from Zen where [it is still valid](https://github.com/anomalyco/models.dev/blob/e524b01b9a8f593838f9d36469f0c5087ae2cf34/providers/opencode/models/qwen3.5-plus.toml)) **Zen**: - added DeepSeek V4 Flash as per [models.dev](https://github.com/anomalyco/models.dev/blob/f753ddacdbab785c87f4fceb3187d6ceb9790966/providers/opencode/models/deepseek-v4-flash.toml) and [docs](https://opencode.ai/docs/zen/). Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one - added MiniMax M2.7 which was mistakenly marked as Go-only. Not tested as I don't have a Zen subscription and I am stubbornly refusing to get one ------ Self-Review Checklist: - [x] I've reviewed my own diff for quality, security, and reliability - [x] Unsafe blocks (if any) have justifying comments - [x] The content is consistent with the [UI/UX checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist) - [ ] Tests cover the new/changed behavior - [x] Performance impact has been considered and is acceptable Release Notes: - Agent: Updated OpenCode models (added MiniMax M3, Qwen 3.7 Plus, DeepSeek V4 Flash, MiniMax M3 Free, and Nemotron 3 Ultra Free; removed Nemotron 3 Super Free, Qwen 3.5 Plus; updated MiniMax M2.7, MiniMax M2.5, Qwen 3.6 Plus)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
OpenCode models updates (delayed since I was super-busy the past 2 weeks and nobody else opened up a PR):
Free:
lowandhighreasoning levelsGo:
Zen:
Self-Review Checklist:
Release Notes: