↓ Skip to main content
tomrochette.com
  1. Agents/

Model Provider Feature Matrix

Author
glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 16 minutes read (~3025 words)
agent-curated 550 comparison 24 fully-ai-generated 653 llm-pricing 3 llm=glm-5.3-flash 561 model-selection 3
Table of Contents

This matrix compares the seven model providers behind every model in the Model Selection guide, provider by provider, so the vendor choice is as visible as the model choice; prices below are as of 2026-10-19.

Provider choice is a bundle decision, list price, cache discount, batch policy, context flatness, weights, and where your subscription does and does not transfer, and the challengers win that bundle on every axis except subscriptions.

Legend: ✓ supported, ✗ not supported, ~ partial or conditional, ? not verified. Each column links to the provider’s canonical pricing page; every cell traces to the guide or to a source cited in its references.

The matrix
#

Provider Alibaba (Qwen) Anthropic (Claude) DeepSeek Google (Gemini) Moonshot AI (Kimi) OpenAI (GPT) Zhipu (GLM)
Flagship model Qwen3.8-Max, $2 / $6 Claude Fable 5.1, $10 / $50 DeepSeek V4 Pro, $1.32 / $3.96 peak, the Flash routing cancelled, rates continue Gemini 4 Argon, $2 / $10 launch rate through November 30, then $4 / $20 Kimi K3, $3 / $15 list (OpenRouter floor by input $0.238 / $16.00 on Wafer, the output floor at $0.80 / $3.00 on Relace after its same-day reprice, the aggregator listing moving to $0.239 / $11.936, as of 2026-10-19) GPT-6 Astra, $10 / $50 GLM-5.3, $1.40 / $4.40
Workhorse model Qwen3.8-Max doubles as the workhorse Claude Sonnet 5.5, $2 / $10 deepseek-flash (V4.1-Flash), $0.30 / $1.20 peak Gemini 4 Argon doubles as the workhorse at the launch rate; Gemini 3.1 Pro Preview, $2 / $12, stays listed kimi-k2.7-code, $0.95 / $4.00 list (host floor $0.67 / $3.35) gpt-6.1-sol, $2 / $10 GLM-5.3 covers the class at $1.40 / $4.40
Cheap model Qwen3.8-Flash, $0.15 / $0.47 Claude Haiku 5.5, $0.10 / $0.50 under 100K prompts, $0.50 / $2.50 past deepseek-flash doubles as the cheap tier, $0.15 / $0.60 off-peak Flash-Lite $0.25 / $1.50, 3.6 Flash $0.75 intro k2.7-code doubles as the cheap tier gpt-6-luna, $0.10 / $0.50 GLM-5.3-Flash, $0.15 / $0.50, GLM-4.7-Flash free
Coding-specialized model ? none in this guide (the open Coder family is separate) ✗ none, the general lineup carries coding ✗ none in the guide ✗ none in the guide ✓ kimi-k2.7-code ✓ gpt-5.3-codex, $1.75 / $14 ✗ none in the guide
Cached input discount ~ model tables name the discount, the billing note prices hits at one tenth ✓ one tenth, Opus 5.5 and Sonnet 5.5 at one twentieth, the Fable pair at one fortieth ✓ about one fiftieth on Flash, the deepest ~ about one tenth, Gemini 4 Argon at one twentieth ($0.10) ✓ one tenth on K3, one fifth on k2.7-code ✓ about one tenth ✓ about one fifth
Long-context policy ✓ 1M flat ~ 1M flat from Claude 4.6 onward, Haiku 5.5 repriced past a 100K prompt ✓ 1M flat, 384K max output ~ Gemini 3.1 Pro doubles beyond 200K, Gemini 4 Argon flat 1M ~ K3 flat 1M, k2.7-code 256K ~ doubles past thresholds ✓ 1M flat
Batch or time discounts ~ batch half price on Max ✓ batch half price ~ off-peak half price instead of batch ✓ batch half price ? not stated ✓ batch half price ? not stated
Live pricing windows ~ 1M-token free quota for new accounts, 90 days ~ Sonnet 5’s planned increase was cancelled ~ off-peak is standing policy; the 2026-09-14 Flash routing was cancelled, V4 Pro rates continue ~ Flash intro rate ends 2026-12-31; Argon’s launch rate doubles 2026-12-01 ~ HighSpeed variant at $1.90 / $8.00 ~ Sol promo through 2026-11-21 ✓ none; the 50% promo ended 2026-09-09 into the $0.15 / $0.50 list
Weights ✓ open weights (27B and Flash-Next) ✗ closed ✓ open weights ✗ closed ✓ open weights (K3, K2.7) ✗ closed ✓ open weights
Subscription includes an agent ? none verified ✓ Claude Code from Pro $20 to Max 20x $200 ✗ API and BYOK only ~ the Antigravity platform is free ~ Kimi OAuth reuse via Kimi Code, now under a rolling 5-hour rate window ✓ Codex from ChatGPT Free tier up ~ coding plans from $18/month
BYOK harness fit ~ OpenAI-compatible, rides OpenRouter or any compatible endpoint ~ subscription does not transfer to third-party harnesses ✓ native OpenCode provider, plus an Anthropic-format endpoint ? not verified here ✓ native OpenCode provider ~ API key works everywhere, the ChatGPT subscription now also signs into OpenCode directly ✓ native OpenCode provider

Reading the matrix
#

I read this table as a bundle scorecard rather than a price list, because the rows move together in ways the model-level table hides. The big three monetize closed frontier weights plus subscriptions, and the four challengers monetize cheap tokens plus open weights, with almost no overlap in which rows they win. On the price rows the challengers sweep: every challenger flagship costs less out than the big-three workhorses, and Zhipu’s free GLM-4.7-Flash has no big-three analogue at any price. On the policy rows the field is closer than list prices suggest, and this is the part I check before switching: DeepSeek’s cache discount is the deepest at about one fiftieth on Flash, Alibaba’s model tables name a discount and its billing note prices hits at one tenth, and batch is half price at the big three and Qwen but unverified at Moonshot and Zhipu. Long context splits cleanly by flatness: Anthropic (except Haiku 5.5’s prompt-length repricing past 100K), DeepSeek, Alibaba, Moonshot K3, and Zhipu keep 1M pricing flat, while OpenAI and Google double past thresholds, which decides whole-repository prompting before any model-quality question. The weights row is the quiet differentiator: open weights from Alibaba, DeepSeek, Moonshot, and Zhipu mean a private deployment path the closed big three do not offer at all. The subscription row runs the other way: only OpenAI and Anthropic ship a first-party agent on subscription, and Anthropic’s is the one that explicitly does not transfer to third-party harnesses.

Choosing between providers
#

  • Default workhorse loop: OpenAI, Anthropic, and Google price identically at the tier, so pick by harness fit and let the challenger prices below pressure that default yearly.
  • Price-floor BYOK loops: DeepSeek and Zhipu, with Alibaba close behind at flagship quality for $6 out.
  • Flat 1M context: Anthropic above the cheap tier, DeepSeek, Alibaba, Moonshot K3, and Zhipu, the vendors that keep whole-repository reads predictable.
  • Coding-specialized spend: Moonshot’s k2.7-code or OpenAI’s gpt-5.3-codex, the only two columns with a model built for the job.
  • Weights you can host: Alibaba, DeepSeek, Moonshot, or Zhipu, and none of the big three at any price.
  • Subscription-first teams: OpenAI or Anthropic, and read the transfer row before assuming the subscription follows your harness.

Changes
#

  • 2026-09-08 - Created on owner request with seven provider columns sorted alphabetically as a companion to the model selection guide.
  • 2026-09-08 - Moved Zhipu’s long-context cell to 1M flat on models.dev evidence, widened the flat-1M club to five, and added the models.dev reference.
  • 2026-09-09 - Updated the Moonshot workhorse and pricing-window cells and fixed the Zhipu cached-price prose contradiction.
  • 2026-09-10 - Moved the DeepSeek workhorse cell to deepseek-flash and updated the Zhipu cells as the promo resolved to list.
  • 2026-09-12 - Updated the DeepSeek cells for the routing cancellation and gave Moonshot’s flagship cell the OpenRouter price with the platform lag.
  • 2026-09-16 - Updated the Moonshot workhorse cell for OpenRouter’s kimi-k2.7-code cut to $3.21 and moved its cache discount to one quarter.
  • 2026-09-18 - Updated the Moonshot flagship cell for OpenRouter’s kimi-k3 cut to $2.10 / $10.95.
  • 2026-09-20 - Updated the Moonshot flagship cell again for OpenRouter’s kimi-k3 cut to $1.70 / $8.50 with cache hits at $0.17, and moved its cache-discount cell from about one ninth to one tenth.
  • 2026-09-24 - Removed the verification preamble line on owner request.
  • 2026-09-25 - Re-grounded the Moonshot flagship and workhorse cells on Moonshot’s official list prices ($3/$15 and $0.95/$4.00) after the endpoints API showed the earlier “OpenRouter price with platform lag” readings were third-party host floors, and moved the OpenAI workhorse and cheap cells to the 2026-09-22 GPT-6 Sol and Luna releases.
  • 2026-09-27 - Refreshed against all seven pricing pages: noted the new Claude Opus 5.5 tier in the cache-discount cell, moved the Kimi K3 host floor to $0.88 / $4.90, and flagged gpt-5.6-terra’s removal from OpenAI’s pricing page in the workhorse cell.
  • 2026-09-29 - Synced with the guide’s refresh: the Anthropic workhorse cell moved to the 2026-09-28 Claude Sonnet 5.5 at the same $2 / $10, the gpt-5.6-terra removal note dropped from the OpenAI workhorse cell (it is listed again), and the Kimi K3 host floor moved to $0.40 / $10.00.
  • 2026-10-02 - Synced with the guide’s refresh: the OpenAI workhorse cell moved to the 2026-09-29 gpt-6.1-sol at the same $2 / $10 with cache hits at $0.10, all seven pricing pages re-verified with no other vendor moves, and the Moonshot host-floor spot readings updated (K3 $0.38 / $10.00, k2.7-code $0.67 / $3.35).
  • 2026-10-02 - Moved the Moonshot flagship cell’s OpenRouter host floor from $0.38 / $10.00 on Relace to $1.39 / $13.00 on InferenceNet; the k2.7-code floor host (Inceptron, $0.67 / $3.35) re-verified unchanged, and no other vendor cell moved.
  • 2026-10-03 - Moved the Moonshot flagship cell’s OpenRouter host floor again, from $1.39 / $13.00 on InferenceNet to $0.98 / $13.00 on Relace; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages.
  • 2026-10-04 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter host floor moved from $0.98 / $13.00 on Relace to $0.40 / $13.00, with InferenceNet at $0.72 / $13.00; Moonshot’s official $3 / $15 (its pricing page now serves its tables through a JS shell, so the read came from the same URL’s markdown render plus its official endpoint) and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-06 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter host floor moved again, from $0.40 / $13.00 to $0.96 / $13.00 on Relace with cache reads at $0.45, and Wafer sitting at $0.97 / $14.00; Moonshot’s official $3 / $15 endpoint (its pricing page read through the markdown render), the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-06 - Moved the Moonshot flagship cell’s OpenRouter host floor a sixth time in six days, from $0.96 / $13.00 to $0.66 / $13.00 on Relace (cache reads $0.30), with InferenceNet and Wafer at $0.83 / $14.00 and the aggregator listing at $0.83 / $14.00, and recorded Kimi Code’s own rolling 5-hour rate window in the Moonshot subscription cell per its membership docs; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged this run.
  • 2026-10-07 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter host floor moved a seventh time in seven days, from $0.66 / $13.00 to $0.61 / $13.00 on Relace with cache reads at $0.45, and the Alibaba cache-discount cell corrected, the billing page’s context-cache note prices hits at one tenth of input where the cell had said the rate was unpublished; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-10 - Synced with the guide’s refresh: the Claude cheap cell moved to the 2026-10-07 Haiku 5.5 ($0.10 / $0.50 under 100K prompts) with the Anthropic long-context cell and the flat-1M recommendation noting its prompt-length repricing, and the Moonshot flagship cell’s OpenRouter host floor moved an eighth time in eight days, from $0.61 / $13.00 on Relace to $0.37 / $14.89 on Wafer (cache reads $0.30); Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-11 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter host floor moved a ninth time in nine days, from $0.37 / $14.89 on Wafer to $0.45 / $16.50 on Wafer (cache reads $0.30), with InferenceNet at $0.73 / $10.00 and the aggregator listing at $0.73 / $10.00, and the gpt-5.6-terra and gpt-5.6-luna cells’ off-the-page state flipped back to listed at launch prices on OpenAI’s pricing page; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-13 - Moved the Moonshot flagship cell’s OpenRouter host floor from $0.45 / $16.50 on Wafer to $0.73 / $13.50 on InferenceNet (cache reads $0.55), with Wafer’s cheap endpoint at $0.78 / $24.00 (cache reads $0.30) and the aggregator listing at $0.73 / $15.00; moved the Anthropic cache-discount cell’s Sonnet 5.5 into the one-twentieth group per the pricing page’s 0.05x multiplier footnote, and corrected the OpenAI BYOK cell, OpenCode’s provider docs now sign ChatGPT subscriptions in directly; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-13 - Synced with the guide’s refresh: the Google flagship and workhorse cells moved to the same-day-launched Gemini 4 Argon ($2 / $10 launch rate through November 30, then $4 / $20 per the pricing page), its cache-discount cell noting the one-twentieth hit and its windows cell the December 1 doubling, and the Moonshot flagship cell’s OpenRouter host floor moved from $0.73 / $13.50 to $0.73 / $10.00 on InferenceNet; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-16 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter floor moved to $0.29 / $28.00 by input on Wafer with the aggregator listing at $0.304 / $11.936 (cache reads $0.21), and the intro gained its as-of clause; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-17 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter floor moved to $0.27 / $14.2307 by input on Relace with the output floor at $0.504 / $8.10 on Sail Research’s fp4 endpoint and the aggregator listing holding at $0.304 / $11.936 (cache reads $0.21); Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-18 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter floor moved to $0.27 / $14.00 by input on Relace (the output leg down from $14.2307) with the aggregator listing holding at $0.304 / $11.936 (cache reads $0.21) and the output floor unchanged at $0.504 / $8.10 on Sail Research’s fp4 endpoint; Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.
  • 2026-10-19 - Synced with the guide’s refresh: the Moonshot flagship cell’s OpenRouter floor moved to $0.238 / $16.00 by input on Wafer, the output floor collapsed to $0.80 / $3.00 on Relace after its wholesale reprice from $0.27 / $14.00, and the aggregator listing’s input leg dropped to $0.239 / $11.936 (cache reads $0.21); Moonshot’s official $3 / $15 endpoint, the k2.7-code floor (Inceptron, $0.67 / $3.35), and every other vendor cell re-verified unchanged against all seven pricing pages, OpenRouter, and models.dev.

See also
#

References
#

  • https://platform.openai.com/docs/pricing - GPT-5.6 and GPT-6 family prices including the 2026-09-22 GPT-6 Sol and Luna, the 2026-09-29 gpt-6.1-sol, batch discount, long-context doubling, gpt-5.6-cyber added under Daybreak; gpt-5.6-terra and gpt-5.6-luna back on the page at this fetch at launch prices, a day after their fourth recorded drop, with OpenRouter serving both at the same rates (fetched 2026-10-19)
  • https://platform.claude.com/docs/en/about-claude/pricing - Claude lineup prices including Sonnet 5.5 ($2/$10, 2026-09-28), Opus 5.5 ($4/$20, 5% cache), and Haiku 5.5 ($0.10/$0.50 under 100K prompts, 2026-10-07), cache multipliers, 1M-context policy with the Haiku 5.5 exception (fetched 2026-10-19, all cells unchanged)
  • https://cloud.google.com/vertex-ai/generative-ai/pricing - Gemini 3 family prices, intro windows (the 2026-12-31 end and 2027-01-01 doubling both stated on the page), long-context and batch rates, 3.8 Flash Cyber at $1.50 / $7.50, and Gemini 4 Argon’s launch table ($2 / $10 through November 30, then $4 / $20) (fetched 2026-10-19, all cells unchanged)
  • https://help.aliyun.com/zh/model-studio/billing-for-model-studio - Qwen3.8-Max and Qwen3.8-Flash official prices, batch half price, context-cache note (explicit-cache hits at one tenth of input, writes at 1.25x), free quota, qwen3.8-max-prime speed variant (fetched 2026-10-19, all cells unchanged)
  • https://api-docs.deepseek.com/news/news260910 - the 2026-09-10 V4.1-Flash release and V4 Pro routing announcement behind the DeepSeek column’s workhorse and windows cells (fetched 2026-09-10, routing cancelled per the DeepSeek pricing page fetched 2026-10-19)
  • https://openrouter.ai/api/v1/models - aggregator listings for the Qwen pair and the GPT-6 pair, serving gpt-5.6-terra and gpt-5.6-luna at their launch rates (fetched 2026-10-19)
  • https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints - per-provider endpoint prices separating Moonshot’s official list prices from third-party host floors, the floor now $0.238 / $16.00 by input on Wafer with the output floor at $0.80 / $3.00 on Relace, InferenceNet at $0.239 / $11.936 matching the aggregator listing (cache reads $0.21), Morph at $0.239 / $14.90, and Wafer’s second endpoint at $0.36 / $11.90, across a 26-endpoint roster (fetched 2026-10-19)
  • https://www.kimi.com/code/docs/en/kimi-code/membership.html - Kimi Code’s own rolling 5-hour rate window on top of the shared monthly credit pool, behind the Moonshot subscription cell (fetched 2026-10-13, re-fetched 200 on 2026-10-18)
  • https://models.dev - the community model list reference: model ids, release dates, and context windows behind the lineup, including the GPT-6 pair’s, Opus 5.5’s, Sonnet 5.5’s, and Haiku 5.5’s release dates, with no new releases from the seven covered providers since 2026-10-13 and the deepseek-flash entry re-stamped at the 2026-10-17 V4.1-Flash-1017 checkpoint (fetched 2026-10-19)