Model prices
Every rate used by the inference cost calculator, in USD per 1 million tokens on the standard API tier. Verified July 2026 against the provider pricing pages linked below.
~~~
OpenAI
pricing source ↗| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| GPT-5.5 | flagship | $5.00 | $0.50 | $30.00 | 1M | Flagship general-purpose: hard agents, coding, research |
| GPT-5.4 | flagship | $2.50 | $0.25 | $15.00 | 1M | Frontier quality at half the GPT-5.5 rate; production default |
| GPT-5.4 mini | workhorse | $0.75 | $0.075 | $4.50 | 400K | High-volume chat, RAG, extraction, support bots |
| GPT-5 mini | workhorse | $0.25 | $0.025 | $2.00 | 400K | Budget general tasks with solid quality |
| GPT-5.4 nano | budget | $0.20 | $0.020 | $1.25 | 400K | Routing, tagging, classification, simple summaries |
| GPT-5 nano | budget | $0.050 | $0.005 | $0.40 | 400K | Cheapest OpenAI model for infrastructure calls |
Anthropic
pricing source ↗| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| Claude Fable 5 | flagship | $10.00 | $1.00 | $50.00 | 1M | Next-gen intelligence for long-running agents |
| Claude Opus 4.8 | flagship | $5.00 | $0.50 | $25.00 | 1M | Complex agentic coding and enterprise work |
| Claude Sonnet 5 | workhorse | $3.00 | $0.30 | $15.00 | 1M | Best speed/intelligence balance; daily-driver agentsIntro pricing $2/$10 through Aug 31, 2026. Standard price shown. |
| Claude Haiku 4.5 | workhorse | $1.00 | $0.10 | $5.00 | 200K | Fast near-frontier chat and tool use |
| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro | flagship | $2.00 | $0.20 | $12.00 | 2M | Flagship reasoning with industry-largest contextPrompts >200K tokens billed at $4/$18. |
| Gemini 3.5 Flash | workhorse | $1.50 | $0.15 | $9.00 | 1M | Agentic tasks and coding; beats 3.1 Pro on some coding |
| Gemini 3 Flash | workhorse | $0.50 | $0.050 | $3.00 | 1M | Fast multimodal default; strong price/performance |
| Gemini 3.1 Flash-Lite | budget | $0.25 | $0.025 | $1.50 | 1M | Bulk simple tasks, translation, extraction |
| Gemini 2.5 Flash-Lite | budget | $0.10 | $0.010 | $0.40 | 1M | Cheapest Google tier for very high volume |
| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| Grok 4.3 | workhorse | $1.25 | $0.20 | $2.50 | 1M | Aggressively priced frontier-class chat and tool use |
Mistral
pricing source ↗| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| Mistral Large 3open | workhorse | $0.50 | — | $1.50 | 256K | Open-weight European frontier; multimodal MoE |
| Mistral Small 3open | budget | $0.10 | — | $0.30 | 128K | Cheap general tasks; open-weight |
| Ministral 8Bopen | budget | $0.10 | — | $0.10 | 128K | Edge and embedded deployments |
OpenRouter
pricing source ↗Aggregator for open-weight models. Listed price is the default routing; actual price varies by underlying provider.
| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| DeepSeek V4 Proopen | workhorse | $0.435 | — | $0.87 | 1M | Frontier-class reasoning and coding at budget rates |
| DeepSeek V4 Flashopen | budget | $0.090 | — | $0.18 | 1M | The open-weight price leader for chat and agents |
| Kimi K2.6open | workhorse | $0.60 | — | $3.40 | 262K | Strong open-weight agentic and writing model |
| Llama 4 Maverickopen | budget | $0.15 | — | $0.60 | 1M | Multimodal open-weight with huge context |
| Llama 4 Scoutopen | budget | $0.10 | — | $0.30 | 10M | Cheap long-context summarization and search |
Workers AI
pricing source ↗Cloudflare edge inference. Billed in neurons ($0.011 per 1k); per-token equivalents shown. 10k neurons/day free.
| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Best for |
|---|---|---|---|---|---|---|
| GPT-OSS 120Bopen | workhorse | $0.35 | — | $0.75 | 128K | OpenAI's open-weight model at the edge, no cold starts |
| Llama 3.3 70Bopen | workhorse | $0.293 | — | $2.253 | 131K | Capable open-weight default on Cloudflare's edge |
| Llama 3.1 8B (fast)open | budget | $0.045 | — | $0.384 | 131K | Very cheap edge inference for simple tasks |
| Llama 3.2 3Bopen | budget | $0.051 | — | $0.335 | 128K | Lightweight classification and drafting |
| Llama 3.2 1Bopen | budget | $0.027 | — | $0.201 | 128K | The cheapest credible model for routing/tagging |