xpu liveBETA
Providers›Together AI

Together AI

Visit provider ↗

Hosted inference for language and media models. Serverless availability is tracked separately from dedicated deployments.

14 linked modelsAPI documentation ↗Official catalog ↗Checked 2026-09-28

Models on Together AI 14

A curated selection, with links to other providers for the same model.

Verified catalog sources
Ranked by intelligence

Artificial Analysis Intelligence Index ↗ · Higher is better · Checked 2026-10-02

Rank among verified models in this catalog. Best published configuration per model; equal scores share a rank. Scores are rounded by the source. Unverified and non-language models appear last without a rank. Methodology ↗

14 models

RankModelIntelligenceBest priceInput → outputProviders
#11GLM 5.3Z Ai45max
$0.9 in / $4 out
USD / 1M tokensDeepInfra

Standard list · Lowest listed input price; output is from the same tariff.

Published cents-per-token list rate. Account discounts and cache/service-tier modifiers are not applied.

Compare prices →
text → textDeepInfraFireworks AIOpenRouterTogether AI
#13Kimi K3Moonshot AI44max
$2.7 in / $13.5 out
USD / 1M tokensOpenRouter

Router catalog · Lowest listed input price; output is from the same tariff.

OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill.

Compare prices →
text, image, video → textDeepInfraFireworks AINovita AIOpenRouterTogether AI
#20DeepSeek V4.1 FlashDeepseek39max
$0.15 in / $0.6 out
USD / 1M tokensDeepSeek

Off-peak · Lowest listed input price; output is from the same tariff.

Time-of-day tariff; consult official source for UTC peak/off-peak windows and alias behavior.

Compare prices →
text, image → textDeepInfraDeepSeekFireworks AIOpenRouterTogether AI
—FLUX.2 [dev]Black Forest Labs—Not comparablePrice not collectedtext, image → imageTogether AI
—FLUX.2 [max]Black Forest Labs—Not comparableSee pricing options →text, image → imageSegmindTogether AI
—FLUX.2 [pro]Black Forest Labs—Not comparablePrice not collectedtext, image → imagefal.aiTogether AI
—gpt-oss-120bOpenai—Not verified
$0.037 in / $0.17 out
USD / 1M tokensOpenRouter

Router catalog · Lowest listed input price; output is from the same tariff.

OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill.

Compare prices →
text → textFireworks AIGroqOpenRouterTogether AI
—Hailuo 02MiniMax—Not comparablePrice not collectedtext, image → videoTogether AI
—Ideogram 3.0Ideogram—Not comparablePrice not collectedtext → imageTogether AI
—Orpheus 3BCanopy Labs—Not comparablePrice not collectedtext → audioTogether AI
—Seedance 2.5ByteDance—Not comparable
From $0.18
USD / secondWaveSpeedAI

Starting price · Starting tariff; final cost depends on the selected settings.

Advertised starting price. Resolution, duration and endpoint can change total charges.

Compare prices →
text, image, video, audio → video, audiofal.aiTogether AIWaveSpeedAI
—Seedream 5 LiteByteDance—Not comparablePrice not collectedtext, image → imageTogether AI
—Sonic 3Cartesia—Not comparablePrice not collectedtext → audioTogether AI
—Veo 3.1Google—Not comparable
From $0.2
USD / secondRunway

veo3.1 (no audio) · Starting tariff; final cost depends on the selected settings.

20 credits per second

Compare prices →
text, image → video, audioGoogle Gemini APIRunwayTogether AI

Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.