MiniMax M3
MiniMax · Open weights · Released May 31, 2026 · minimax/minimax-m3
Best $0.23 in / $0.96 out via CoreWeave · fp4 · 262K ctx at this price (headline 1.05M)
1.05M contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 13 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 CoreWeave | $0.23 | $0.96 | $0.05 | 262K | fp4 | ✕ | ✕ | 5/5 | 99.1% |
 GMICloud | $0.24 | $0.96 | $0.048 | 1.05M | fp8 | 3.5s | 150 tok/s | 5/5 | 99.7% |
 DeepInfra | $0.28 | $1.10 | $0.056 | 524K | fp8 | ✕ | ✕ | 5/5 | 99.7% |
 Minimax1ST PARTY | $0.30 | $1.20 | $0.06 | 524K | fp8 | 2s | 101 tok/s | — | 100.0% |
 AtlasCloud | $0.30 | $1.20 | $0.06 | 524K | fp8 | 1.4s | 149 tok/s | 5/5 | 98.2% |
 Novita | $0.30 | $1.20 | $0.06 | 1M | fp8 | ✕ | ✕ | — | 100.0% |
 Parasail | $0.30 | $1.20 | $0.06 | 1.05M | fp8 | 0.67s | 213 tok/s | 3/5 | 99.8% |
 StreamLake | $0.30 | $1.20 | $0.06 | 1M | fp8 | 1.2s | 119 tok/s | — | 98.9% |
 Together | $0.30 | $1.20 | $0.06 | 524K | — | 0.52s | 105 tok/s | — | 100.0% |
 Venice | $0.30 | $1.20 | $0.06 | 524K | fp8 | 1s | 157 tok/s | — | 96.8% |
 Mara | $0.60 | $2.40 | — | 1.05M | — | 1.6s | 195 tok/s | — | 91.5% |
 SambaNova | $0.60 | $2.40 | $0.06 | 1.05M | — | 2s | 271 tok/s | — | 67.7% |
 ModelRun | $0.75 | $3.00 | $0.15 | 1.05M | fp4 | 1.9s | 183 tok/s | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Quality benchmarksCURATED AUG 24, 2026
Third-party reported results, hand-curated with sources — not measured by ModelIndex. Our own measured serving data (TTFT/TPS/SMOKE) is in the providers table above.
Input price history · best listed price, observed
$0.23 · SEP 9, 2026$0.23 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.23 / $0.96
per MTok in / out
CACHE READ $0.05
Recent changesRSS ↗
Sep 15, 2026endpoint added · mara12 → 13
Sep 9, 2026price decreased · input0.23 → 0.12
Sep 9, 2026price decreased · output0.96 → 0.48
Sep 5, 2026endpoint added · together11 → 12
Aug 29, 2026endpoint removed · together12 → 11
Aug 27, 2026endpoint removed · morph13 → 12
About
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Specifications
Context window1,048,576
Max output512,000
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedMay 31, 2026
TokenizerOther
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/minimax/minimax-m3)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks14 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.