LLM API price changes — Per Millionhttps://aobaworks.com/per-million/changes/enThu, 22 Oct 2026 00:00:00 +0000720New items in LLM API price changes (up to 50, updated daily). Always check the official notice. Data: LiteLLM model price list (MIT License). Unofficial.Data: LiteLLM model price list (MIT License). Unofficial.deepseek-v4p1-flash-1017-us (Fireworks AI): newly listed at $0.45 input / $1.80 output per 1M tokenshttps://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-deepseek-v4p1-flash-1017-us/https://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-deepseek-v4p1-flash-1017-us/Thu, 22 Oct 2026 00:00:00 +0000Recorded between 2026-10-21 and 2026-10-22.minimax-m3p1-flash (Fireworks AI): newly listed at $0.15 input / $0.60 output per 1M tokenshttps://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-minimax-m3p1-flash/https://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-minimax-m3p1-flash/Wed, 21 Oct 2026 00:00:00 +0000Recorded between 2026-10-20 and 2026-10-21.Beam-1.0-501B-A23B (Together AI): newly listed at $0.40 input / $1.20 output per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--reflection-beam-1-0-501b-a23b/https://aobaworks.com/per-million/model/together-ai--reflection-beam-1-0-501b-a23b/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Qwen3.7-Max (Together AI): output price cut, $7.50 → $4.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Qwen3.7-Max (Together AI): input price cut, $2.50 → $1.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Qwen3.7-Max (Together AI): cached input price cut, $0.50 → $0.30 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.NVIDIA-Nemotron-3.5-Super-VL (Together AI): newly listed at $0.15 input / $0.50 output per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--nvidia-nvidia-nemotron-3-5-super-vl/https://aobaworks.com/per-million/model/together-ai--nvidia-nvidia-nemotron-3-5-super-vl/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Kimi-K3 (Together AI): output price raised, $13.50 → $15.00 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Kimi-K3 (Together AI): input price raised, $2.70 → $3.00 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Kimi-K3 (Together AI): cached input price raised, $0.27 → $0.30 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Muse-Spark-Open-816B-A42B (Together AI): newly listed at $1.25 input / $4.25 output per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--meta-models-muse-spark-open-816b-a42b/https://aobaworks.com/per-million/model/together-ai--meta-models-muse-spark-open-816b-a42b/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.gpt-5.5-cyber-preview (OpenAI): newly listed at $12.50 input / $75.00 output per 1M tokenshttps://aobaworks.com/per-million/model/openai--gpt-5-5-cyber-preview/https://aobaworks.com/per-million/model/openai--gpt-5-5-cyber-preview/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.gemini-4-argon (Google Gemini API): newly listed at $2.00 input / $10.00 output per 1M tokenshttps://aobaworks.com/per-million/model/google-gemini--gemini-4-argon/https://aobaworks.com/per-million/model/google-gemini--gemini-4-argon/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.muse-spark-open (Fireworks AI): newly listed at $1.25 input / $4.25 output per 1M tokenshttps://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-muse-spark-open/https://aobaworks.com/per-million/model/fireworks-ai--accounts-fireworks-models-muse-spark-open/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.DeepSeek-V4.1-Flash (DeepInfra): newly listed at $0.14 input / $0.42 output per 1M tokenshttps://aobaworks.com/per-million/model/deepinfra--deepseek-ai-deepseek-v4-1-flash/https://aobaworks.com/per-million/model/deepinfra--deepseek-ai-deepseek-v4-1-flash/Mon, 19 Oct 2026 00:00:00 +0000Recorded between 2026-10-12 and 2026-10-19.Tev1-4B-experimental (Together AI): cached input price raised, $0.04 → — per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--together-tev1-4b-experimental/https://aobaworks.com/per-million/model/together-ai--together-tev1-4b-experimental/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Qwen3.8-Flash (Together AI): output price raised, $0.28 → $0.47 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-8-flash/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-8-flash/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Qwen3.8-Flash (Together AI): input price raised, $0.09 → $0.15 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-8-flash/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-8-flash/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Qwen3.7-Max (Together AI): output price raised, $4.50 → $7.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Qwen3.7-Max (Together AI): input price raised, $1.50 → $2.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Qwen3.7-Max (Together AI): cached input price raised, $0.30 → $0.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/https://aobaworks.com/per-million/model/together-ai--qwen-qwen3-7-max/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Kimi-K3 (Together AI): output price cut, $15.00 → $13.50 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Kimi-K3 (Together AI): input price cut, $3.00 → $2.70 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.Kimi-K3 (Together AI): cached input price cut, $0.30 → $0.27 per 1M tokenshttps://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/https://aobaworks.com/per-million/model/together-ai--moonshotai-kimi-k3/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.gpt-rosalind-discovery (OpenAI): newly listed at $5.00 input / $25.00 output per 1M tokenshttps://aobaworks.com/per-million/model/openai--gpt-rosalind-discovery/https://aobaworks.com/per-million/model/openai--gpt-rosalind-discovery/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.mistral-large-4 (Mistral AI): newly listed at $0.68 input / $2.09 output per 1M tokenshttps://aobaworks.com/per-million/model/mistral--mistral-large-4/https://aobaworks.com/per-million/model/mistral--mistral-large-4/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.mistral-large-4-0 (Mistral AI): newly listed at $0.68 input / $2.09 output per 1M tokenshttps://aobaworks.com/per-million/model/mistral--mistral-large-4-0/https://aobaworks.com/per-million/model/mistral--mistral-large-4-0/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.claude-sonnet-5-5 (Anthropic): cached input price cut, $0.20 → $0.10 per 1M tokenshttps://aobaworks.com/per-million/model/anthropic--claude-sonnet-5-5/https://aobaworks.com/per-million/model/anthropic--claude-sonnet-5-5/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.claude-haiku-5-5 (Anthropic): newly listed at $0.10 input / $0.50 output per 1M tokenshttps://aobaworks.com/per-million/model/anthropic--claude-haiku-5-5/https://aobaworks.com/per-million/model/anthropic--claude-haiku-5-5/Mon, 12 Oct 2026 00:00:00 +0000Recorded between 2026-10-05 and 2026-10-12.grok-4-latest (xAI): no longer in the price listhttps://aobaworks.com/per-million/changes/https://aobaworks.com/per-million/changes/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4-fast-reasoning (xAI): no longer in the price listhttps://aobaworks.com/per-million/changes/https://aobaworks.com/per-million/changes/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4-fast-non-reasoning (xAI): no longer in the price listhttps://aobaworks.com/per-million/changes/https://aobaworks.com/per-million/changes/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.7 (xAI): newly listed at $2.00 input / $6.00 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-7/https://aobaworks.com/per-million/model/xai--grok-4-7/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.3-latest (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-3-latest/https://aobaworks.com/per-million/model/xai--grok-4-3-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.3 (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-3/https://aobaworks.com/per-million/model/xai--grok-4-3/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4 (xAI): no longer in the price listhttps://aobaworks.com/per-million/changes/https://aobaworks.com/per-million/changes/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-reasoning-latest (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-reasoning-latest/https://aobaworks.com/per-million/model/xai--grok-4-20-reasoning-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-reasoning-gv2 (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-reasoning-gv2/https://aobaworks.com/per-million/model/xai--grok-4-20-reasoning-gv2/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-reasoning (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-non-reasoning-latest (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning-latest/https://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-non-reasoning-gv2 (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning-gv2/https://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning-gv2/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-non-reasoning (xAI): batch input price added, — → $1.00 per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-non-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-reasoning-latest (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-reasoning-latest/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-reasoning-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-non-reasoning-latest (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-non-reasoning-latest/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-non-reasoning-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-latest (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-latest/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-latest/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-0304-reasoning (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-0304-non-reasoning (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304-non-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304-non-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-experimental-beta-0304 (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304/https://aobaworks.com/per-million/model/xai--grok-4-20-experimental-beta-0304/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-beta-reasoning (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-beta-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-beta-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.grok-4.20-beta-non-reasoning (xAI): newly listed at $1.25 input / $2.50 output per 1M tokenshttps://aobaworks.com/per-million/model/xai--grok-4-20-beta-non-reasoning/https://aobaworks.com/per-million/model/xai--grok-4-20-beta-non-reasoning/Mon, 05 Oct 2026 00:00:00 +0000Recorded between 2026-09-19 and 2026-10-05.