AI model price report — week 44, 2026
100 price movements across 7 providers. This report is generated from the same dataset that powers the JSON API and the raw changelog — 1,557 priced chat models across 32 providers. Dataset refreshed 2026-10-28 12:57 UTC.
Priced chat models
1,557
1,657 endpoints total
Cheapest input
$0.01
Qwen2.5 Coder 7B · Nebius
Median input price
$0.6
half of tracked models are cheaper
Models under $1/1M in
976
cheapest tier on the market
Price movements this week
| Model | Provider | Field | Before | After | Change |
|---|---|---|---|---|---|
| Gemini Pro | Google Gemini | input per 1m | $1.25 | $2 | +60.0% |
| Gemini Pro | Google Gemini | output per 1m | $10 | $12 | +20.0% |
| Gemini Pro | Google Gemini | cached input per 1m | $0.125 | $0.2 | +60.0% |
| Gemini Robotics Er 2 Preview | Google Gemini | input per 1m | $2 | $1 | -50.0% |
| Gemini Robotics Er 2 Preview | Google Gemini | output per 1m | $10 | $5 | -50.0% |
| Gemini Robotics Er 2 Preview | Google Gemini | cached input per 1m | $0.2 | $0.1 | -50.0% |
| Gemini Robotics Er 2 Streaming Preview | Google Gemini | input per 1m | $2 | $1 | -50.0% |
| Gemini Robotics Er 2 Streaming Preview | Google Gemini | output per 1m | $10 | $5 | -50.0% |
| Gemini Flash | Google Gemini | input per 1m | $0.3 | $0.75 | +150.0% |
| Gemini Flash | Google Gemini | output per 1m | $2.5 | $3.75 | +50.0% |
| Gemini Flash | Google Gemini | cached input per 1m | $0.03 | $0.075 | +150.0% |
| Gemini Flash Lite | Google Gemini | input per 1m | $0.1 | $0.3 | +200.0% |
| Gemini Flash Lite | Google Gemini | output per 1m | $0.4 | $2.5 | +525.0% |
| Gemini Flash Lite | Google Gemini | cached input per 1m | $0.01 | $0.03 | +200.0% |
| GPT 5.6 Sol | Perplexity | input per 1m | $5 | $4 | -20.0% |
| GPT 5.6 Sol | Perplexity | output per 1m | $30 | $20 | -33.3% |
| GPT 5.6 Sol | Perplexity | cached input per 1m | $0.5 | $0.4 | -20.0% |
| O1 | Azure OpenAI | input per 1m | $15 | $16.5 | +10.0% |
| O1 | Azure OpenAI | output per 1m | $60 | $66 | +10.0% |
| O1 | Azure OpenAI | cached input per 1m | $7.5 | $8.25 | +10.0% |
| O1 Preview | Azure OpenAI | input per 1m | $15 | $16.5 | +10.0% |
| O1 Preview | Azure OpenAI | output per 1m | $60 | $66 | +10.0% |
| O1 Preview | Azure OpenAI | cached input per 1m | $7.5 | $8.25 | +10.0% |
| GPT 4 Turbo | Azure OpenAI | input per 1m | $10 | $11 | +10.0% |
| GPT 4 Turbo | Azure OpenAI | output per 1m | $30 | $33 | +10.0% |
| GPT 4 Turbo | Azure OpenAI | input per 1m | $10 | $11 | +10.0% |
| GPT 4 Turbo | Azure OpenAI | output per 1m | $30 | $33 | +10.0% |
| GPT 4 Turbo Vision Preview | Azure OpenAI | input per 1m | $10 | $11 | +10.0% |
| GPT 4 Turbo Vision Preview | Azure OpenAI | output per 1m | $30 | $33 | +10.0% |
| GPT 5.6 | Azure OpenAI | input per 1m | $5 | $4 | -20.0% |
| GPT 5.6 | Azure OpenAI | output per 1m | $30 | $20 | -33.3% |
| GPT 5.6 | Azure OpenAI | cached input per 1m | $0.5 | $0.4 | -20.0% |
| GPT 5.6 Sol | Azure OpenAI | input per 1m | $5 | $4 | -20.0% |
| GPT 5.6 Sol | Azure OpenAI | output per 1m | $30 | $20 | -33.3% |
| GPT 5.6 Sol | Azure OpenAI | cached input per 1m | $0.5 | $0.4 | -20.0% |
| GPT 4o | Azure OpenAI | input per 1m | $2.5 | $2.75 | +10.0% |
| GPT 4o | Azure OpenAI | output per 1m | $10 | $11 | +10.0% |
| GPT 4o | Azure OpenAI | cached input per 1m | $1.25 | $1.38 | +10.0% |
| GPT 5.1 | Azure OpenAI | input per 1m | $1.38 | $1.38 | -0.4% |
| GPT 5.1 | Azure OpenAI | cached input per 1m | $0.14 | $0.138 | -1.8% |
| GPT 5.1 Codex | Azure OpenAI | input per 1m | $1.38 | $1.38 | -0.4% |
| GPT 5.1 Codex | Azure OpenAI | cached input per 1m | $0.14 | $0.138 | -1.8% |
| GPT 5.1 Chat | Azure OpenAI | input per 1m | $1.38 | $1.25 | -9.4% |
| GPT 5.1 Chat | Azure OpenAI | output per 1m | $11 | $10 | -9.1% |
| GPT 5.1 Chat | Azure OpenAI | cached input per 1m | $0.14 | $0.125 | -10.7% |
| O3 Mini | Azure OpenAI | input per 1m | $1.1 | $1.21 | +10.0% |
| O3 Mini | Azure OpenAI | output per 1m | $4.4 | $4.84 | +10.0% |
| O3 Mini | Azure OpenAI | cached input per 1m | $0.55 | $0.605 | +10.0% |
| O1 Mini | Azure OpenAI | input per 1m | $1.21 | $1.1 | -9.1% |
| O1 Mini | Azure OpenAI | output per 1m | $4.84 | $4.4 | -9.1% |
| O1 Mini | Azure OpenAI | cached input per 1m | $0.605 | $0.55 | -9.1% |
| GPT 5.1 Codex Mini | Azure OpenAI | cached input per 1m | $0.028 | $0.028 | -1.8% |
| GPT 4o Mini | Azure OpenAI | input per 1m | $0.15 | $0.165 | +10.0% |
| GPT 4o Mini | Azure OpenAI | output per 1m | $0.6 | $0.66 | +10.0% |
| GPT 4o Mini Audio Preview | Azure OpenAI | input per 1m | $2.5 | $0.15 | -94.0% |
| GPT 4o Mini Audio Preview | Azure OpenAI | output per 1m | $10 | $0.6 | -94.0% |
| Text Embedding 3 Large | Azure OpenAI | input per 1m | $0.13 | $0.143 | +10.0% |
| Ada | Azure OpenAI | input per 1m | $0.1 | $0.11 | +10.0% |
| Text Embedding Ada 002 | Azure OpenAI | input per 1m | $0.1 | $0.11 | +10.0% |
| Text Embedding 3 Small | Azure OpenAI | input per 1m | $0.02 | $0.022 | +10.0% |
| Mistral.mistral Large 2402 V1:0 | Amazon Bedrock | input per 1m | $10.4 | $5.2 | -50.0% |
| Mistral.mistral Large 2402 V1:0 | Amazon Bedrock | output per 1m | $31.2 | $15.6 | -50.0% |
| Meta.llama3 1 405b Instruct V1:0 | Amazon Bedrock | input per 1m | $5.32 | $2.4 | -54.9% |
| Meta.llama3 1 405b Instruct V1:0 | Amazon Bedrock | output per 1m | $16 | $2.4 | -85.0% |
| Us.meta.llama3 1 405b Instruct V1:0 | Amazon Bedrock | input per 1m | $5.32 | $2.4 | -54.9% |
| Us.meta.llama3 1 405b Instruct V1:0 | Amazon Bedrock | output per 1m | $16 | $2.4 | -85.0% |
| Mistral.mistral Large 2407 V1:0 | Amazon Bedrock | input per 1m | $3 | $2 | -33.3% |
| Mistral.mistral Large 2407 V1:0 | Amazon Bedrock | output per 1m | $9 | $6 | -33.3% |
| Cohere.command Text V14 | Amazon Bedrock | input per 1m | $1.5 | $1 | -33.3% |
| Meta.llama3 1 70b Instruct V1:0 | Amazon Bedrock | input per 1m | $0.99 | $0.72 | -27.3% |
| Meta.llama3 1 70b Instruct V1:0 | Amazon Bedrock | output per 1m | $0.99 | $0.72 | -27.3% |
| Meta.llama3 2 90b Instruct V1:0 | Amazon Bedrock | input per 1m | $2 | $0.72 | -64.0% |
| Meta.llama3 2 90b Instruct V1:0 | Amazon Bedrock | output per 1m | $2 | $0.72 | -64.0% |
| Us.meta.llama3 1 70b Instruct V1:0 | Amazon Bedrock | input per 1m | $0.99 | $0.72 | -27.3% |
| Us.meta.llama3 1 70b Instruct V1:0 | Amazon Bedrock | output per 1m | $0.99 | $0.72 | -27.3% |
| Us.meta.llama3 2 90b Instruct V1:0 | Amazon Bedrock | input per 1m | $2 | $0.72 | -64.0% |
| Us.meta.llama3 2 90b Instruct V1:0 | Amazon Bedrock | output per 1m | $2 | $0.72 | -64.0% |
| Nvidia.nemotron Super 3 120b | Amazon Bedrock | input per 1m | $0.18 | $0.23 | +27.8% |
| Nvidia.nemotron Super 3 120b | Amazon Bedrock | output per 1m | $0.78 | $1.01 | +29.5% |
| Amazon.titan Text Express V1 | Amazon Bedrock | input per 1m | $1.3 | $0.2 | -84.6% |
| Amazon.titan Text Express V1 | Amazon Bedrock | output per 1m | $1.7 | $0.6 | -64.7% |
| Meta.llama3 2 11b Instruct V1:0 | Amazon Bedrock | input per 1m | $0.35 | $0.16 | -54.3% |
| Meta.llama3 2 11b Instruct V1:0 | Amazon Bedrock | output per 1m | $0.35 | $0.16 | -54.3% |
| Us.meta.llama3 2 11b Instruct V1:0 | Amazon Bedrock | input per 1m | $0.35 | $0.16 | -54.3% |
| Us.meta.llama3 2 11b Instruct V1:0 | Amazon Bedrock | output per 1m | $0.35 | $0.16 | -54.3% |
| Amazon.titan Text Lite V1 | Amazon Bedrock | input per 1m | $0.3 | $0.15 | -50.0% |
| Amazon.titan Text Lite V1 | Amazon Bedrock | output per 1m | $0.4 | $0.2 | -50.0% |
| Kimi K3 Us | Fireworks AI | input per 1m | $3.3 | $4.5 | +36.4% |
| Kimi K3 Us | Fireworks AI | output per 1m | $16.5 | $22.5 | +36.4% |
| Kimi K3 Us | Fireworks AI | cached input per 1m | $0.33 | $0.45 | +36.4% |
| Deepseek V4 Pro | Fireworks AI | input per 1m | $1.74 | $1.2 | -31.0% |
| Deepseek V4 Pro | Fireworks AI | output per 1m | $3.48 | $1.2 | -65.5% |
| Deepseek V4 Pro | Fireworks AI | cached input per 1m | $0.145 | $0.6 | +313.8% |
| Deepseek V4p1 Flash | Fireworks AI | input per 1m | $0.22 | $0.3 | +36.4% |
| Deepseek V4p1 Flash | Fireworks AI | output per 1m | $0.66 | $1.2 | +81.8% |
| Deepseek V4p1 Flash | Fireworks AI | cached input per 1m | $0.007 | $0.006 | -14.3% |
| Gemini 2.5 Flash | Replicate | input per 1m | $2.5 | $0.3 | -88.0% |
| Qwen3.7 Max | Together AI | input per 1m | $2.5 | $1.5 | -40.0% |
| Qwen3.7 Max | Together AI | output per 1m | $7.5 | $4.5 | -40.0% |
| Qwen3.7 Max | Together AI | cached input per 1m | $0.5 | $0.3 | -40.0% |
Biggest cuts
- Gemini 2.5 Pro Preview Tts-99.2%
- Ai21.jamba 1 5 Large V1:0-98.4%
- Ai21.jamba 1 5 Mini V1:0-98.4%
- Deepseek.v3.2-95.1%
- GPT 4o Mini Audio Preview-94.0%
Biggest increases
- Qwen3 Coder 480b Instruct Bf16+6300.0%
- Qwen3 Vl 8b Instruct+6300.0%
- Minimax M2+4700.0%
- Ernie 4p5 21b A3b Pt+3100.0%
- Ernie 4p5 300b A47b Pt+3100.0%
Models added
- Claude Opus 5 5Anthropic
- Claude Sonnet 5 5Anthropic
- Claude Haiku 5 5Anthropic
- Embed V5.0 ProCohere
- Embed V5.0 FastCohere
- Qwen3.8 FlashAlibaba DashScope
- Qwen3.8 Omni FlashAlibaba DashScope
- Deep Research Preview 04 2026Google Gemini
- Deep Research Max Preview 04 2026Google Gemini
- Deep Research Pro Preview 12 2025Google Gemini
- Gemini 4 ArgonGoogle Gemini
- Lyria Realtime ExpGoogle Gemini
Models retired
- Claude 3 OpusAnthropic
- Claude 4 OpusAnthropic
- Claude Opus 4 1Anthropic
- Claude Opus 4 1Anthropic
- Claude Opus 4Anthropic
- Claude 3 7 SonnetAnthropic
- Claude 4 SonnetAnthropic
- Claude Sonnet 4Anthropic
- Claude 3 HaikuAnthropic
- CommandCohere
- Embed English Light V2.0Cohere
- Embed English V2.0Cohere
Cheapest input tokens
The floor of the market as of this data refresh — what the input side of a bill costs per 1M tokens.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Qwen2.5 Coder 7B | Nebius | $0.01 | $0.03 | — | 33K |
| 2 | Qwen2.5 Coder 3B Instruct | Nscale | $0.01 | $0.03 | — | — |
| 3 | Qwen2.5 Coder 7B Instruct | Nscale | $0.01 | $0.03 | — | — |
| 4 | Nemotron 3.5 Lightning 30b A3b | Perplexity | $0.011 | $0.17 | $0.0011 | — |
| 5 | Granite 4.0 H Micro | Cloudflare Workers AI | $0.017 | $0.112 | — | 131K |
| 6 | Mistral Nemo Instruct 2407 | DeepInfra | $0.019 | $0.03 | — | 131K |
| 7 | Llama 3.2 3B Instruct | DeepInfra | $0.02 | $0.02 | — | 131K |
| 8 | Meta Llama 3.1 8B Instruct Turbo | DeepInfra | $0.02 | $0.04 | — | 131K |
| 9 | Gemma 4 E4B It | DeepInfra | $0.02 | $0.1 | — | 131K |
| 10 | Llama Guard 3 8B | Nebius | $0.02 | $0.06 | — | 128K |
| 11 | Meta Llama 3.1 8B Instruct | Nebius | $0.02 | $0.06 | — | 128K |
| 12 | Qwen2 VL 7B Instruct | Nebius | $0.02 | $0.06 | — | 131K |
12 models shown — estimate your monthly bill →
Best blended cost
Weighted 3:1 toward input tokens, which is how most chat and agent workloads actually bill.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
| 7 | Labs Leanstral 1 5 | Mistral AI | free | free | — | 262K |
| 8 | Labs Leanstral 1 5 1 | Mistral AI | free | free | — | 262K |
| 9 | Gemma 2b It Lora | Cloudflare Workers AI | free | free | — | 8K |
| 10 | Mistral 7b Instruct V0.2 Lora | Cloudflare Workers AI | free | free | — | 15K |
| 11 | Llama 2 7b Chat Hf Lora | Cloudflare Workers AI | free | free | — | 8K |
| 12 | Gemma 7b It Lora | Cloudflare Workers AI | free | free | — | 4K |
12 models shown — estimate your monthly bill →
Most expensive models tracked
The top of the market, for reference — what frontier pricing looks like against the floor above.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | O1 Pro | OpenAI | $150 | $600 | — | 200K |
| 2 | O1 Pro | OpenAI | $150 | $600 | — | 200K |
| 3 | GPT 4.5 Preview | Azure OpenAI | $75 | $150 | $37.5 | 128K |
| 4 | GPT 4 32k 0613 | Azure OpenAI | $60 | $120 | — | 33K |
| 5 | GPT 4 32k | Azure OpenAI | $60 | $120 | — | 33K |
| 6 | GPT 5.5 Pro | Azure OpenAI | $30 | $180 | $3 | 1.1M |
| 7 | GPT 5.5 Pro | Azure OpenAI | $30 | $180 | $3 | 1.1M |
| 8 | GPT 5.4 Pro | Azure OpenAI | $30 | $180 | $3 | 922K |
8 models shown — estimate your monthly bill →
What this costs in practice
Three common workloads priced at the cheapest rate available in the index this week.
| Workload | Priced at | Total |
|---|---|---|
| support bot · 10,000 chats/day for a month (1.2k in, 400 out) | Qwen2.5 Coder 7B · $0.01/$0.03 | $7.20 |
| 1,000,000 document summaries (8k in, 300 out) | Qwen2.5 Coder 7B · $0.01/$0.03 | $89.00 |
| RAG index · 100M embedding tokens | Pplx Embed V1 0.6b · $0.004/free | $0.40 |
Straight arithmetic from published list prices — no volume discounts, batch tiers or committed-use pricing applied. Run your own numbers in the cost calculator.
Provider price floors
Median and floor input price per provider across the models we track, and how many moved this week.
| Provider | Models | Floor in | Median in | Top in | Moved this week |
|---|---|---|---|---|---|
| Fireworks AI | 280 | $0.05 | $0.22 | $4.5 | — |
| DeepInfra | 136 | $0.019 | $0.27 | $16.5 | — |
| Novita AI | 132 | $0.02 | $0.28 | $4 | — |
| Amazon Bedrock | 117 | $0.042 | $1 | $27.5 | — |
| OpenAI | 114 | $0.05 | $2 | $150 | — |
| Azure OpenAI | 113 | $0.05 | $2 | $75 | — |
| Together AI | 92 | $0.02 | $0.5 | $3.5 | — |
| Perplexity | 79 | $0.011 | $1.25 | $10 | — |
| Nebius | 61 | $0.01 | $0.2 | $3 | — |
| Databricks | 58 | $0.05 | $1.75 | $30 | — |
| Mistral AI | 53 | $0.1 | $0.3 | $2 | — |
| Google Gemini | 43 | $0.1 | $1 | $2 | — |
| xAI | 43 | $1 | $1.25 | $2 | — |
| Replicate | 40 | $0.03 | $0.65 | $15 | — |
| Baseten | 32 | $0.1 | $0.6 | $3 | — |
| Cloudflare Workers AI | 30 | $0.017 | $0.351 | $1.92 | — |
| Ollama | 29 | — | — | — | — |
| Alibaba DashScope | 27 | $0.05 | $0.4 | $2.5 | — |
| Google Vertex AI | 26 | $0.075 | $1.25 | $4 | — |
| Voyage AI | 23 | — | — | — | — |
Largest context window
Gemini Exp 1206
2.1M
Free-tier models
46
published at $0 for input tokens
Tracked providers
32
with 1,557 priceable chat models
Frequently asked
› What does the 2026-w44 report measure?
It summarises every price difference detected between consecutive refresh runs of the dataset. Each refresh snapshots input, output and cached-input rates per 1M tokens for every tracked endpoint, then diffs that snapshot against the previous one; the movements listed on this page are those diffs, grouped by ISO week.
› Why does a week sometimes show no changes?
Because providers do not change published rates every week. A report with zero movements means every diff run in that week came back clean — the figures in the market snapshot sections still reflect the current dataset.
› Can I reuse this report?
Yes. The underlying data is published under CC BY 4.0 and served free at /api/models. Attribute Price per 1M with a link when you republish figures.