NewPoint any agent at UberLLM — one key, every model, list price or less.
UberLLM

LLM API prices and speed, October 2026

39 numbers measured on UberLLM from 122,027 API requests to 143 models, October 19 – 31, 2026. Published November 1, 2026 and frozen: a number quoted from this page never changes. A number with too little data behind it is left out, never estimated.

Download CSVHow we measure

Volume and reliability

  1. From October 19 to 31, 2026, UberLLM handled 122,027 API requests to 143 models.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-requestsMethod

  2. From October 19 to 31, 2026, 0.8% of 120,845 requests to UberLLM failed because no seller was available, a seller was rate-limited or returned a server error, or the call timed out.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failure-rateMethod

  3. From October 19 to 31, 2026, 119,899 answered requests through UberLLM cost 71% less than the same tokens at list price.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-listMethod

Failure rate by model family

  1. From October 19 to 31, 2026, 0.0% of 95,369 requests to OpenAI models through UberLLM failed (no seller available, rate-limited, server error or timeout).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failures-openaiMethod

  2. From October 19 to 31, 2026, 2.8% of 15,470 requests to DeepSeek models through UberLLM failed (no seller available, rate-limited, server error or timeout).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failures-deepseekMethod

  3. From October 19 to 31, 2026, 0.4% of 3,444 requests to Google models through UberLLM failed (no seller available, rate-limited, server error or timeout).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failures-googleMethod

  4. From October 19 to 31, 2026, 0.3% of 2,545 requests to Meta models through UberLLM failed (no seller available, rate-limited, server error or timeout).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failures-meta-llamaMethod

  5. From October 19 to 31, 2026, 0.9% of 1,728 requests to MoonshotAI models through UberLLM failed (no seller available, rate-limited, server error or timeout).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-failures-moonshotaiMethod

Fastest seller per model

  1. From October 19 to 31, 2026, bedrock was the fastest of 3 sellers of Gemma 3 27B on UberLLM, with a median first token in 0.55 seconds against 0.60 seconds for openrouter (prompts under 8,000 tokens, 1,633 streamed requests).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-fastest-seller-google-gemma-3-27b-itMethod

  2. From October 19 to 31, 2026, venice was the fastest of 3 sellers of DeepSeek V4 Flash on UberLLM, with a median first token in 0.65 seconds against 0.97 seconds for bankr (prompts under 8,000 tokens, 1,081 streamed requests).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-fastest-seller-deepseek-deepseek-v4-flashMethod

Below list price

  1. From October 19 to 31, 2026, 95,232 requests to GPT-OSS 120B through UberLLM cost 96% less than the same tokens at list price ($0.18 against $4.87).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-openai-gpt-oss-120bMethod

  2. From October 19 to 31, 2026, 7,721 requests to DeepSeek V4.1 Flash 1017 through UberLLM cost 42% less than the same tokens at list price ($9.11 against $15.62).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-deepseek-deepseek-v4-1-flash-1017Method

  3. From October 19 to 31, 2026, 3,685 requests to DeepSeek V4.1 Flash through UberLLM cost 43% less than the same tokens at list price ($7.26 against $12.70).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-deepseek-deepseek-v4-1-flashMethod

  4. From October 19 to 31, 2026, 2,774 requests to Gemma 4 26B A4B IT through UberLLM cost 99% less than the same tokens at list price ($0.00061 against $0.065).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-google-gemma-4-26b-a4b-itMethod

  5. From October 19 to 31, 2026, 2,456 requests to Meta: Muse Spark 1.3 through UberLLM cost 99% less than the same tokens at list price ($2.07 against $207).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-meta-llama-muse-spark-1-3Method

  6. From October 19 to 31, 2026, 2,451 requests to DeepSeek V4 Flash through UberLLM cost 71% less than the same tokens at list price ($0.0030 against $0.010).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-deepseek-deepseek-v4-flashMethod

  7. From October 19 to 31, 2026, 1,129 requests to Kimi K3 through UberLLM cost 74% less than the same tokens at list price ($12.43 against $47.65).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-below-list-moonshotai-kimi-k3Method

Prices

  1. On October 31, 2026, GPT-OSS 120B cost $0.031 per 1M input tokens and $0.13 per 1M output tokens on UberLLM, 56% below its list price of $0.070 and $0.30.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-openai-gpt-oss-120bMethod

  2. On October 31, 2026, MiniMax M2.1 cost $0.027 per 1M input tokens and $0.11 per 1M output tokens on UberLLM, 91% below its list price of $0.30 and $1.20.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-minimax-minimax-m2-1Method

  3. On October 31, 2026, DeepSeek V4 Flash cost $0.071 per 1M input tokens and $0.14 per 1M output tokens on UberLLM, 22% below its list price of $0.091 and $0.18.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-deepseek-deepseek-v4-flashMethod

  4. On October 31, 2026, GPT 5 Mini cost $0.10 per 1M input tokens and $0.80 per 1M output tokens on UberLLM, 60% below its list price of $0.25 and $2.00.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-openai-gpt-5-miniMethod

  5. On October 31, 2026, Qwen 3 Coder 480B Turbo cost $0.31 per 1M input tokens and $1.32 per 1M output tokens on UberLLM, 12% below its list price of $0.35 and $1.50.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-qwen-qwen3-coder-turboMethod

  6. On October 31, 2026, Qwen3 Next 80B A3B cost $0.023 per 1M input tokens and $0.29 per 1M output tokens on UberLLM, 74% below its list price of $0.090 and $1.10.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-qwen-qwen3-next-80b-a3b-instructMethod

  7. On October 31, 2026, GPT-5.2 Codex cost $1.73 per 1M input tokens and $13.86 per 1M output tokens on UberLLM, 1.0% below its list price of $1.75 and $14.00.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-openai-gpt-5-2-codexMethod

  8. On October 31, 2026, Llama 3.3 70B Instruct cost $0.086 per 1M input tokens and $0.28 per 1M output tokens on UberLLM, 14% below its list price of $0.10 and $0.32.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-meta-llama-llama-3-3-70b-instructMethod

  9. On October 31, 2026, Claude Opus 4.6 cost $1.40 per 1M input tokens and $7.00 per 1M output tokens on UberLLM, 72% below its list price of $5.00 and $25.00.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-anthropic-claude-opus-4-6Method

  10. On October 31, 2026, Mistral Small 3.2 24B Instruct cost $0.052 per 1M input tokens and $0.14 per 1M output tokens on UberLLM, 30% below its list price of $0.075 and $0.20.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-price-mistralai-mistral-small-3-2-24b-instructMethod

Price gap between providers

  1. On October 31, 2026, the list price of MiniMax M2.1 input tokens ranged from $0.30 per 1M at OpenRouter to $0.35 at Venice AI across 3 providers, and UberLLM charged $0.027.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-minimax-minimax-m2-1Method

  2. On October 31, 2026, the list price of DeepSeek V4 Flash input tokens ranged from $0.091 per 1M at OpenRouter to $0.17 at Bankr across 4 providers, and UberLLM charged $0.071.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-deepseek-deepseek-v4-flashMethod

  3. On October 31, 2026, the list price of Qwen3 Next 80B A3B input tokens ranged from $0.090 per 1M at OpenRouter to $0.35 at Venice AI across 6 providers, and UberLLM charged $0.023.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-qwen-qwen3-next-80b-a3b-instructMethod

  4. On October 31, 2026, the list price of GPT-5.2 Codex input tokens ranged from $1.75 per 1M at Bankr to $2.19 at Venice AI across 3 providers, and UberLLM charged $1.73.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-openai-gpt-5-2-codexMethod

  5. On October 31, 2026, the list price of Llama 3.3 70B Instruct input tokens ranged from $0.10 per 1M at OpenRouter to $0.70 at Venice AI across 6 providers, and UberLLM charged $0.086.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-meta-llama-llama-3-3-70b-instructMethod

  6. On October 31, 2026, the list price of Claude Opus 4.6 input tokens ranged from $5.00 per 1M at Anthropic to $6.00 at Uncensored AI across 5 providers, and UberLLM charged $1.40.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-provider-gap-anthropic-claude-opus-4-6Method

Video price per second

  1. On October 31, 2026, Runway Gen-4.5 Text-to-Video (Venice) video cost from $0.16 per second on UberLLM (its lowest resolution).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-venice-runway-gen4-5-textMethod

  2. On October 31, 2026, Venice Video Gen (legacy alias) video cost from $0.16 per second on UberLLM (its lowest resolution).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-venice-video-genMethod

  3. On October 31, 2026, PixVerse C1 Text-to-Video (Venice) video cost from $0.070 per second on UberLLM (its lowest resolution).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-venice-pixverse-c1-t2vMethod

  4. On October 31, 2026, Seedance 2.0 Fast Text-to-Video (Venice) video cost from $0.059 per second on UberLLM (its lowest resolution), 61% below its list price of $0.15 per second.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-venice-seedance-2-fast-t2vMethod

  5. On October 31, 2026, PixVerse V5.6 Text-to-Video video cost from $0.23 per second on UberLLM (its lowest resolution).

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-pixverse-pixverse-v5-6-text-to-videoMethod

  6. On October 31, 2026, Kling 2.6 Pro Text-to-Video video cost from $0.055 per second on UberLLM (its lowest resolution), 64% below its list price of $0.15 per second.

    Cite this: UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10#fact-video-kling-kling-2-6-pro-text-to-videoMethod

Every number in this edition

The tables behind the facts. The same rows are in the CSV.

Prices on UberLLM

Per 1M tokens, what UberLLM charged and the official list price.

ModelInputOutputList inputList output
Aion 2.0$0.68$1.36$0.80$1.60
Aion 3.0$2.22$4.44$3.00$6.00
Aion 3.0 Mini$0.56$1.12$0.70$1.40
Aion 3.5$3.00$6.00$3.75$7.50
Aion 3.5 Mini$0.71$1.42$0.88$1.75
ByteDance Seed: Seed-2.0-Code$0.50$3.00$0.50$3.00
Claude Fable 5$4.70$23.50$10.00$50.00
Claude Fable 5.1$5.50$27.50$10.00$50.00
Claude Haiku 4.5$0.52$2.60$1.00$5.00
Claude Haiku 5.5$0.088$0.44$0.10$0.50
Claude Haiku 5.5 (batch)$0.050$0.25$0.050$0.25
Claude Opus 4.5$2.50$12.50$5.00$25.00
Claude Opus 4.6$1.40$7.00$5.00$25.00
Claude Opus 4.7$1.80$9.00$5.00$25.00
Claude Opus 4.8$2.20$11.00$5.00$25.00
Claude Opus 4.8 Fast$8.20$41.00$10.00$50.00
Claude Opus 5$2.85$14.25$5.00$25.00
Claude Opus 5 (Fast)$7.20$36.00$10.00$50.00
Claude Opus 5.5$2.72$13.60$4.00$20.00
Claude Sonnet 4.5$2.43$12.15$3.00$15.00
Claude Sonnet 4.6$1.83$9.15$3.00$15.00
Claude Sonnet 5$1.10$5.50$2.00$10.00
Claude Sonnet 5.5$1.62$8.10$2.00$10.00
Cohere: Command A+$0.30$1.50$0.30$1.50
DeepSeek V3.1$0.0050$0.019$0.25$0.95
DeepSeek V3.2$0.0052$0.0076$0.26$0.38
DeepSeek V4 Flash$0.071$0.14$0.091$0.18
DeepSeek V4 Flash 0731$0.039$0.079$0.12$0.24
DeepSeek V4 Flash 0731 Fast$0.29$0.59$0.35$0.70
DeepSeek V4 Flash E2EE$0.15$0.31$0.18$0.37
DeepSeek V4 Pro$0.56$1.12$1.60$3.20
DeepSeek V4 Pro 0813$0.059$0.18$0.66$1.98
DeepSeek V4.1 Flash$0.013$0.15$0.045$0.50
DeepSeek V4.1 Flash 1017$0.015$0.060$0.15$0.60
DeepSeek: DeepSeek V4 Flash Vision Exp$0.21$0.64$0.22$0.65
Devstral 2 123B$0.016$0.080$0.40$2.00
Elorian: Glimpse$0.60$3.00$0.60$3.00
Fireworks: Ember-1$3.00$15.00$3.00$15.00
GLM 4.5$0.012$0.044$0.60$2.20
GLM 4.5 Air$0.0026$0.017$0.13$0.85
GLM 4.7 Flash$0.0073$0.048$0.060$0.40
GLM 4.7 Thinking$0.34$1.50$0.45$2.00
GLM 5.1$0.35$1.10$1.40$4.40
GLM 5.2 E2EE$1.40$4.60$1.75$5.75
GLM 5.3$0.0049$0.098$0.070$1.40
GLM 5.3 Flash$0.0016$0.015$0.016$0.15
GLM 5V Turbo$1.18$3.92$1.20$4.00
GLM-4.6$0.021$0.087$0.43$1.75
GLM-4.7$0.21$0.77$0.54$1.98
GLM-5$0.39$1.25$1.00$3.20
GLM-5 Turbo$0.42$1.40$1.20$4.00
GLM-5.2$0.00072$0.53$0.0060$4.40
GPT 5 Mini$0.10$0.80$0.25$2.00
GPT 5 Nano$0.026$0.21$0.050$0.40
GPT 5.4 Nano$0.040$0.25$0.20$1.25
GPT OSS 120B$0.12$0.58$0.13$0.65
GPT OSS Safeguard 120B$0.0030$0.012$0.15$0.60
GPT OSS Safeguard 20B$0.00075$0.0030$0.075$0.30
GPT-4o$0.28$1.10$2.50$10.00
GPT-4o Mini$0.0075$0.030$0.15$0.60
GPT-5.2$0.16$1.26$1.75$14.00
GPT-5.2 Codex$1.73$13.86$1.75$14.00
GPT-5.3 Codex$1.29$10.36$1.75$14.00
GPT-5.4$1.27$7.65$2.50$15.00
GPT-5.4 Mini$0.17$0.99$0.75$4.50
GPT-5.4 Pro$20.40$122.40$30.00$180.00
GPT-5.5$1.65$9.90$5.00$30.00
GPT-5.5 Pro$25.50$153.00$30.00$180.00
GPT-5.6 Luna$0.074$0.44$0.20$1.20
GPT-5.6 Luna Pro$0.19$1.12$0.20$1.20
GPT-5.6 Sol$2.08$10.40$4.00$20.00
GPT-5.6 Sol Pro$3.08$15.40$4.00$20.00
GPT-5.6 Terra$1.32$7.92$2.00$12.00
GPT-5.6 Terra Pro$1.82$10.92$2.00$12.00
GPT-6 Astra$3.40$17.00$10.00$50.00
GPT-6 Luna$0.075$0.38$0.10$0.50
GPT-6 Luna Pro$0.10$0.50$0.10$0.50
GPT-6 Sol$0.94$4.70$2.00$10.00
GPT-6 Sol Pro$1.92$9.60$2.00$10.00
GPT-6.1 Sol$0.80$4.00$2.00$10.00
GPT-OSS 120B$0.031$0.13$0.070$0.30
GPT-OSS 20B$0.00018$0.00090$0.018$0.090
Gemini 2.5 Flash$0.036$0.30$0.30$2.50
Gemini 2.5 Pro$0.44$3.50$1.25$10.00
Gemini 3 Flash Preview$0.14$0.81$0.50$3.00
Gemini 3.1 Flash Lite$0.060$0.36$0.25$1.50
Gemini 3.1 Pro Preview$0.78$4.68$2.00$12.00
Gemini 3.5 Flash$0.24$1.44$1.50$9.00
Gemini 3.5 Flash Lite$0.10$0.88$0.30$2.50
Gemini 3.6 Flash$0.36$1.80$0.75$3.75
Gemini 3.7 Flash$0.21$1.05$0.75$3.75
Gemini 3.8 Flash$0.18$0.91$0.82$4.13
Gemma 3 12B IT$0.0010$0.0030$0.050$0.15
Gemma 3 27B$0.072$0.18$0.080$0.20
Gemma 3 4B IT$0.0010$0.0020$0.050$0.10
Gemma 4 26B A4B IT$0.018$0.059$0.068$0.23
Gemma 4 31B$0.0012$0.0036$0.12$0.36
Gemma 4 31B IT$0.014$0.043$0.12$0.36
Gemma 4 E2B$0.0024$0.0048$0.040$0.080
Google: Gemini 4 Argon$0.56$2.80$2.00$10.00
Grok 4.20 Beta$0.88$1.75$1.25$2.50
Grok 4.20 Multi-Agent Beta$1.11$2.23$1.25$2.50
Grok 4.3$0.84$1.68$1.25$2.50
Grok 4.5$1.04$3.12$2.00$6.00
Grok 4.6$1.58$4.74$2.00$6.00
Grok 4.7$1.68$5.04$2.00$6.00
Grok Build 0.1$0.87$1.74$1.00$2.00
Hermes 3 Llama 3.1 405b$0.84$0.84$1.00$1.00
Inception: Mercury 2.5$0.040$0.15$0.040$0.15
Kimi K2$0.45$1.82$0.57$2.30
Kimi K2 Thinking$0.030$0.13$0.60$2.50
Kimi K2.5$0.20$1.00$0.50$2.50
Kimi K2.6$0.052$0.27$0.65$3.41
Kimi K2.7 Code$0.31$1.79$0.60$3.50
Kimi K3$0.0077$0.60$0.19$15.00
Kimi K3 Fast$3.65$18.23$4.50$22.50
LiquidAI: LFM2.5-24B-A2B$0.050$0.70$0.050$0.70
Llama 3.2 3B$0.041$0.27$0.050$0.33
Llama 3.3 70B Instruct$0.086$0.28$0.10$0.32
Magistral Small 2509$0.010$0.030$0.50$1.50
Mercury 2$0.25$0.75$0.25$0.75
Mercury 3$0.084$0.29$0.10$0.35
Meta: Muse Glimmer 30B$0.30$1.20$0.30$1.20
Meta: Muse Spark 1.1$0.26$0.89$1.25$4.25
Meta: Muse Spark 1.2$0.33$1.10$1.25$4.25
Meta: Muse Spark 1.2 Contributor$0.067$0.13$0.10$0.20
Meta: Muse Spark 1.3$0.30$1.02$1.25$4.25
Meta: Muse Spark 1.3 Contributor$0.0060$0.012$0.10$0.20
Meta: Muse Spark Open$1.13$3.83$1.25$4.25
Meta: Muse Wonder$2.60$13.00$4.00$20.00
MiMo-V2.5$0.32$1.60$0.40$2.00
MiMo-V2.5-Pro$0.26$0.99$0.48$1.80
MiMo-V2.6-Flash$0.13$0.25$0.14$0.28
MiMo-V2.6-Pro$0.37$0.73$0.43$0.87
MiMo-V2.6-Pro-UltraSpeed$4.31$8.61$4.35$8.70
MiniMax M2$0.0051$0.020$0.26$1.02
MiniMax M2.1$0.027$0.11$0.30$1.20
MiniMax M2.5$0.022$0.076$0.27$0.95
MiniMax M2.7$0.17$0.66$0.30$1.20
MiniMax M3$0.29$1.18$0.30$1.20
MiniMax M3 Preview$0.25$0.98$0.30$1.20
MiniMax M3.1 Flash$0.088$0.35$0.15$0.60
Ministral 14B 3.0$0.010$0.010$0.20$0.20
Ministral 3 8B$0.0030$0.0030$0.15$0.15
Ministral 3B$0.0050$0.0050$0.10$0.10
Mistral Large$0.28$0.84$2.00$6.00
Mistral Large 3$0.070$0.21$0.50$1.50
Mistral Small 3.2 24B Instruct$0.052$0.14$0.075$0.20
Mistral Small 4$0.10$0.41$0.15$0.60
Mistral: Mistral Large 4$0.61$1.83$0.70$2.10
Moondream: Moondream 3 Preview$0.30$2.50$0.30$2.50
Moondream: Moondream 3.1$0.30$2.50$0.30$2.50
MoonshotAI: Kimi K3.1 Pro$0.62$3.10$2.00$10.00
NVIDIA Nemotron 3 Nano 30B$0.0015$0.0060$0.075$0.30
NVIDIA Nemotron 3 Super 120B$0.0030$0.024$0.30$2.40
NVIDIA Nemotron 3 Ultra 550B$0.49$2.47$0.63$3.13
NVIDIA Nemotron 3.5 Lightning 30B$0.070$0.20$0.070$0.20
NVIDIA Nemotron Nano 12B v2 VL BF16$0.0040$0.012$0.20$0.60
NVIDIA Nemotron Nano 9B v2$0.0018$0.0069$0.060$0.23
NVIDIA: Nemotron 3.5 Super VL$0.15$0.50$0.15$0.50
OpenAI: GPT-6.1 Sol Pro$1.92$9.60$2.00$10.00
OpenAI: GPT-6.1 Terra$0.39$1.95$1.00$5.00
OpenAI: GPT-6.1 Terra (batch)$0.50$2.50$0.50$2.50
OpenAI: GPT-6.1 Terra Pro$1.00$5.00$1.00$5.00
OpenAI: GPT-6.1 Terra Pro (batch)$0.50$2.50$0.50$2.50
Palmyra Vision 7B$0.0045$0.018$0.15$0.60
Pareto 26.9$2.50$7.50$2.50$7.50
Particle AI: Particle-1$0.050$0.50$0.050$0.50
Qwen 2.5 7B$0.050$0.13$0.050$0.13
Qwen 3 235B A22B Instruct 2507$0.0018$0.011$0.090$0.55
Qwen 3 235B A22B Thinking 2507$0.13$1.01$0.45$3.50
Qwen 3 Coder 480B Turbo$0.31$1.32$0.35$1.50
Qwen 3 Coder 480b$0.054$0.18$0.30$1.00
Qwen 3.5 35B A3B$0.12$0.80$0.15$1.00
Qwen 3.5 397B$0.34$2.45$0.50$3.60
Qwen 3.6 27B$0.14$1.13$0.33$2.70
Qwen 3.6 35B A3B$0.063$0.63$0.10$1.00
Qwen 3.6 35B A3B (E2EE)$0.14$0.92$0.18$1.18
Qwen 3.7 Plus$0.42$1.70$0.50$2.00
Qwen 3.8 27B$0.0020$0.12$0.040$2.30
Qwen 3.8 Max$1.07$3.23$2.50$7.50
Qwen3 30B A3B$0.094$0.39$0.12$0.50
Qwen3 32B$0.0016$0.0056$0.080$0.28
Qwen3 Coder 30B A3B Instruct$0.0014$0.0056$0.070$0.28
Qwen3 Coder Next$0.0048$0.032$0.12$0.80
Qwen3 Next 80B A3B$0.023$0.29$0.090$1.10
Qwen3 VL 235B$0.16$1.46$0.21$1.90
Qwen3 VL 235B A22B$0.0042$0.038$0.21$1.90
Qwen3 VL 30B A3B$0.20$0.72$0.25$0.90
Qwen3.7 Max$2.11$6.28$2.70$8.05
Qwen3.8 2.4T A95B$0.080$0.24$2.00$6.00
Qwen3.8 Flash$0.0060$0.019$0.15$0.47
Qwen: Qwen3.7 Flash$0.030$0.13$0.030$0.13
Qwen: Qwen3.8 Max (0902)$0.22$0.66$2.00$6.00
Qwen: Qwen3.8 Max Prime$4.00$12.00$4.00$12.00
Qwen: Qwen3.8 Omni Flash$0.10$0.32$0.15$0.47
Reflection: Beam 1.0 501B A23B$0.25$1.00$0.25$1.00
Sakana: Fugu Max$2.00$6.00$2.00$6.00
Sakana: Fugu Ultra v2$5.00$30.00$5.00$30.00
Sakana: Sakana Namazu$0.95$4.00$0.95$4.00
Seed 2.1 Turbo$0.35$1.75$0.50$2.50
Tencent HY3$0.034$0.14$0.13$0.53
Thinking Machines: Inkling$0.48$1.94$1.00$4.05
Trinity Large Thinking$0.30$1.00$0.30$1.00
Z.ai: GLM 5.3 FlashX$0.37$1.25$0.37$1.25
Z.ai: GLM 5.3 Prime$0.70$2.20$2.80$8.80
inclusionAI: Ling 3.1 Flash$0.075$0.23$0.075$0.23

List price by provider

Each provider’s official input price per 1M tokens.

ModelProviderList inputSample
Aion 2.0OpenRouter$0.802 providers
Aion 2.0Venice AI$1.002 providers
Aion 3.0OpenRouter$3.002 providers
Aion 3.0Venice AI$3.752 providers
Aion 3.0 MiniOpenRouter$0.702 providers
Aion 3.0 MiniVenice AI$0.882 providers
ByteDance Seed: Seed-2.0-CodeMorpheus$0.502 providers
ByteDance Seed: Seed-2.0-CodeOpenRouter$0.502 providers
Claude Fable 5OpenRouter$10.005 providers
Claude Fable 5Venice AI$10.005 providers
Claude Fable 5Amazon Bedrock$12.005 providers
Claude Fable 5Anthropic$12.005 providers
Claude Fable 5Bankr$12.005 providers
Claude Fable 5.1Anthropic$10.004 providers
Claude Fable 5.1Bankr$10.004 providers
Claude Fable 5.1OpenRouter$10.004 providers
Claude Fable 5.1Venice AI$10.004 providers
Claude Haiku 4.5Amazon Bedrock$1.003 providers
Claude Haiku 4.5Anthropic$1.003 providers
Claude Haiku 4.5Bankr$1.003 providers
Claude Haiku 5.5Anthropic$0.103 providers
Claude Haiku 5.5OpenRouter$0.103 providers
Claude Haiku 5.5Venice AI$0.103 providers
Claude Opus 4.5Anthropic$5.004 providers
Claude Opus 4.5Bankr$5.004 providers
Claude Opus 4.5OpenRouter$5.004 providers
Claude Opus 4.5Venice AI$5.004 providers
Claude Opus 4.6Anthropic$5.005 providers
Claude Opus 4.6Bankr$5.005 providers
Claude Opus 4.6OpenRouter$5.005 providers
Claude Opus 4.6Venice AI$5.005 providers
Claude Opus 4.6Uncensored AI$6.005 providers
Claude Opus 4.7Anthropic$5.006 providers
Claude Opus 4.7Bankr$5.006 providers
Claude Opus 4.7OpenRouter$5.006 providers
Claude Opus 4.7Venice AI$5.006 providers
Claude Opus 4.7Amazon Bedrock$6.006 providers
Claude Opus 4.7Uncensored AI$6.006 providers
Claude Opus 4.8Venice AI$5.005 providers
Claude Opus 4.8Amazon Bedrock$6.005 providers
Claude Opus 4.8Anthropic$6.005 providers
Claude Opus 4.8Bankr$6.005 providers
Claude Opus 4.8Uncensored AI$6.005 providers
Claude Opus 5Amazon Bedrock$5.005 providers
Claude Opus 5Anthropic$5.005 providers
Claude Opus 5Bankr$5.005 providers
Claude Opus 5OpenRouter$5.005 providers
Claude Opus 5Venice AI$5.005 providers
Claude Opus 5 (Fast)OpenRouter$10.002 providers
Claude Opus 5 (Fast)Venice AI$10.002 providers
Claude Opus 5.5Anthropic$4.004 providers
Claude Opus 5.5Mordiem$4.004 providers
Claude Opus 5.5OpenRouter$4.004 providers
Claude Opus 5.5Venice AI$4.004 providers
Claude Sonnet 4.5Anthropic$3.004 providers
Claude Sonnet 4.5Bankr$3.004 providers
Claude Sonnet 4.5OpenRouter$3.004 providers
Claude Sonnet 4.5Venice AI$3.754 providers
Claude Sonnet 4.6Bankr$3.005 providers
Claude Sonnet 4.6OpenRouter$3.005 providers
Claude Sonnet 4.6Venice AI$3.005 providers
Claude Sonnet 4.6Anthropic$3.605 providers
Claude Sonnet 4.6Uncensored AI$3.605 providers
Claude Sonnet 5Amazon Bedrock$2.006 providers
Claude Sonnet 5Anthropic$2.006 providers
Claude Sonnet 5Bankr$2.006 providers
Claude Sonnet 5OpenRouter$2.006 providers
Claude Sonnet 5Uncensored AI$2.006 providers
Claude Sonnet 5Venice AI$2.006 providers
Claude Sonnet 5.5OpenRouter$2.002 providers
Claude Sonnet 5.5Venice AI$2.002 providers
DeepSeek V3.2Bankr$0.267 providers
DeepSeek V3.2OpenRouter$0.267 providers
DeepSeek V3.2DeepSeek$0.287 providers
DeepSeek V3.2Amazon Bedrock$0.337 providers
DeepSeek V3.2Fireworks AI$0.337 providers
DeepSeek V3.2Together AI$0.337 providers
DeepSeek V3.2Venice AI$0.337 providers
DeepSeek V4 FlashOpenRouter$0.0914 providers
DeepSeek V4 FlashVenice AI$0.144 providers
DeepSeek V4 FlashMorpheus$0.154 providers
DeepSeek V4 FlashBankr$0.174 providers
DeepSeek V4 Flash 0731Engy.ai$0.0904 providers
DeepSeek V4 Flash 0731Fireworks AI$0.0904 providers
DeepSeek V4 Flash 0731Mordiem$0.0904 providers
DeepSeek V4 Flash 0731OpenRouter$0.124 providers
DeepSeek V4 ProMorpheus$1.604 providers
DeepSeek V4 ProOpenRouter$1.604 providers
DeepSeek V4 ProVenice AI$1.654 providers
DeepSeek V4 ProBankr$1.734 providers
DeepSeek V4 Pro 0813Bankr$0.436 providers
DeepSeek V4 Pro 0813Fireworks AI$0.436 providers
DeepSeek V4 Pro 0813Mordiem$0.436 providers
DeepSeek V4 Pro 0813Morpheus$0.436 providers
DeepSeek V4 Pro 0813OpenRouter$0.666 providers
DeepSeek V4 Pro 0813Venice AI$1.656 providers
DeepSeek V4.1 FlashOpenRouter$0.0457 providers
DeepSeek V4.1 FlashBankr$0.307 providers
DeepSeek V4.1 FlashDeepSeek$0.307 providers
DeepSeek V4.1 FlashMordiem$0.307 providers
DeepSeek V4.1 FlashMorpheus$0.307 providers
DeepSeek V4.1 FlashUncensored AI$0.307 providers
DeepSeek V4.1 FlashVenice AI$0.307 providers
GLM 4.7 FlashOpenRouter$0.0604 providers
GLM 4.7 FlashMorpheus$0.104 providers
GLM 4.7 FlashAmazon Bedrock$0.134 providers
GLM 4.7 FlashVenice AI$0.134 providers
GLM 5.1Z.ai$1.405 providers
GLM 5.1Morpheus$1.505 providers
GLM 5.1Venice AI$1.545 providers
GLM 5.1Bankr$1.755 providers
GLM 5.1Jatevo$1.755 providers
GLM 5.3OpenRouter$0.0705 providers
GLM 5.3Bankr$1.405 providers
GLM 5.3Morpheus$1.405 providers
GLM 5.3Z.ai$1.405 providers
GLM 5.3Venice AI$1.755 providers
GLM 5.3 FlashOpenRouter$0.0165 providers
GLM 5.3 FlashBankr$0.0755 providers
GLM 5.3 FlashMordiem$0.0755 providers
GLM 5.3 FlashZ.ai$0.0755 providers
GLM 5.3 FlashVenice AI$0.155 providers
GLM-4.6Venice AI$0.434 providers
GLM-4.6OpenRouter$0.504 providers
GLM-4.6Z.ai$0.604 providers
GLM-4.6Amazon Bedrock$0.854 providers
GLM-4.7Morpheus$0.505 providers
GLM-4.7OpenRouter$0.545 providers
GLM-4.7Venice AI$0.555 providers
GLM-4.7Z.ai$0.605 providers
GLM-4.7Amazon Bedrock$1.105 providers
GLM-5Bankr$0.728 providers
GLM-5Morpheus$1.008 providers
GLM-5OpenRouter$1.008 providers
GLM-5Venice AI$1.008 providers
GLM-5Z.ai$1.008 providers
GLM-5Amazon Bedrock$1.108 providers
GLM-5Fireworks AI$1.108 providers
GLM-5Together AI$1.108 providers
GLM-5 TurboBankr$1.203 providers
GLM-5 TurboVenice AI$1.203 providers
GLM-5 TurboZ.ai$1.203 providers
GLM-5.2OpenRouter$0.00609 providers
GLM-5.2Engy.ai$0.689 providers
GLM-5.2Bankr$1.209 providers
GLM-5.2Fireworks AI$1.209 providers
GLM-5.2Jatevo$1.209 providers
GLM-5.2Mistral AI$1.209 providers
GLM-5.2Morpheus$1.209 providers
GLM-5.2Z.ai$1.209 providers
GLM-5.2Venice AI$1.409 providers
GPT 5.4 NanoBankr$0.202 providers
GPT 5.4 NanoOpenAI$0.202 providers
GPT-4oOpenRouter$2.502 providers
GPT-4oVenice AI$2.502 providers
GPT-4o MiniOpenRouter$0.152 providers
GPT-4o MiniVenice AI$0.152 providers
GPT-5.2Bankr$1.754 providers
GPT-5.2OpenRouter$1.754 providers
GPT-5.2Venice AI$1.754 providers
GPT-5.2Jatevo$2.194 providers
GPT-5.2 CodexBankr$1.753 providers
GPT-5.2 CodexOpenRouter$1.753 providers
GPT-5.2 CodexVenice AI$2.193 providers
GPT-5.3 CodexOpenRouter$1.753 providers
GPT-5.3 CodexVenice AI$1.753 providers
GPT-5.3 CodexJatevo$2.193 providers
GPT-5.4Bankr$2.506 providers
GPT-5.4OpenRouter$2.506 providers
GPT-5.4Venice AI$2.506 providers
GPT-5.4Amazon Bedrock$3.136 providers
GPT-5.4Jatevo$3.136 providers
GPT-5.4OpenAI$3.136 providers
GPT-5.4 MiniBankr$0.755 providers
GPT-5.4 MiniOpenRouter$0.755 providers
GPT-5.4 MiniVenice AI$0.755 providers
GPT-5.4 MiniJatevo$0.945 providers
GPT-5.4 MiniOpenAI$0.945 providers
GPT-5.4 ProOpenRouter$30.003 providers
GPT-5.4 ProVenice AI$30.003 providers
GPT-5.4 ProOpenAI$37.503 providers
GPT-5.5Venice AI$5.004 providers
GPT-5.5Amazon Bedrock$6.254 providers
GPT-5.5Bankr$6.254 providers
GPT-5.5Jatevo$6.254 providers
GPT-5.6 LunaOpenRouter$0.204 providers
GPT-5.6 LunaVenice AI$0.204 providers
GPT-5.6 LunaAmazon Bedrock$1.004 providers
GPT-5.6 LunaBankr$1.004 providers
GPT-5.6 Luna ProOpenRouter$0.202 providers
GPT-5.6 Luna ProVenice AI$0.202 providers
GPT-5.6 SolOpenRouter$4.004 providers
GPT-5.6 SolVenice AI$4.004 providers
GPT-5.6 SolAmazon Bedrock$5.004 providers
GPT-5.6 SolBankr$5.004 providers
GPT-5.6 Sol ProOpenRouter$4.002 providers
GPT-5.6 Sol ProVenice AI$4.002 providers
GPT-5.6 TerraOpenRouter$2.004 providers
GPT-5.6 TerraVenice AI$2.004 providers
GPT-5.6 TerraAmazon Bedrock$2.504 providers
GPT-5.6 TerraBankr$2.504 providers
GPT-5.6 Terra ProOpenRouter$2.002 providers
GPT-5.6 Terra ProVenice AI$2.002 providers
GPT-6 AstraAmazon Bedrock$10.006 providers
GPT-6 AstraBankr$10.006 providers
GPT-6 AstraMordiem$10.006 providers
GPT-6 AstraOpenAI$10.006 providers
GPT-6 AstraOpenRouter$10.006 providers
GPT-6 AstraVenice AI$10.006 providers
GPT-6 LunaMordiem$0.104 providers
GPT-6 LunaOpenAI$0.104 providers
GPT-6 LunaOpenRouter$0.104 providers
GPT-6 LunaVenice AI$0.104 providers
GPT-6 SolMordiem$2.004 providers
GPT-6 SolOpenAI$2.004 providers
GPT-6 SolOpenRouter$2.004 providers
GPT-6 SolVenice AI$2.004 providers
GPT-6.1 SolOpenAI$2.003 providers
GPT-6.1 SolOpenRouter$2.003 providers
GPT-6.1 SolVenice AI$2.003 providers
GPT-OSS 120BAmazon Bedrock$0.0705 providers
GPT-OSS 120BFireworks AI$0.0705 providers
GPT-OSS 120BMorpheus$0.0705 providers
GPT-OSS 120BTogether AI$0.0705 providers
GPT-OSS 120BVenice AI$0.0705 providers
Gemini 2.5 FlashBankr$0.302 providers
Gemini 2.5 FlashGoogle$0.302 providers
Gemini 2.5 ProBankr$1.252 providers
Gemini 2.5 ProGoogle$1.252 providers
Gemini 3 Flash PreviewBankr$0.504 providers
Gemini 3 Flash PreviewOpenRouter$0.504 providers
Gemini 3 Flash PreviewGoogle$0.704 providers
Gemini 3 Flash PreviewVenice AI$0.704 providers
Gemini 3.1 Pro PreviewOpenRouter$2.003 providers
Gemini 3.1 Pro PreviewGoogle$2.503 providers
Gemini 3.1 Pro PreviewVenice AI$2.503 providers
Gemini 3.5 FlashBankr$1.505 providers
Gemini 3.5 FlashGoogle$1.505 providers
Gemini 3.5 FlashMordiem$1.505 providers
Gemini 3.5 FlashOpenRouter$1.505 providers
Gemini 3.5 FlashVenice AI$1.555 providers
Gemini 3.5 Flash LiteBankr$0.303 providers
Gemini 3.5 Flash LiteOpenRouter$0.303 providers
Gemini 3.5 Flash LiteVenice AI$0.383 providers
Gemini 3.6 FlashBankr$0.753 providers
Gemini 3.6 FlashOpenRouter$0.753 providers
Gemini 3.6 FlashVenice AI$0.943 providers
Gemini 3.7 FlashBankr$0.383 providers
Gemini 3.7 FlashOpenRouter$0.753 providers
Gemini 3.7 FlashVenice AI$0.943 providers
Gemini 3.8 FlashBankr$0.754 providers
Gemini 3.8 FlashMordiem$0.754 providers
Gemini 3.8 FlashOpenRouter$0.824 providers
Gemini 3.8 FlashVenice AI$0.944 providers
Gemma 3 27BOpenRouter$0.0806 providers
Gemma 3 27BVenice AI$0.126 providers
Gemma 3 27BAmazon Bedrock$0.146 providers
Gemma 3 27BFireworks AI$0.146 providers
Gemma 3 27BGoogle$0.146 providers
Gemma 3 27BTogether AI$0.146 providers
Gemma 4 26B A4B ITBankr$0.135 providers
Gemma 4 26B A4B ITVenice AI$0.135 providers
Gemma 4 26B A4B ITMorpheus$0.155 providers
Gemma 4 26B A4B ITAmazon Bedrock$0.165 providers
Gemma 4 26B A4B ITJatevo$0.165 providers
Gemma 4 31B ITVenice AI$0.124 providers
Gemma 4 31B ITBankr$0.144 providers
Gemma 4 31B ITMorpheus$0.154 providers
Gemma 4 31B ITJatevo$0.174 providers
Grok 4.20 BetaOpenRouter$1.253 providers
Grok 4.20 BetaVenice AI$1.423 providers
Grok 4.20 BetaBankr$2.003 providers
Grok 4.20 Multi-Agent BetaOpenRouter$1.252 providers
Grok 4.20 Multi-Agent BetaVenice AI$1.422 providers
Grok 4.3Amazon Bedrock$1.423 providers
Grok 4.3Bankr$1.423 providers
Grok 4.3Venice AI$1.423 providers
Grok 4.5Bankr$2.003 providers
Grok 4.5OpenRouter$2.003 providers
Grok 4.5Venice AI$2.273 providers
Grok 4.6Bankr$2.004 providers
Grok 4.6Mordiem$2.004 providers
Grok 4.6OpenRouter$2.004 providers
Grok 4.6Venice AI$2.274 providers
Hermes 3 Llama 3.1 405bFireworks AI$1.103 providers
Hermes 3 Llama 3.1 405bTogether AI$1.103 providers
Hermes 3 Llama 3.1 405bVenice AI$1.103 providers
Kimi K2 ThinkingOpenRouter$0.604 providers
Kimi K2 ThinkingAmazon Bedrock$0.754 providers
Kimi K2 ThinkingMorpheus$0.754 providers
Kimi K2 ThinkingVenice AI$0.754 providers
Kimi K2.5Bankr$0.456 providers
Kimi K2.5OpenRouter$0.506 providers
Kimi K2.5Amazon Bedrock$0.566 providers
Kimi K2.5Together AI$0.566 providers
Kimi K2.5Venice AI$0.566 providers
Kimi K2.5Morpheus$0.606 providers
Kimi K2.6Morpheus$0.505 providers
Kimi K2.6OpenRouter$0.655 providers
Kimi K2.6Venice AI$0.755 providers
Kimi K2.6Bankr$0.855 providers
Kimi K2.6Fireworks AI$0.855 providers
Kimi K2.7 CodeOpenRouter$0.606 providers
Kimi K2.7 CodeBankr$0.686 providers
Kimi K2.7 CodeFireworks AI$0.686 providers
Kimi K2.7 CodeJatevo$0.686 providers
Kimi K2.7 CodeMorpheus$0.686 providers
Kimi K2.7 CodeVenice AI$0.756 providers
Kimi K3OpenRouter$0.196 providers
Kimi K3Engy.ai$1.506 providers
Kimi K3Bankr$3.006 providers
Kimi K3Fireworks AI$3.006 providers
Kimi K3Morpheus$3.006 providers
Kimi K3Venice AI$3.756 providers
Llama 3.2 3BOpenRouter$0.0506 providers
Llama 3.2 3BMorpheus$0.106 providers
Llama 3.2 3BFireworks AI$0.156 providers
Llama 3.2 3BGroq$0.156 providers
Llama 3.2 3BTogether AI$0.156 providers
Llama 3.2 3BVenice AI$0.156 providers
Llama 3.3 70B InstructOpenRouter$0.106 providers
Llama 3.3 70B InstructFireworks AI$0.706 providers
Llama 3.3 70B InstructGroq$0.706 providers
Llama 3.3 70B InstructMorpheus$0.706 providers
Llama 3.3 70B InstructTogether AI$0.706 providers
Llama 3.3 70B InstructVenice AI$0.706 providers
Mercury 3OpenRouter$0.102 providers
Mercury 3Venice AI$0.102 providers
Meta: Muse Glimmer 30BOpenRouter$0.302 providers
Meta: Muse Glimmer 30BFireworks AI$0.352 providers
MiMo-V2.5Mordiem$0.144 providers
MiMo-V2.5Morpheus$0.144 providers
MiMo-V2.5OpenRouter$0.404 providers
MiMo-V2.5Venice AI$0.404 providers
MiMo-V2.5-ProMorpheus$0.432 providers
MiMo-V2.5-ProOpenRouter$0.482 providers
MiMo-V2.6-FlashOpenRouter$0.142 providers
MiMo-V2.6-FlashUncensored AI$0.142 providers
MiniMax M2.1OpenRouter$0.303 providers
MiniMax M2.1Amazon Bedrock$0.353 providers
MiniMax M2.1Venice AI$0.353 providers
MiniMax M2.5OpenRouter$0.276 providers
MiniMax M2.5Venice AI$0.276 providers
MiniMax M2.5Bankr$0.306 providers
MiniMax M2.5Morpheus$0.306 providers
MiniMax M2.5Amazon Bedrock$0.346 providers
MiniMax M2.5Together AI$0.346 providers
MiniMax M2.7Bankr$0.304 providers
MiniMax M2.7OpenRouter$0.304 providers
MiniMax M2.7Morpheus$0.354 providers
MiniMax M2.7Venice AI$0.384 providers
MiniMax M3Bankr$0.403 providers
MiniMax M3Fireworks AI$0.403 providers
MiniMax M3Mordiem$0.403 providers
MiniMax M3.1 FlashOpenRouter$0.154 providers
MiniMax M3.1 FlashMordiem$0.194 providers
MiniMax M3.1 FlashTogether AI$0.194 providers
MiniMax M3.1 FlashVenice AI$0.194 providers
Mistral LargeFireworks AI$0.504 providers
Mistral LargeMistral AI$0.504 providers
Mistral LargeTogether AI$0.504 providers
Mistral LargeOpenRouter$2.004 providers
Mistral Small 3.2 24B InstructOpenRouter$0.0757 providers
Mistral Small 3.2 24B InstructFireworks AI$0.0947 providers
Mistral Small 3.2 24B InstructGroq$0.0947 providers
Mistral Small 3.2 24B InstructMistral AI$0.0947 providers
Mistral Small 3.2 24B InstructTogether AI$0.0947 providers
Mistral Small 3.2 24B InstructVenice AI$0.0947 providers
Mistral Small 3.2 24B InstructMorpheus$0.507 providers
Mistral Small 4OpenRouter$0.152 providers
Mistral Small 4Venice AI$0.192 providers
MoonshotAI: Kimi K3.1 ProOpenRouter$2.002 providers
MoonshotAI: Kimi K3.1 ProVenice AI$3.752 providers
NVIDIA Nemotron 3 Nano 30BAmazon Bedrock$0.0752 providers
NVIDIA Nemotron 3 Nano 30BVenice AI$0.0752 providers
NVIDIA Nemotron 3 Ultra 550BFireworks AI$0.502 providers
NVIDIA Nemotron 3 Ultra 550BJatevo$0.502 providers
NVIDIA Nemotron 3.5 Lightning 30BFireworks AI$0.102 providers
NVIDIA Nemotron 3.5 Lightning 30BVenice AI$0.102 providers
NVIDIA: Nemotron 3.5 Super VLOpenRouter$0.152 providers
NVIDIA: Nemotron 3.5 Super VLTogether AI$0.152 providers
OpenAI: GPT-6.1 TerraMordiem$1.005 providers
OpenAI: GPT-6.1 TerraOpenAI$1.005 providers
OpenAI: GPT-6.1 TerraOpenRouter$1.005 providers
OpenAI: GPT-6.1 TerraUncensored AI$1.005 providers
OpenAI: GPT-6.1 TerraVenice AI$1.005 providers
Qwen 3 235B A22B Instruct 2507OpenRouter$0.0906 providers
Qwen 3 235B A22B Instruct 2507Amazon Bedrock$0.156 providers
Qwen 3 235B A22B Instruct 2507Fireworks AI$0.156 providers
Qwen 3 235B A22B Instruct 2507Together AI$0.156 providers
Qwen 3 235B A22B Instruct 2507Venice AI$0.156 providers
Qwen 3 235B A22B Instruct 2507Morpheus$0.406 providers
Qwen 3 235B A22B Thinking 2507OpenRouter$0.453 providers
Qwen 3 235B A22B Thinking 2507Together AI$0.453 providers
Qwen 3 235B A22B Thinking 2507Venice AI$0.453 providers
Qwen 3 Coder 480bOpenRouter$0.305 providers
Qwen 3 Coder 480bBankr$0.605 providers
Qwen 3 Coder 480bAmazon Bedrock$0.755 providers
Qwen 3 Coder 480bTogether AI$0.755 providers
Qwen 3 Coder 480bVenice AI$0.755 providers
Qwen 3.5 35B A3BVenice AI$0.152 providers
Qwen 3.5 35B A3BMorpheus$0.312 providers
Qwen 3.7 PlusFireworks AI$0.502 providers
Qwen 3.7 PlusMordiem$0.502 providers
Qwen 3.8 27BOpenRouter$0.0402 providers
Qwen 3.8 27BVenice AI$0.452 providers
Qwen 3.8 MaxFireworks AI$2.502 providers
Qwen 3.8 MaxVenice AI$2.502 providers
Qwen3 30B A3BOpenRouter$0.124 providers
Qwen3 30B A3BFireworks AI$0.194 providers
Qwen3 30B A3BTogether AI$0.194 providers
Qwen3 30B A3BVenice AI$0.194 providers
Qwen3 Next 80B A3BOpenRouter$0.0906 providers
Qwen3 Next 80B A3BMorpheus$0.156 providers
Qwen3 Next 80B A3BAmazon Bedrock$0.356 providers
Qwen3 Next 80B A3BFireworks AI$0.356 providers
Qwen3 Next 80B A3BTogether AI$0.356 providers
Qwen3 Next 80B A3BVenice AI$0.356 providers
Qwen3 VL 235BVenice AI$0.213 providers
Qwen3 VL 235BTogether AI$0.253 providers
Qwen3 VL 235BOpenRouter$0.263 providers
Qwen3 VL 30B A3BTogether AI$0.253 providers
Qwen3 VL 30B A3BVenice AI$0.253 providers
Qwen3 VL 30B A3BOpenRouter$0.293 providers
Qwen3.8 2.4T A95BFireworks AI$2.006 providers
Qwen3.8 2.4T A95BMordiem$2.006 providers
Qwen3.8 2.4T A95BOpenRouter$2.006 providers
Qwen3.8 2.4T A95BTogether AI$2.006 providers
Qwen3.8 2.4T A95BUncensored AI$2.006 providers
Qwen3.8 2.4T A95BVenice AI$2.506 providers
Qwen3.8 FlashOpenRouter$0.152 providers
Qwen3.8 FlashBankr$0.162 providers
Seed 2.1 TurboOpenRouter$0.502 providers
Seed 2.1 TurboVenice AI$0.632 providers
Trinity Large ThinkingMorpheus$0.302 providers
Trinity Large ThinkingVenice AI$0.312 providers

Time to first token by seller

Median, streamed requests with prompts under 8,000 tokens.

ModelSellerMedianSample
Claude Sonnet 5.5openrouter5.0 s101 streamed requests
DeepSeek V4 Flashvenice0.65 s328 streamed requests
DeepSeek V4 Flashopenrouter0.76 s541 streamed requests
DeepSeek V4 Flashbankr0.97 s212 streamed requests
DeepSeek V4 Prodashscope-cn1.7 s256 streamed requests
DeepSeek V4.1 Flashdashscope-cn0.99 s2,838 streamed requests
DeepSeek V4.1 Flash 1017dashscope-cn0.94 s868 streamed requests
GLM 5.3 Flashzai1.2 s105 streamed requests
GLM-5.2dashscope-cn0.95 s160 streamed requests
GPT OSS Safeguard 20Bbedrock0.40 s453 streamed requests
GPT-OSS 120Bbedrock0.37 s378 streamed requests
GPT-OSS 20Bbedrock0.39 s110 streamed requests
Gemini 2.5 Flashgoogle0.86 s1,570 streamed requests
Gemini 3.5 Flash Liteopenrouter0.67 s195 streamed requests
Gemma 3 27Bbedrock0.55 s1,096 streamed requests
Gemma 3 27Bvenice0.60 s126 streamed requests
Gemma 3 27Bopenrouter0.60 s411 streamed requests
Kimi K3dashscope-cn1.3 s453 streamed requests
MiniMax M2.5bedrock0.47 s124 streamed requests
MiniMax M2.7venice0.60 s341 streamed requests
Mistral: Mistral Large 4openrouter0.95 s143 streamed requests
MoonshotAI: Kimi K3.1 Prodashscope-cn3.1 s177 streamed requests
Qwen 3.5 35B A3Bvenice0.52 s198 streamed requests
Qwen 3.7 Plusvenice1.7 s185 streamed requests
Qwen3.7 Maxvenice1.6 s199 streamed requests

Failure rate

No seller available, rate-limited, server error or timeout.

ModelFailedSample
All models0.8%120,845 requests
OpenAI models0.0%95,369 requests
DeepSeek models2.8%15,470 requests
Google models0.4%3,444 requests
Meta models0.3%2,545 requests
MoonshotAI models0.9%1,728 requests

Below list price

What callers paid against the same tokens at list price.

ModelBelow listSample
All models71%119,899 requests
GPT-OSS 120B96%95,232 requests
DeepSeek V4.1 Flash 101742%7,721 requests
DeepSeek V4.1 Flash43%3,685 requests
Gemma 4 26B A4B IT99%2,774 requests
Meta: Muse Spark 1.399%2,456 requests
DeepSeek V4 Flash71%2,451 requests
Kimi K374%1,129 requests

Video price per second

Per second of generated video, at the model’s lowest resolution.

ModelPriceList price
Gemini Omni Flash$0.079
Gemini Omni Flash (image-to-video)$0.079$0.14
Gemini Omni Flash (reference-to-video)$0.14
Gemini Omni Flash 1.1$0.079
Grok Imagine$0.012
Grok Imagine 1.5 Image To Video Private (image-to-video)$0.090
Grok Imagine Image To Video Private (image-to-video)$0.060
Grok Imagine Reference To Video Private (reference-to-video)$0.060
Grok Imagine Text-to-Video$0.012$0.088
Grok Imagine Video 1.5$0.012
Hailuo 02 Pro$0.048
Hailuo 02 Standard Image to Video$0.010$0.017
Hailuo 02 Standard Text to Video$0.025$0.045
Hailuo 2.3 Pro$0.045
Hailuo 2.3 Standard$0.025
HappyHorse 1.0 Text-to-Video$0.14$0.26
HappyHorse 1.1$0.11
Happyhorse 1.0 (image-to-video)$0.14$0.15
Happyhorse 1.0 (reference-to-video)$0.15
Happyhorse 1.1 (image-to-video)$0.11$0.15
Happyhorse 1.1 (reference-to-video)$0.11$0.15
Kling 2.1 Standard$0.025
Kling 2.5 Turbo Pro (image-to-video)$0.042$0.078
Kling 2.5 Turbo Pro Text-to-Video$0.042$0.078
Kling 2.6 Pro (image-to-video)$0.055$0.15
Kling 2.6 Pro Image to Video$0.042$0.070
Kling 2.6 Pro Text to Video$0.042$0.070
Kling 2.6 Pro Text-to-Video$0.055$0.15
Kling 3 Pro Image to Video$0.067$0.11
Kling 3 Pro Text to Video$0.067$0.11
Kling 3 Standard Image to Video$0.050$0.084
Kling 3 Standard Text to Video$0.050$0.084
Kling 3.0 Turbo$0.090
Kling 4.0$0.14
Kling 4.0 Reference$0.14
Kling O3 4K Text-to-Video$0.46
Kling O3 Pro (image-to-video)$0.090$0.15
Kling O3 Pro (reference-to-video)$0.090$0.15
Kling O3 Pro Text-to-Video$0.090$0.15
Kling O3 Standard (image-to-video)$0.070$0.12
Kling O3 Standard (reference-to-video)$0.070$0.12
Kling O3 Standard Image to Video$0.050$0.084
Kling O3 Standard Text to Video$0.050$0.084
Kling O3 Standard Text-to-Video$0.070$0.12
Kling O3.4k (image-to-video)$0.46
Kling O3.4k (reference-to-video)$0.46
Kling V3 4K Text-to-Video$0.46
Kling V3 Pro (image-to-video)$0.16$0.18
Kling V3 Pro Text-to-Video$0.18
Kling V3 Standard (image-to-video)$0.14
Kling V3 Standard Text-to-Video$0.14
Kling V3 Turbo Pro (image-to-video)$0.15
Kling V3 Turbo Standard (image-to-video)$0.12
Kling V3.4k (reference-to-video)$0.46
LTX 2 19B Full Text-to-Video$0.088
LTX 2 Fast Text-to-Video$0.067
LTX 2 Full Text-to-Video$0.088
LTX 2 v2.3 Fast Text-to-Video$0.067
LTX 2 v2.3 Full Text-to-Video$0.088
LTX 2.3 Fast Image to Video$0.036$0.060
LTX 2.3 Fast Text to Video$0.036$0.060
LTX 2.3 Text to Video$0.048$0.080
LongCat Distilled Text-to-Video$0.018
LongCat Text-to-Video$0.050
Longcat (image-to-video)$0.050
Longcat Distilled (image-to-video)$0.015$0.018
Ltx 2 V2.3 Fast (image-to-video)$0.067
Ltx 2 V2.3 Full (image-to-video)$0.088
MiniMax H3$0.040
MiniMax H3 Reference$0.040
Ovi Image-to-Video$0.044
PixVerse C1 Text-to-Video (Venice)$0.070
PixVerse V5.6 Text-to-Video$0.23
PixVerse V6$0.020
PixVerse V6 Fusion$0.020
PixVerse V6 Max$0.024
Pixverse C1 (image-to-video)$0.043
Pixverse C1 (reference-to-video)$0.043
Pixverse C1 Transition (transition)$0.043
Pixverse V5.6 (image-to-video)$0.20
Pixverse V5.6 Transition (transition)$0.20
Runway Gen-4 Turbo$0.068
Runway Gen-4.5$0.16
Runway Gen-4.5 Text-to-Video (Venice)$0.16
Seedance 1.0 Pro$0.014
Seedance 1.0 Pro Fast$0.018
Seedance 1.5 Pro (image-to-video)$0.034
Seedance 1.5 Pro Text-to-Video$0.058
Seedance 2.0 (image-to-video)$0.088
Seedance 2.0 (reference-to-video)$0.075$0.088
Seedance 2.0 Fast (image-to-video)$0.059$0.070
Seedance 2.0 Fast (reference-to-video)$0.070
Seedance 2.0 Fast Text-to-Video (Venice)$0.059$0.15
Seedance 2.0 Mini (image-to-video)$0.019$0.044
Seedance 2.0 Mini (reference-to-video)$0.044
Seedance 2.0 Text-to-Video$0.095$0.19
Seedance 2.5$0.14
Seedance 2.5 Image-to-Video$0.14
Seedance 2.5 Reference-to-Video$0.14
Seedance 2.5 Text-to-Video$0.14
Sora 2 (image-to-video)$0.11
Sora 2 Pro (image-to-video)$0.33
Venice Video Gen (legacy alias)$0.16
Veo 3 Fast Text-to-Video$0.17
Veo 3 Full Text-to-Video$0.44
Veo 3.1 Fast Image to Video$0.060$0.10
Veo 3.1 Fast Text to Video$0.060$0.10
Veo 3.1 Fast Text-to-Video$0.16$0.17
Veo 3.1 Full Text-to-Video$0.44
Veo 3.1 Image to Video$0.12$0.20
Veo 3.1 Lite Text to Video$0.018$0.030
Veo 3.1 Text to Video$0.12$0.20
Veo3.1 Fast (image-to-video)$0.17
Veo3.1 Full (image-to-video)$0.44
Vidu Q3 (image-to-video)$0.090
Vidu Q3 Image to Video$0.042$0.070
Vidu Q3 Text to Video$0.042$0.070
Vidu Q3 Text-to-Video$0.19
Vidu Q3 Turbo Image to Video$0.021$0.035
Vidu Q3 Turbo Text to Video$0.021$0.035
Vidu Q4$0.036
Vidu Q4 Reference$0.036
Wan 2.1 Pro Image-to-Video$0.15
Wan 2.2 A14B Turbo$0.040
Wan 2.5 Preview (image-to-video)$0.056
Wan 2.5 Preview Text-to-Video$0.060$0.11
Wan 2.6 (image-to-video)$0.070$0.11
Wan 2.6 Flash Image-to-Video$0.020$0.056
Wan 2.6 Text-to-Video$0.070$0.17
Wan 2.6 Ultra (image-to-video)$0.30
Wan 2.7 (image-to-video)$0.080$0.11
Wan 2.7 (reference-to-video)$0.080$0.11
Wan 2.7 Image to Video$0.060$0.10
Wan 2.7 Pro (image-to-video)$0.12
Wan 2.7 Text to Video$0.060$0.10
Wan 2.7 Text-to-Video$0.080$0.11
Wan 3.0$0.040
Wan 3.0 Prime$0.061

How we measure

Every number comes from UberLLM’s own records for October 19 – 31, 2026: the 122,027 API requests callers sent to UberLLM, the log of which seller answered each one, and a daily copy of the public model catalog. Nothing is estimated, sampled from another source or edited by hand.

Prices are as listed on October 31, 2026, the last day of the month we priced: what UberLLM charged per 1M tokens (or per second of video) and each model’s official list price. A price change is reported when the first and last price of the month are at least 14 days apart and differ by 5% or more. A video price is per second of video at the model’s lowest resolution; a job costs that rate times its length.

Time to first token is the median (and 90th percentile) over streamed requests with prompts under 8,000 tokens, because a long prompt takes longer to read on every seller. A model needs 300 such requests and a seller 100.

A request failed when no seller answered it: none was available, the seller was rate-limited or returned a server error, or the call timed out. Requests refused because of the caller (a bad request, a missing key, no credit) and calls the caller cancelled are not counted either way. A family needs 1,000 requests.

Below list price compares what callers paid UberLLM for 1,000 or more answered requests to a model with what the same tokens cost at the model’s official list price on the day the edition was built.

An edition is published on the 1st of the next month, only when the month had at least 7 days of data and 20 numbers passed their minimum. It is then frozen.

Cite this edition

UberLLM, "LLM API price and speed stats, October 2026", uberllm.dev/stats/2026-10

Free to reuse with a link (CC BY 4.0). Data: CSV · JSON