Cost ledger
LLM API Pricing Comparison and Cost Calculator
As of October 8, 2026, the cheapest LLM API is Perplexity Decider v1 27B at $0.02/$0.00 per million input/output tokens, of 174 paid models across 32 providers. The cheapest production-grade model (score 70+) is MiMo-V2.6-Pro at $0.43/$0.87. The cheapest frontier-tier model (score 80+) is Claude Sonnet 5.5 at $2.00/$10.00.
The cheapest API is rarely the cheapest model to run. Price per token below, price per answer in the calculator. The Score/$ column uses the public overall score per dollar of output — higher means better value.
Updated October 8, 2026. 174 paid models, 32 providers, per million tokens. Official API rates. Open-weight model costs depend on your infrastructure. How does LLM token pricing work?
Cheapest LLM APIs in 2026
The lowest token rate, the strongest score per output dollar, and the highest-scoring paid model answer different questions. Use the first for raw volume, the second for a shortlist, and the third when quality matters more than list price.
Cheapest API
$0.15 in / $0 out per 1M tokens
GLiDE
Best Value (Score/$)
Qwen3.7 Flash
Score/$ ratio: 364.6
Highest Scored (Paid)
Claude Opus 5.5
Public score: 86.3 — $4 in / $20 out
LLM pricing comparison
Filter by provider, family, or model name, then sort the current API rates by input price, output price, context window, benchmark score, or score per output dollar. Cache rates remain blank unless the exact model row has a published cache-hit price.
Model / providerInput · output
$4.00·$20.00
$10.00·$50.00
$2.00·$10.00
$10.00·$50.00
Gemini 4 ArgonGoogle · Context not listedScore ~81.72 · 8.2 score/$Cache $0.10/1M · checked October 8, 2026
$2.00·$10.00
$2.00·$10.00
$5.00·$25.00
$10.00·$50.00
$4.00·$20.00
$2.00·$10.00
$0.43·$0.87
$0.75·$3.75
$30.00·$180.00
$2.00·$12.00
$3.00·$15.00
Not listed
$1.00·$2.70
$5.00·$25.00
$30.00·$180.00
Free*
$2.00·$6.00
Claude Opus 4.7 (Adaptive)Anthropic · 1MScore ~67.87 · 2.7 score/$Cache not published · checked October 8, 2026
$5.00·$25.00
$0.30·$1.20
$5.00·$30.00
$0.75·$3.75
$2.50·$15.00
$1.25·$4.25
$0.10·$0.50
$21.00·$168.00
$0.20·$1.20
$2.00·$10.00
$0.10·$0.50
$0.14·$0.28
$2.00·$12.00
Claude Opus 4.7Anthropic · 1MScore ~64.17 · 2.6 score/$Cache not published · checked October 8, 2026
$5.00·$25.00
Free*
DeepSeek V4 Pro 0813DeepSeek · 1MScore ~63.91 · 16.1 score/$Cache $0.04/1M · checked October 8, 2026
$1.32·$3.96
$2.00·$6.00
Free*
$0.75·$3.75
Not listed
$1.50·$9.00
Not listed
Free*
$5.00·$25.00
$1.40·$4.40
$1.75·$14.00
Free*
$1.75·$14.00
$2.00·$12.00
$0.95·$4.00
Free*
$1.25·$2.50
Free*
$1.25·$10.00
$1.40·$4.40
Claude Sonnet 4.6Anthropic · 200KScore 55.2 · 3.7 score/$Cache not published · checked October 8, 2026
$3.00·$15.00
$1.75·$14.00
$0.50·$3.00
Inkling-SmallThinking Machines Lab · 1MScore 54.42 · 37.8 score/$Cache $0.12/1M · checked October 8, 2026
$0.58·$1.44
$0.30·$1.20
$1.20·$4.00
$5.00·$25.00
$0.60·$3.60
$0.75·$4.50
Not listed
$0.68·$2.09
$1.25·$2.50
$1.00·$3.20
Free*
$1.87·$4.68
Free*
Not listed
$0.95·$4.00
$0.60·$3.00
Not listed
Free*
$0.30·$2.50
Not listed
$0.30·$1.20
$1.25·$10.00
$1.20·$4.00
$1.25·$10.00
$0.28·$0.42
Quasar 438BMultiverse Computing · 1MScore ~49.32 · 27.4 score/$Cache not published · checked October 8, 2026
$0.60·$1.80
Free*
$0.25·$2.00
Claude Sonnet 4.5Anthropic · 200KScore ~48.48 · 3.2 score/$Cache not published · checked October 8, 2026
$3.00·$15.00
Free*
$0.40·$2.40
$0.25·$1.50
Free*
$0.30·$1.20
$0.03·$0.13
$0.20·$1.25
Free*
Free*
Not listed
$20.00·$80.00
Free*
Free*
$2.00·$8.00
Not listed
$0.30·$0.50
Step 3.7 FlashStepFun · 256KScore ~44.09 · 38.3 score/$Cache not published · checked October 8, 2026
$0.20·$1.15
$0.10·$0.40
Not listed
Step 3.5 FlashStepFun · 256KScore ~42.38 · 141.3 score/$Cache not published · checked October 8, 2026
$0.10·$0.30
$0.30·$2.50
Free*
$0.55·$2.19
$1.00·$5.00
Free*
Free*
Free*
Free*
Claude 4.1 OpusAnthropic · 200KScore ~40.32 · 0.5 score/$Cache not published · checked October 8, 2026
$15.00·$75.00
$1.10·$4.40
Not listed
Free*
$15.00·$60.00
Free*
Claude 4 SonnetAnthropic · 200KScore ~38.37 · 2.6 score/$Cache not published · checked October 8, 2026
$3.00·$15.00
$2.00·$8.00
$0.05·$0.40
Free*
Not listed
$0.20·$0.50
$2.50·$10.00
$15.00·$60.00
$0.04·$0.15
$0.25·$0.75
$150.00·$600.00
Mistral Medium 3.5 128BMistral · 256KScore ~35.25 · 4.7 score/$Cache not published · checked October 8, 2026
$1.50·$7.50
$0.20·$1.10
Mistral Small 4Mistral · 256KScore ~34.75 · 57.9 score/$Cache not published · checked October 8, 2026
$0.15·$0.60
Trinity-Large-ThinkingArcee AI · 512KScore ~34.53 · 38.4 score/$Cache not published · checked October 8, 2026
$0.25·$0.90
$0.20·$1.50
Free*
Free*
Mistral Large 3Mistral · 256KScore ~33.25 · 22.2 score/$Cache not published · checked October 8, 2026
$0.50·$1.50
Not listed
Free*
$0.27·$1.10
Free*
Free*
DeepSeek R1 Distill Qwen 32BDeepSeek · 128KScore ~31.13Cache not published · checked October 8, 2026
Free*
Free*
Free*
Free*
$0.40·$1.60
$0.15·$0.60
Free*
$2.50·$10.00
Free*
Free*
Free*
$0.60·$2.50
Free*
Mistral Medium 3Mistral · 128KScore ~29.14 · 14.6 score/$Cache not published · checked October 8, 2026
$0.40·$2.00
Free*
Free*
$15.00·$75.00
$0.20·$0.70
Free*
Not listed
Claude 3.5 SonnetAnthropic · 200KScore ~28.32 · 1.9 score/$Cache not published · checked October 8, 2026
$3.00·$15.00
Qwen3-Omni-30B-A3B-InstructAlibaba · Context not listedScore ~28.31Cache not published · checked October 8, 2026
Not listed
$1.25·$5.00
Not listed
Free*
Free*
Free*
$0.15·$0.60
Free*
$0.10·$0.40
Free*
Ministral 3 14BMistral · 256KScore ~25.05 · 125.3 score/$Cache not published · checked October 8, 2026
$0.20·$0.20
Free*
Not listed
Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · 1MScore ~21.76Cache not published · checked October 8, 2026
Free*
$10.00·$30.00
Free*
Free*
Ministral 3 8BMistral · 256KScore ~20.17 · 134.5 score/$Cache not published · checked October 8, 2026
$0.15·$0.15
Free*
Free*
Ministral 3 3BMistral · 256KScore ~18.99 · 189.9 score/$Cache not published · checked October 8, 2026
$0.10·$0.10
Free*
Claude 3 HaikuAnthropic · 200KScore 14.44 · 11.6 score/$Cache not published · checked October 8, 2026
$0.25·$1.25
Not listed
Free*
Free*
Free*
Free*
Free*
Free*
Free*
Free*
$0.80·$1.60
AJev lora5 (Gemma 4 12B)andyzhang232 · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Alibaba GTE Reranker ModernBERT-baseAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Amazon Nova 2 SonicAmazon · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Arena-Hard (claude-3-5-sonnet-20240620) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (claude-3-haiku-20240307) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (DeepSeek-R1-250120) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (gemini-1.5-flash-001) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (gemini-1.5-pro-001) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (gpt-4o-2024-05-13) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (gpt-4o-mini-2024-07-18) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (Llama-3.1-405B-Instruct) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (Llama-3.1-70B-Instruct) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (Llama-3.1-8B-Instruct) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (Mistral-7B-v0.1-Instruct) (JudgeBench)JudgeBench evaluated system · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (o1-mini-2024-09-12) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (o1-preview-2024-09-12) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (o3-mini-2025-01-31 (high)) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (o3-mini-2025-01-31 (low)) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Arena-Hard (o3-mini-2025-01-31 (medium)) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Atria Dawn PreviewShanghai Artificial Intelligence Laboratory · 256KScore not rankedCache not published · checked October 8, 2026
Free*
Audio Flamingo 3 7BNVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Auto-J (JudgeBench)GAIR · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
AutoJev-27Bdenis-pplx · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
AutoJev-27B (Decision Index reference)denis-pplx · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
AutoJev-27B (RTX PRO 6000)denis-pplx · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Autoloops Gemma 4 31B ITAutoloops · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BAAI bge-reranker-v2-m3BAAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Baichuan-AudioBaichuan · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Baichuan-Omni 1.5Baichuan · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Bekko System One v0 17Mhotchpotch · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Bekko System One v0 400Mhotchpotch · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Bekko System One v0 68Mhotchpotch · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
BERT base / Fine-tuned on case law and contract corpora Chalkidis et al. (2020) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT base / Fine-tuned on NDAs (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT base / None (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT base / Pretrained from scratch using a case law corpus Zheng et al. (2021) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT classifier w/o Table (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT large / Fine-tuned on NDAs (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT large / None (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-BOOLQ-YN (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-DIS-YN (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-MNLI-YN (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-YN (Answer) (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-YN (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BERT-YN (Question) (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Bespoke Nimble 9BBespoke Labs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Bespoke Nimble 9B v2bespokelabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Bespoke Nimble 9B v3bespokelabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Bev / Bonsai 27BReza Sayar · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Blink v0.3 26B-A4B (NVFP4)PixilabAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
BLOOMZ 7.1B (Belebele zero-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BLSP 7BBLSP authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
BOOLQ (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Bosun v3.1 0.6BClause Logic · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Bosun v3.1 1.7BHanno-Labs · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
BR-Voice-ReasonerBairong Xdynamics · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
Canary 180M FlashNVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Cartesia Ink-WhisperCartesia · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Cartesia Sonic 3Cartesia · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Cartesia Sonic 3.6Cartesia · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Certo v1AltSlate Labs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
ChatEval (gpt-4o-2024-05-13) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
classifier.dev (fast)classifier.dev · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$10.00·$50.00
Not listed
Claude Mythos PreviewAnthropic · Context not listedScore not rankedCache not published · checked October 8, 2026
$25.00·$125.00
Claude-3.5-Sonnet Solver (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
CLM-8BContrastive-LM · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
CLM-v0.1-8BContrastive-LM · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Cohere Transcribe 03-2026Cohere · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Cohere Transcribe Arabic 07-2026Cohere · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
CompassJudger-1-1.5B (JudgeBench)OpenCompass · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
CompassJudger-1-14B (JudgeBench)OpenCompass · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
CompassJudger-1-32B (JudgeBench)OpenCompass · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
CompassJudger-1-7B (JudgeBench)OpenCompass · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.50·$2.50
$0.50·$2.50
Free*
Not listed
Not listed
Free*
Free*
Free*
DeBERTa v2 xlarge / Fine-tuned on span identification Hendrycks et al. (2021) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
DeBERTa v2 xlarge / None (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Decider chat · Gemma-4-31BMapika · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decider chat · Qwen3.6-27BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
decider-35b-a3bMapika · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
decider-4b v2Mapika · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
decisio 0.4.0 (Gemma 4 12B)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
decisio 0.4.0 (Qwen3.6-35B-A3B)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decision 2B v59FlyMy.AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decision 4B v1.1FlyMy.AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decision 4B v1.2FlyMy.AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decision Fast v53aFlyMy.AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Decision-4B (Eval Engine / Chromia)Eval Engine / Chromia · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
decision-machine-1milliseconds.ai · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
deck31b (Gemma 4 31B)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Deem 0.8B v1LibertAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Deepgram Aura-2Deepgram · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Deepgram FluxDeepgram · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Deepgram Flux MultilingualDeepgram · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Deepgram Nova-3Deepgram · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Free*
$0.55·$2.19
$0.14·$0.28
Free*
Dinah-0Lukitaduarte · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
DiVA Llama 3 8BDiVA authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
djev (thinking)Maisa · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
DM-JEPA 1.1Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Doc TF-IDF+SVM (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Eikos-27Bcaiovicentino1 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
ElevenLabs Eleven v3 ConversationalElevenLabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
ElevenLabs Eleven v4ElevenLabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
ElevenLabs Eleven v4 TurboElevenLabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Free*
$3.00·$15.00
EXAONE-4.0-1.2B-JEV v0.3Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
ezjev 4B s2everettjf · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Falcon 40B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Fastino GLiDE no-thinking (28B)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Finetuned Llama-2-13B (RAGTruth detector)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Fish Audio S2.1 ProFish Audio · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Freya TTS Adam V1Freya · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$6.00·$36.00
Gemini 2.5 Flash Native Audio Preview (12-2025)Google · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.10·$0.40
Not listed
Gemini 3.1 Flash Live PreviewGoogle · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Gemini 3.5 Flash CyberGoogle · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Gemini 3.5 TranscribeGoogle · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Gemini 3.8 Flash CyberGoogle · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
$0.75·$4.50
Gemini 3.8 Live Extended ThinkingGoogle · 128KScore not rankedCache not published · checked October 8, 2026
$0.75·$4.50
Gemini-1.5-pro Solver (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GEV-26B-Decideautotrust · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Gevva E2Bdavidburhans · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Gevva E4Bdavidburhans · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
$0.15·$0.00
GLiNER2 largeFastino · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLiNER2.5 baseFastino · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLiNER2.5 multiFastino · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLiNER2.5 smallFastino · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLiNER2.5-Decidefastino · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
GLM Realtime AirZhipu AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLM Realtime FlashZhipu AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GLM-4-VoiceZhipu AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.60·$2.20
$1.00·$3.20
GNN-TabFact (GNN-TabFact comparison)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$2.50·$10.00
GPT Live TranscribeOpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$4.00·$16.00
$4.00·$16.00
$4.00·$24.00
$4.00·$24.00
$0.60·$2.40
$0.60·$2.40
GPT TranscribeOpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GPT-3.5-turbo-0613 (RAGTruth generator)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GPT-4-0613 (RAGTruth generator)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$2.50·$10.00
$0.15·$0.60
$0.60·$12.00
GPT-4o Solver (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$1.25·$10.00
$1.25·$10.00
$1.50·$6.00
$1.75·$14.00
Not listed
GPT-5.6 CyberOpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GPT-5.6 Luna (low)OpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GPT-6 Luna (low)OpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
GPT-6 Luna (medium)OpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
GPT3.5-turbo unk (Belebele zero-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Granite Speech 5.0 470M TurboCTCIBM · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
GRM-Gemma-2B (JudgeBench)GRM authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
$2.00·$6.00
$1.00·$2.00
Not listed
Grok Voice Think Fast 1.0xAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Grok Voice Think Fast 2.0xAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Grok Voice Transcribe 2.0xAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
$0.40·$3.00
Not listed
Free*
$0.25·$1.80
Free*
Free*
Free*
Free*
Free*
Not listed
Hopper (G) 1.2HopitAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Hopper 12B (trained)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Hy ASR 3.0 previewTencent · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Not listed
Imajev-4Bmohit67890 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Imajev-4B (RTX 5090)mohit67890 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
InfoXLM large (550M) (Belebele English fine-tuning)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
InfoXLM large (550M) (Belebele Translate-Train-All)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Instinct Dual 4BZooWork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Instinct Qwen3.8-27BZooWork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Intelif Qwen3-4BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$1.50·$3.50
Intern-Decision-0.8Binternlm · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Intern-Decision-2Binternlm · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Intern-Decision-4Binternlm · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
InternLM2-20B-Reward (JudgeBench)InternLM · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
InternLM2-7B-Reward (JudgeBench)InternLM · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Inworld Realtime TTS-2Inworld · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Inworld Realtime TTS-2 FlashInworld · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Jebadiah 27Bfrontier-infra · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
jeffLogan Markewich · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Jet v6.2michaljach · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Not listed
Jev 1.13.0TypeSafe AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JEV Qwen3.5-9B Base NVFP4WilfLin · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
jev-local Qwen3.5-9Bus (GitHub) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Jev-Style 0.8B v3Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Jev-Style 2B v3Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
JevK5 9B v0.3.3alibiserikbay · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
JevK5 Litealibiserikbay · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
JevK5 v0.2.0allebee · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JevK5 v0.3Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JevK5 v0.3 4Ballebee · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Jevstral 8BAmirBraham · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Free*
Free*
Not listed
Jobe Qwen3.5-4BMantisShrimpdev · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JoshuaSP diffusiongemma (open-jev)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
Free*
jqv Qwen3-32BOctalab · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JudgeLM-13B-v1.0 (JudgeBench)BAAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JudgeLM-33B-v1.0 (JudgeBench)BAAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
JudgeLM-7B-v1.0 (JudgeBench)BAAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Julia 1SupersonicLabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Free*
Kalpa TTS Beta v0.1Kalpa Labs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
kev 0.5BJared Palmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
kev 0.6BJared Palmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kev 0.8B r15Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kev 27Bjaredpalmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
kev 4BJared Palmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kev 4B r10jaredpalmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
kev 8BJared Palmer · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kev 9B v2Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kimi K2.5 (Reasoning)Moonshot AI · 256KScore not rankedCache not published · checked October 8, 2026
$0.60·$3.00
Kimi-Audio 7BMoonshot AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Kodiak v0.2 1B (accuracy)cortex-agent-llc · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Not listed
Kyutai Pocket TTSKyutai · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
$0.10·$0.20
$0.10·$0.20
Free*
Free*
LayaConvai Innovations · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Laya multilingualConvai Innovations · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Laya typed-decisionsConvai Innovations · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
lev-350mFranck Verrot (franckverrot) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Lev1 3.7BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Not listed
LFM2.5-2.6B-RLCDmonotykamary · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Free*
Free*
LFM2.5-350M-RLCDnotnotsamuel · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Free*
Free*
Free*
Free*
Not listed
Not listed
Free*
LitJev Qwen3.8-27BZhengxu Yu · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Llama 1 13B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama 1 30B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama 1 65B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama 1 7B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama 2 base 70B (Belebele 5-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Llama-2-13B-chat (RAGTruth generator)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-70B-chat (RAGTruth, 4-bit)Meta / TheBloke · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-7B-chat (RAGTruth generator)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 70B (Belebele 89-language English instructions)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 70B (Belebele 89-language translated instructions)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 70B (Belebele 91-language in-language)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 70B (Belebele 91-language Translate-Test)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 70B (Belebele zero-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-2-chat 7B (Belebele zero-shot)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.1-405B-Instruct Solver (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.1-Nemotron-70B-Reward (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-70B-Reward (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-70B-Reward-Multilingual (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-70B-Reward-Principle (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-Super-49B-GenRM (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-Super-49B-GenRM + voting@32 (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-Super-49B-GenRM-Multilingual (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Llama-3.3-Nemotron-Super-49B-GenRM-Multilingual + voting@32 (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
LMvLM (gpt-4-turbo) (RAGTruth detector)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
local-jev Qwen3.5-4BAmith Chandrappa (amithgc) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
LPA-Ranking w/ Discriminator (Caption) (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
LPA-Ranking w/ Discriminator (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
LPA-Voting w/o Discriminator (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
LPA-Weighted-Voting (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
LPS (FinancialPhraseBank)Malo et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Free*
Not listed
Not listed
MAI-Transcribe-1.5Microsoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MAI-Transcribe-2Microsoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MAI-Transcribe-2-StreamingMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MAI-Voice-2-FlashMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MAI-Voice-2.1Microsoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MAI-Voice-2.1-FlashMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mair-hub 0.5B OmniMair Hub · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Malkuth-2Bnewfull5 (dhtocks) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Malkuth-4Bnewfull5 (dhtocks) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Manchego v2.1oraculumai · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Megrez-3B-OmniInfinigence AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mellum2.1-12B-A2.5B-ThinkingJetBrains · 128KScore not rankedCache not published · checked October 8, 2026
Free*
MERaLiON-AudioLLMAI Singapore · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
$0.25·$0.75
$0.40·$1.50
metask-jev-4bWayfind (metask-ai) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mica v0.1 4Bsky7350 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
mini-jevNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mini-Omni 0.5Bgpt-omni · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mini-Omni2gpt-omni · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MiniCPM-o 2.6OpenBMB · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
MiniMax M3.1 Flash PreviewMiniMax · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MiniMax Speech 2.8 HDMiniMax · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ministral 3 14B (Reasoning)Mistral · 256KScore not rankedCache not published · checked October 8, 2026
$0.20·$0.20
Ministral 3 3B (Reasoning)Mistral · 256KScore not rankedCache not published · checked October 8, 2026
$0.10·$0.10
Ministral 3 8B (Reasoning)Mistral · 256KScore not rankedCache not published · checked October 8, 2026
$0.15·$0.15
Not listed
Free*
Free*
Mistral Small 4 (Reasoning)Mistral · 256KScore not rankedCache not published · checked October 8, 2026
$0.15·$0.60
Mistral-7B-Instruct (RAGTruth generator)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Mixedbread mxbai-rerank-base-v2Mixedbread · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
mmastrac diffusiongemma (vLLM PR 57250)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
MNLI (Circa)Louis et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Moonshine TinyUseful Sensors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Murf Falcon 2Murf AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$1.25·$4.25
Muse Voice TranscribeMeta · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Needle 3 (2-bit)Cactus Compute · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Needle 3 (options as tools)Cactus Compute · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Nemotron 3 Super 120B A12BNVIDIA · 256KScore not rankedCache not published · checked October 8, 2026
Free*
Nemotron 3.5 ASR Streaming 0.6BNVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Nemotron Diffusion 8B (optimized vLLM)pst2154 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
NeoHorse-Jev-4BTokenRhythm · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
NExT-GPT 7BNExT-GPT authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
NInfer Qwen3.8-27B NVFP4Igor L. / NInfer contributors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
NInfer Qwen3.8-27B NVFP4 (T=1.5)Igor L. / NInfer contributors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
NInfer Qwen3.8-Flash-Next mixedIgor L. / NInfer contributors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
North Micro Vision InstructCohere · 128KScore not rankedCache not published · checked October 8, 2026
Free*
Free*
Not listed
NSM w/ LPA-guided ML + RL (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
NSM w/ RL (Binary Reward) (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$1.10·$4.40
Not listed
Not listed
OneJev 0.8BOmniJev · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Open Jev JSON CanvasJoshuaSP · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
open-alternative-jev Qwen3.5-4BIkerMoel · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
open-jev (pngwn)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Open-Jev 2BZefan Cai (@Zefan_Cai) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Open-Jev 9BZefan Cai (@Zefan_Cai) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
open-jev-deberta-v3-largeKotoba Labs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
OpenDecision ModernBERT-largeDeepan Wadhwa · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
OpenJev (thinking, BF16)razorback16 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
OpenJev DiffusionGemma 26B-A4B NVFP4razorback16 / Codiv · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
openJev VerdictHemant (heman10x) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
openJev Verdict 1.4Hemant (heman10x) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
openjev-sglang Qwen3.6-35B-A3Bekzhang · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
OpenSourceJev Qwen3.5-4B Q4_K_Msabeel111 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
openvonsNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Oracle NLI (BERT base ) binary subset (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Oracle NLI (BERT large ) binary subset (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
PandaGPT 7BPandaGPT authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
PandaLM-7B-v1 (JudgeBench)PandaLM authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Parakeet CTC 1.1BNVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Parakeet ReduxMoondream · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Parakeet TDT 0.6B v3NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Pareto 26.10 PreviewUnbiased · Context not listedScore not rankedCache $0.25/1M · checked October 8, 2026
$2.50·$7.50
$2.50·$7.50
Perplexity Decider v1 27BPerplexity · 262KScore not rankedCache not published · checked October 8, 2026
$0.02·$0.00
Perplexity Decider v1.1 (27B)Perplexity · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Phi-4 Multimodal InstructMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Phonon-1Fermion Research · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Phonon-2Fermion Research · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
$0.15·$1.00
pplx-embed-v2-late-0.6bPerplexity · 4096Score not rankedCache not published · checked October 8, 2026
Free*
Free*
Prometheus2-7b (JudgeBench)Prometheus authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Prometheus2-8x7b (JudgeBench)Prometheus authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Prometheus2-bgb-8x7b (JudgeBench)Prometheus authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Prompt (gpt-3.5-turbo) (RAGTruth detector)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Prompt (gpt-4-turbo) (RAGTruth detector)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Quyet-1.0-Largechinhnc · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Qwen-2.5-1B-RLCDharshatheg · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Qwen-2.5-Nemotron-32B-Reward (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen-3-Nemotron-32B-Reward (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Qwen-Audio 7BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen-Audio-Chat 7BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen2-Audio 7B InstructAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Qwen2.5-Omni 7BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Qwen3 235B 2507 (Reasoning)Alibaba · 128KScore not rankedCache not published · checked October 8, 2026
Free*
Qwen3-ASR 0.6BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3-ASR 1.7BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3-Nemotron-32B-GenRM-Principle (JudgeBench)NVIDIA · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3-Omni-30B-A3B-ThinkingAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3-Reranker-4BAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.60·$3.60
Qwen3.5-0.8B Decision ModelMourad Ghafiri · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3.5-9B Jev-like data-mix v2jsaurabh · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3.8 Max PreviewAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Qwen3.8-27B (Chutes TEE)Alibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Qwen4 Flash & PlusAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
R-LPS (FinancialPhraseBank)Malo et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Raw Phi-4 mini direct logitsMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Raw Qwen3 0.6B direct logitsAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Raw Qwen3 1.7B direct logitsAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Raw Qwen3 4B Instruct 2507 direct logitsAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Raw Qwen3 8B direct logitsAlibaba · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
razorback16 openjev diffusiongemma (NVFP4, vLLM)Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
reflex 4Bkshetrajna12 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
reflex-27bkshetrajna12 · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
RSI-Jev v5.0 VL 3Bshgao · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Ryotide Qwen v0.3.1Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
$5.00·$30.00
$0.95·$4.00
SALMONN 13BSALMONN authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SALMONN 7BSALMONN authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Scribe v2.2 RealtimeElevenLabs · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Not listed
Not listed
Not listed
Not listed
SeedRealtimeByteDance · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SelfCheckGPT (gpt-3.5-turbo) (RAGTruth detector)RAGTruth authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
SemIf Qwen3.5-4BTheodore Lee (TheoLeeCJ) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Sieve 2Bsthanika-ai · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Sieve 9Bsthanika-ai · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Sifr 0.8B v3.1Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
simple-jev · Qwen3.8-27BFeatherless AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SimpleJev Qwen3.5-0.8BFeatherless AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SimpleJev Qwen3.6-35B-A3BFeatherless AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SimpleJev Qwen3.8-27BFeatherless AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Skywork-Critic-Llama-3.1-70B (JudgeBench)Skywork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Skywork-Critic-Llama-3.1-8B (JudgeBench)Skywork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Skywork-Reward-Gemma-2-27B (JudgeBench)Skywork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Skywork-Reward-Llama-3.1-8B (JudgeBench)Skywork · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
smalljev semantic-v9Aditya (isHeSatoshi) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
$0.30·$1.20
Solomon v1.1Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Span NLI (BERT base ) binary subset (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Span NLI (BERT large ) binary subset (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Span TF-IDF+Cosine (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Span TF-IDF+SVM (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
spark-s1-4b-v6Abhishek Rai (abhishek085) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SpeechGPT 7BOpenMOSS · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SQuAD (BERT base ) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SQuAD (BERT large ) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Standard One 8BStandard Thinking · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Step-Audio-Chat 130BStepFun · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Surogate Rune 26B-A4B v3Surogate · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Surogate Rune 26B-A4B v3 (RTX PRO 6000)Surogate · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
SVM-MPQA (FinancialPhraseBank)Malo et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
Symbol (BERT base ) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Symbol (BERT large ) (ContractNLI)Koreeda and Manning · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
system-one Qwen3-8BSean Goedecke · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
system-one-gemmaNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
system-one-openmithalouni · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT (GNN-TabFact comparison)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT-Horizontal-F+T-Concatenate (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT-Horizontal-F+T-Template (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT-Horizontal-T+F-Template (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT-Vertical-F+T-Template (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Table-BERT-Vertical-T+F-Template (TabFact)TabFact authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Free*
Free*
Tev1-0.8B-experimentaltogethercomputer · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Tev1-4B-experimentaltogethercomputer · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
this-that 1.2Not listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.30·$0.72
Torchcast Decision 27BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
$0.25·$1.00
typecastlmMikhail Gribov · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Free*
Free*
Ultravox GLM-4P6Fixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox GLM-4P7Fixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox v0.4.1 Llama 3.1 8BFixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox v0.5 Llama 3.1 8BFixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox v0.5 Llama 3.2 1BFixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox v0.6 Llama 3.3 70BFixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Ultravox v0.7Fixie AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Vanilla (gpt-4o-2024-05-13) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Vanilla (Mistral-7B-v0.1-Instruct) (JudgeBench)JudgeBench evaluated system · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
verdict-smallManavarya09 (Manav) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
VertexAI Evaluation (gemini-1.5-pro-001) (JudgeBench)JudgeBench authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
VibeVoice-ASR-Streaming 1.5BMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
VibeVoice-ASR-Streaming 7BMicrosoft · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
vLLM-SR Decision 2.0 Eos 0.8BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
vLLM-SR Decision 2.0 Kai 0.6BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
vLLM-SR Decision 2.0 Lux 9BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
vLLM-SR Decision 2.0 Nox 4BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
vLLM-SR Decision 2.0 Sol 2BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
vLLM-SR Decision 2.0 Vega 27BNot listed · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Von 395Mwfzyx (Victor Hugo) · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Voxtral 4B TTS 2603Mistral AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Voxtral Mini 4B Realtime 2602Mistral AI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
W-Loughran (FinancialPhraseBank)Malo et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
W-MPQA (FinancialPhraseBank)Malo et al. · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Whisper large-v3-turboOpenAI · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Winnow-12B Q8Eldan Ring · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Winnow-E4BEldanRing · Context not listedScore not rankedCache not published · checked October 8, 2026
Free*
Not listed
XLM-R large (550M) (Belebele English fine-tuning)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
XLM-R large (550M) (Belebele Translate-Train-All)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
XLM-V large (1.2B) (Belebele English fine-tuning)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
XLM-V large (1.2B) (Belebele Translate-Train-All)Belebele authors · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Free*
Not listed
Free*
Free*
ZeroEntropy zerank-2ZeroEntropy · Context not listedScore not rankedCache not published · checked October 8, 2026
Not listed
Not listed
Not listed
* Score/$ = Overall benchmark score ÷ output price per million tokens. Higher is better. Free/open-weight models are excluded. “Price checked” is the registry observation date, not a claim that every provider changed its rate that day.
Best value by category
Best Value: Coding →Best Value: Agentic →Best Value: Reasoning →Best Value: Knowledge →Best Value: Math →Best Value: Multimodal →Best Value: Overall →
Below the top tier, the choice most teams actually face is Gemini 3.8 Flash or Claude Sonnet 5.5, compared on score and price.
Buying through a gateway or marketplace instead of a provider account? We paid seven of them to run the same workload and scored the invoices: OpenRouter alternatives, tested.
LLM API pricing calculator
Pick a starting workload or enter your own token counts. The result applies the current input, output, and published cache-hit rates from the pricing table below.
%
| Model | Per request | Per month | Input share | Output share | Cache treatment |
|---|---|---|---|---|---|
| DeepSeek V4.1 FlashDeepSeek | $0.0016 | $1.56 | $0.600 | $0.960 | Published: $0.006/1M |
| Grok 4.6xAI | $0.0088 | $8.80 | $4.00 | $4.80 | Published: $0.5/1M |
| Gemini 3.5 FlashGoogle | $0.010 | $10.20 | $3.00 | $7.20 | Published: $0.15/1M |
| Claude Sonnet 5Anthropic | $0.012 | $12.00 | $4.00 | $8.00 | Published: $0.2/1M |
| GPT-5.6 TerraOpenAI | $0.014 | $13.60 | $4.00 | $9.60 | Published: $0.2/1M |
Keep these assumptions with the decision. The estimate above is today’s list rates against the workload you typed; both move. Save it as a Radar cost scenario and the next review starts from the same numbers, with the source of every rate attached.
Estimate only. It excludes batch discounts, long-context surcharges, taxes, tools, images, and provider minimums. A cache share is applied only when the selected model has a published cache-hit rate. Pricing registry updated October 8, 2026.
The estimate depends on these assumptions
The rate card tells you what a token costs. Your workload decides how many paid tokens it takes to finish the job, and that is the number the calculator estimates. Keep the input, output and cache assumptions beside the estimate before you compare two models, because the same rate card produces a different bill for every workload.
The calculator applies one formula per model: uncached input tokens at the input rate, cached input tokens at the published cache-hit rate, output tokens at the output rate, each divided by one million. Requests per month multiplies everything. There is no hidden markup and no allowance for anything the provider bills separately.
What the calculation assumes
| Assumption | What the calculator does | What you should check |
|---|---|---|
| Input tokens per request | Multiplies by requests per month at the model’s input rate | Measure a real request, including the system prompt and any retrieved context |
| Output tokens per request | Multiplies by requests per month at the output rate | Output usually costs more per token than input; long answers move the bill faster than long prompts |
| Cache-hit share | Applies the published cache-hit rate to that share of input tokens | A share above zero only helps when your prompts repeat a stable prefix |
| Missing cache rate | Applies the standard input rate to every input token and shows “Standard input rate” in the cache column | A blank cache field means the registry has no published rate, not that caching is free or unavailable |
| Zero requests | Returns a zero estimate and says so | A zero bill describes zero traffic, not a free model |
| Blank, negative or non-numeric input | Uses 0 for the estimate and names the field to correct; your entry is kept | Re-enter the number; the estimate is only as good as the workload you typed |
One worked example, with invented rates
The two models below are hypothetical. Their rates are not a provider’s prices and do not appear in the table on this page. The workload is 20,000 requests a month, 1,500 input tokens and 400 output tokens per request, with 40% of input tokens served from cache.
| Hypothetical | Model A (hypothetical) | Model B (hypothetical) |
|---|---|---|
| Input rate per 1M tokens | $0.50 | $0.30 |
| Output rate per 1M tokens | $2.00 | $3.50 |
| Cache-hit rate per 1M tokens | $0.10 | Not published |
| Monthly input tokens | 30,000,000 | 30,000,000 |
| Monthly output tokens | 8,000,000 | 8,000,000 |
| Input cost | 18M × $0.50 + 12M × $0.10 = $10.20 | 30M × $0.30 = $9.00 (cache share ignored) |
| Output cost | 8M × $2.00 = $16.00 | 8M × $3.50 = $28.00 |
| Monthly estimate | $26.20 | $37.00 |
| Per request | $0.0013 | $0.0019 |
Model B has the lower input rate and the higher bill. Two things did that: output tokens cost more than input tokens on both cards, and Model B has no published cache rate, so the 40% cache share does nothing for it. Change the workload to 100 output tokens and the order can flip. That is the point of keeping the assumptions visible. We recomputed this table with the same function the calculator runs, so the figures match what the page would show for those inputs. They are arithmetic, not a saving anyone realised.
What the estimate leaves out
Retries, unless you enter them as extra requests. Reasoning tokens and tool charges that some models bill on top of the output count. Batch discounts, long-context surcharges, taxes, image inputs and provider minimums. Human review of the outputs, which is often the largest cost in a workload that needs an acceptable result rather than a response. The cheapest list rate is a shortlist, not a verdict: before you switch, run the candidates against a small fixed set of your own requests and count the outputs you would accept. The custom benchmark guide shows a repeatable way to get that number.
Confirm the setup you priced
The estimate is only valid for the exact model row. Copy the documented identifier from the model ID directory before it reaches production, and check the pricing history if the rate you priced was set more than a few weeks ago. The Radar placement on this page remains the way to follow published price changes for supported providers; it does not promise a cost alert for your own bill.
How to compare LLM API pricing
Start with the token mix your application actually sends. Monthly cost equals standard input, cached input, and output token charges across every request. A low input rate can still lose when the model produces long answers, misses the cache, or needs more retries to pass the same acceptance test.
Separate input from output
Output tokens usually cost more. Compare the ratio instead of averaging the two advertised rates.
Apply cache rates exactly
Use a cache discount only when the provider publishes one for that model and your prompts can reuse it.
Test cost against quality
Score/$ builds a shortlist. Your accepted result per dollar is the production number that matters.
A price only means something next to what it buys: GPT-6 Astra against Gemini 3.8 Flash sets the two side by side, benchmark by benchmark and rate by rate.
Pricing sources and field rules
Numeric rates come from provider-owned pricing pages, API documentation, or launch announcements for the exact model row. A missing cache field means the registry does not have an explicit cache-hit rate; it does not mean caching is unavailable or free. Tiered, reseller, and self-hosting rates stay separate.
LLM pricing updates and API price history
The live table is a current registry snapshot. Use the history view for dated model launches and price changes, or the token price index for a normalized view of how frontier inference cost moves over time.
LLM API pricing questions
How do I calculate LLM API cost?
LLM API cost equals input tokens multiplied by the input rate, plus output tokens multiplied by the output rate, divided by one million. Add cached input at the provider’s published cache rate. The calculator above applies that formula per request and per month across the models you select.
What is the cheapest LLM API in 2026?
As of October 8, 2026, Perplexity Decider v1 27B is the cheapest listed paid API at $0.02 input and $0.00 output per million tokens. The lowest list price is not automatically the lowest production cost: output volume, cache hits, retries, and task quality can change the result.
Which LLM has the best price-to-performance ratio?
On the current table, Qwen3.7 Flash has the highest public benchmark score per dollar of output. Score/$ is a shortlist metric, not a workload guarantee: it ignores latency, input-heavy prompts, hidden reasoning tokens, tool charges, and quality differences inside your own acceptance tests.
How does cached input pricing change LLM cost?
Cached input pricing discounts prompt tokens that a provider can reuse, such as a repeated system prompt or stable document context. The calculator applies the discount only when the exact model has a published cache-hit rate. A blank cache field does not mean caching is free or unavailable: when the rate is missing, the calculator charges every input token at the standard rate and labels the row “Standard input rate”.
Does the LLM pricing calculator include retries?
No. The estimate counts the requests you enter at the tokens you enter. A retried call is a second paid request, so add it to requests per month, or raise the per-request token counts if the retry resends the prompt. Reasoning and tool charges are also excluded unless the provider folds them into the output count.
Is the cheapest LLM API also the cheapest completed task?
Not necessarily. A low input rate loses when the model writes long answers, misses the cache or needs more retries to pass the same acceptance test. Compare cost per acceptable result on your own requests; the worked example on this page shows a lower input rate producing the higher monthly bill.
Are open-weight LLMs free to run?
Open-weight models can be free to download, but inference still requires GPUs, electricity, hosting, and engineering time. Hosted APIs for open models also charge per token. Compare the API table with the self-host estimate, then use the dedicated break-even calculator for your hardware, utilization, and traffic assumptions.
Get the weekly price-change file
Material API price changes, newly priced models, and deprecations that could change a production shortlist.
Read a sample issueJoin 5,500+ readers.
One email each week. Unsubscribe anytime.