feat: upgrade MiniMax default model to M3#1492
Open
octo-patch wants to merge 2 commits into
Open
Conversation
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed models (204K context, 192K max output) - Fix API base URL from api.minimax.chat to api.minimax.io (official endpoint) - Update model reference in Argcfile.sh from MiniMax-Text-01 to MiniMax-M2.7 - Update documentation link to current API reference
- Add MiniMax-M3 (1M context, 128K max output, multimodal) as the new default - Remove deprecated minimax-m2.5/m2.5-highspeed/m2.1/m2.1-highspeed - Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed as legacy alternatives - Update Argcfile.sh test model reference to MiniMax-M3
octo-patch
changed the title
ei-grad
added a commit
to ei-grad/aichat
that referenced
this pull request
Jul 11, 2026
Replace retired Gemini entries with current direct and Vertex model IDs, limits, capabilities, and global standard pricing where the scalar catalog can represent it. Add Claude Opus 4.7 to Claude, Vertex AI, Bedrock, and OpenRouter with the published 1M/128K limits and provider-specific adaptive thinking request shapes. Sampling fields are removed for every Opus 4.7 variant, and no fixed thinking budget is sent. Add the corrected DeepSeek V4 Flash and Pro metadata and keep the legacy aliases accurate until their announced July 24 retirement. Move MiniMax to the current international endpoint and exact M2.7/M2.5/M2.1 model IDs and prices; deliberately exclude the unverified M3 proposal and unsupported output-limit guess. Keep the existing Moonshot name on the China endpoint and add an explicit moonshot_intl route for the international endpoint. Refresh each region's catalog without silently changing existing users' data route. Add focused catalog and request-merge tests plus list-model defaults and examples. Upstream context: sigoden#1445 sigoden#1469 sigoden#1514 sigoden#1519 sigoden#1492 sigoden#1515 sigoden#1520 sigoden#1526 Primary sources verified 2026-07-11: https://ai.google.dev/gemini-api/docs/deprecations https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite https://ai.google.dev/gemini-api/docs/pricing https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing https://platform.claude.com/docs/en/about-claude/models/overview https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-4-7 https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-adaptive-thinking.html https://openrouter.ai/anthropic/claude-opus-4.7 https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/claude-4-7 https://api-docs.deepseek.com/quick_start/pricing https://api-docs.deepseek.com/news/news260424/ https://platform.minimax.io/docs/api-reference/text-openai-api https://platform.minimax.io/docs/guides/pricing-paygo https://platform.kimi.com/docs/api/overview https://platform.kimi.com/docs/models https://platform.kimi.ai/docs/guide/start-using-kimi-api https://platform.kimi.ai/docs/models Co-Authored-By: Codex CLI <noreply@openai.com>
ei-grad
added a commit
to ei-grad/aichat
that referenced
this pull request
Jul 11, 2026
Replace retired Gemini entries with current direct and Vertex model IDs, limits, capabilities, and global standard pricing where the scalar catalog can represent it. Add Claude Opus 4.7 to Claude, Vertex AI, Bedrock, and OpenRouter with the published 1M/128K limits and provider-specific adaptive thinking request shapes. Sampling fields are removed for every Opus 4.7 variant, and no fixed thinking budget is sent. Add the corrected DeepSeek V4 Flash and Pro metadata and keep the legacy aliases accurate until their announced July 24 retirement. Move MiniMax to the current international endpoint and exact M2.7/M2.5/M2.1 model IDs and prices; deliberately exclude the unverified M3 proposal and unsupported output-limit guess. Keep the existing Moonshot name on the China endpoint and add an explicit moonshot_intl route for the international endpoint. Refresh each region's catalog without silently changing existing users' data route. Add focused catalog and request-merge tests plus list-model defaults and examples. Upstream context: sigoden#1445 sigoden#1469 sigoden#1514 sigoden#1519 sigoden#1492 sigoden#1515 sigoden#1520 sigoden#1526 Primary sources verified 2026-07-11: https://ai.google.dev/gemini-api/docs/deprecations https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite https://ai.google.dev/gemini-api/docs/pricing https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing https://platform.claude.com/docs/en/about-claude/models/overview https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-4-7 https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-adaptive-thinking.html https://openrouter.ai/anthropic/claude-opus-4.7 https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/claude-4-7 https://api-docs.deepseek.com/quick_start/pricing https://api-docs.deepseek.com/news/news260424/ https://platform.minimax.io/docs/api-reference/text-openai-api https://platform.minimax.io/docs/guides/pricing-paygo https://platform.kimi.com/docs/api/overview https://platform.kimi.com/docs/models https://platform.kimi.ai/docs/guide/start-using-kimi-api https://platform.kimi.ai/docs/models Co-Authored-By: Codex CLI <noreply@openai.com>
ei-grad
added a commit
to ei-grad/aichat
that referenced
this pull request
Jul 11, 2026
Integrate the named verified catalog branch without importing model proposal heads sigoden#1492, sigoden#1515, sigoden#1520, or sigoden#1526. The second parent records corrected model metadata, request shapes, and explicit regional routes with primary-source and focused test provenance. Context: sigoden#1492 sigoden#1515 sigoden#1520 sigoden#1526
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
1 participant
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.
Summary
Upgrade the MiniMax model configuration in this project to make MiniMax-M3 (the latest flagship coding/agentic model) the new default, while retaining M2.7 variants as legacy alternatives.
Changes
api.minimax.chattoapi.minimax.io(official endpoint)Why
MiniMax-M3 is the new flagship model with a 1M-token context window, 128K max output, native multimodality, and strong agentic/coding performance. Older M2.5 / M2.1 models have been superseded; M2.7 / M2.7-highspeed remain available as legacy alternatives.
Testing
models.yamlvalidated as well-formed YAML