MiniMax M3.1 Flash
MiniMax's open-weights multimodal model for agents and coding, scoring 43 on the AA Intelligence Index v4.3.2 at $0.15/$0.60 per million tokens with a 1M-token context window.
Start requirement: From 1 credit
Capabilities
Pricing
| Input | $0.3 / 1M tokens |
| Cached input | $0.03 / 1M tokens |
| Output | $1.2 / 1M tokens |
List prices plus 100%. Higher reasoning effort can consume more output tokens; it has no separate fixed multiplier. One credit equals 1¢ charged, with a one-credit minimum per completed run and the aggregate rounded up once.
Fireworks serverless preview; not yet in the Fireworks pricing table.
Provider pricing source · verified 2026-10-26
MiniMax M3.1 Flash: frequently asked questions
- What is MiniMax M3.1 Flash?
- MiniMax's open-weights multimodal model for agents and coding, scoring 43 on the AA Intelligence Index v4.3.2 at $0.15/$0.60 per million tokens with a 1M-token context window. You can try MiniMax M3.1 Flash on TryAI without a separate provider account.
- How much does MiniMax M3.1 Flash cost on TryAI?
- MiniMax M3.1 Flash uses these rates (provider list price plus 100%): Input: $0.3 / 1M tokens, Cached input: $0.03 / 1M tokens, Output: $1.2 / 1M tokens. One TryAI credit equals one cent charged; completed runs have a one-credit minimum and the aggregate cost is rounded up once.
- What can MiniMax M3.1 Flash do?
- MiniMax M3.1 Flash supports Streaming, Reasoning, Tool use, Vision with a context window of about 1M tokens.
- How do I try MiniMax M3.1 Flash?
- Create a free TryAI account, pick MiniMax M3.1 Flash from the model selector, and start generating in seconds.
Related models
GPT-6 Astra
Chat & reasoning
250 credits to start
OpenAI's newest frontier model for complex reasoning, coding, and computer use, with a 1.05M-token context window. Self-reported 96.0 on GPQA and 91.5 on BrowseComp.
Try GPT-6 Astra→Claude Opus 5.5
Chat & reasoning
250 credits to start
Anthropic's newest Opus for long-running agentic coding and knowledge work. $4/$20 per million tokens, with cache reads at $0.20/M. Vendor-reported Terminal-Bench 4.0 66.4% and GDPval-AA 1846 Elo at max effort.
Try Claude Opus 5.5→Claude Sonnet 5.5
Chat & reasoning
75 credits to start
Anthropic's fast everyday model, second only to Opus 5.5 on the AA Intelligence Index v4.3.2 at 56, for $2/$10 per million tokens. Vendor-reported Terminal-Bench 4.0 70.6% and GDPval-AA 1844 Elo.
Try Claude Sonnet 5.5→