RoninForge / LLM API pricing

LLM API pricing, side by side

Token prices for six providers, taken from their official pricing pages and nothing else. Standard tier, USD per 1 million tokens, with the caching and long-context caveats that quietly change your bill.

Every number verified against the linked source on 2026-06-10. The spread is real: Mistral Small 4 costs $0.40 per combined 1M in + 1M out, GPT-5.5 Pro costs $210.00.

Anthropic

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
Claude Fable 5$10.00$1.00$50.00$60.001M
Claude Opus 4.8$5.00$0.50$25.00$30.001M
Claude Sonnet 4.6$3.00$0.30$15.00$18.001M
Claude Haiku 4.5$1.00$0.10$5.00$6.00-
  • Cached input is the cache read price (0.1x input). Cache writes cost extra: 1.25x input for 5-minute TTL, 2x for 1-hour TTL.
  • Batch API: 50 percent off input and output.
  • Fable 5, Opus 4.8/4.7/4.6, and Sonnet 4.6 include the full 1M-token context window at standard pricing.

OpenAI

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
GPT-5.5 Protiered$30.00-$180.00$210.00-
GPT-5.5tiered$5.00$0.50$30.00$35.00-
GPT-5.4tiered$2.50$0.25$15.00$17.50-
GPT-5.3-Codex$1.75$0.175$14.00$15.75-
GPT-5.4 mini$0.75$0.075$4.50$5.25-
GPT-5.4 nano$0.20$0.02$1.25$1.45-
  • GPT-5.5, GPT-5.5 Pro, and GPT-5.4 have a separate long-context tier (roughly 2x input, 1.5x output). The threshold is not stated on the pricing page.
  • Batch and Flex: 50 percent off. Priority tier costs roughly 2x standard.

Google

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
Gemini 3.1 Pro (preview)tiered$2.00$0.20$12.00$14.00-
Gemini 3.5 Flash$1.50$0.15$9.00$10.50-
Gemini 2.5 Protiered$1.25$0.125$10.00$11.25-
Gemini 3 Flash (preview)$0.50$0.05$3.00$3.50-
Gemini 3.1 Flash-Lite$0.25$0.025$1.50$1.75-
  • Gemini 3.1 Pro and 2.5 Pro charge higher rates for prompts above 200K tokens (3.1 Pro: $4.00 in / $18.00 out).
  • Flash models charge more for audio input than text input. Rates shown are text/image/video.
  • Context caching storage costs $1.00 per 1M tokens per hour on top of cached-input rates.

DeepSeek

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
DeepSeek V4 Pro$0.44$0.0036$0.87$1.311M
DeepSeek V4 Flash$0.14$0.0028$0.28$0.421M
  • Cached input is the cache-hit price; cache misses pay the normal input rate.
  • deepseek-chat and deepseek-reasoner aliases deprecate 2026-07-24.

Mistral

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
Magistral Medium$2.00-$5.00$7.00-
Mistral Medium 3.5$1.50-$7.50$9.00-
Mistral Large 3$0.50-$1.50$2.00-
Codestral$0.30-$0.90$1.20-
Mistral Small 4$0.10-$0.30$0.40-
  • Mistral Large 3 is priced below the newer Mistral Medium 3.5 on the official page (verified twice on 2026-06-10).
  • Batch API: 50 percent off.

xAI

official pricing page
ModelInput /1MCached /1MOutput /1M1M in + 1M outContext
Grok 4.3$1.25$0.20$2.50$3.751M
Grok 4.20 (reasoning)$1.25$0.20$2.50$3.751M
Grok Build 0.1$1.00$0.20$2.00$3.00256K
  • Batch API: 20 to 50 percent off standard rates, varies per model.

How to read this table honestly

  • Cached input is not one thing. Anthropic and DeepSeek list a cache-read price; Anthropic also bills cache writes (1.25x input), Google bills cache storage per hour. Two providers with the same "cached" number can produce different bills.
  • "Tiered" means the listed price is the floor. OpenAI's GPT-5.5/5.4 and Google's Pro models charge roughly double for long-context requests, which is exactly what agent workflows produce.
  • Batch discounts are large. Anthropic, OpenAI, and Mistral all offer 50 percent off for async batch workloads; xAI 20 to 50 percent.
  • Excluded providers are excluded for a reason. Meta Llama API, Cohere, and Amazon Nova render their prices client-side, so they could not be verified from source. No number on this page is quoted from a third-party blog.

Copilot AI Credits calculator

GitHub Copilot now bills these same token rates through AI credits. Estimate your monthly burn against your plan allowance.

Open the calculator

BudgetClaw for Claude Code

Hard daily spend caps and per-branch cost attribution for Claude Code. Reads local telemetry only: zero keys, zero prompts, zero latency added.

Set a spend cap